To see the other types of publications on this topic, follow the link: Local extensive binary pattern.
Dissertations / Theses on the topic 'Local extensive binary pattern'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Local extensive binary pattern.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Chan, Chi Ho. "Multi-scale local Binary Pattern Histogram for Face Recognition." Thesis, University of Surrey, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.493135.
Full textAbstract:
Recently, the research in face recognition has focused on developing a face representation that is capable of capturing the relevant information in a manner which is invariant to facial expression and illumination. Motivated by a simple but powerful texture descriptor, called Local Binary Pattern (LBP), our proposed system extends this descriptor to evoke multiresolution and multispectral analysis for face recognition. The first descriptor, namely Multi-scale Local Binary Pattern Histogram (MLBPH), provides a robust system which is relatively insensitive to localisation errors because it benefits from the multiresolution information captured from the regional histogram.
2
Lindahl, Tobias. "Study of Local Binary Patterns." Thesis, Linköping University, Department of Science and Technology, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-9415.
Full textAbstract:
<p>This Masters thesis studies the concept of local binary patterns, which describe the neighbourhood of a pixel in a digital image by binary derivatives. The operator is often used in texture analysis and has been successfully used in facial recognition.</p><p>This thesis suggests two methods based on some basic ideas of Björn Kruse and studies of literature on the subject. The first suggested method presented is an algorithm which reproduces images from their local binary patterns by a kind of integration of the binary derivatives. This method is a way to prove the preservation of information. The second suggested method is a technique of interpolating missing pixels in a single CCD camera based on local binary patterns and machine learning. The algorithm has shown some very promising results even though in its current form it does not keep up with the best algorithms of today.</p>
3
Mäenpää, T. (Topi). "The local binary pattern approach to texture analysis — extensions and applications." Doctoral thesis, University of Oulu, 2003. http://urn.fi/urn:isbn:9514270762.
Full textAbstract:
Abstract
This thesis presents extensions to the local binary pattern (LBP) texture analysis operator. The operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. It is made invariant against the rotation of the image domain, and supplemented with a rotation invariant measure of local contrast. The LBP is proposed as a unifying texture model that describes the formation of a texture with micro-textons and their statistical placement rules.
The basic LBP is extended to facilitate the analysis of textures with multiple scales by combining neighborhoods with different sizes. The possible instability in sparse sampling is addressed with Gaussian low-pass filtering, which seems to be somewhat helpful.
Cellular automata are used as texture features, presumably for the first time ever. With a straightforward inversion algorithm, arbitrarily large binary neighborhoods are encoded with an eight-bit cellular automaton rule, resulting in a very compact multi-scale texture descriptor. The performance of the new operator is shown in an experiment involving textures with multiple spatial scales.
An opponent-color version of the LBP is introduced and applied to color textures. Good results are obtained in static illumination conditions. An empirical study with different color and texture measures however shows that color and texture should be treated separately.
A number of different applications of the LBP operator are presented, emphasizing real-time issues. A very fast software implementation of the operator is introduced, and different ways of speeding up classification are evaluated. The operator is successfully applied to industrial visual inspection applications and to image retrieval.
4
RIBEIRO, M. V. L. "Proposta de Local Binary Pattern Coerente e Incoerente na Categorização de Cenas." Universidade Federal do Espírito Santo, 2017. http://repositorio.ufes.br/handle/10/9682.
Full textAbstract:
Made available in DSpace on 2018-08-02T00:01:14Z (GMT). No. of bitstreams: 1
tese_9974_Dissertação de Mestrado - Matheus Ribeiro.pdf: 13133495 bytes, checksum: c89441388ef04fc065e4bfc94cdc216f (MD5)
Previous issue date: 2017-10-11<br>Este trabalho propõe um novo descritor visual de cenas a partir da técnica Local Binary Pattern (LBP) e explorando a informação espacial utilizando o algoritmo Color Coherent Vector (CCV). O LBP se caracteriza por ser uma técnica não linear e não paramétrica, dispensando conceitos intermediários no processo de descrição da imagem, tornando uma alternativa para usuários leigos com pouco conhecimento na área. Já a representação CCV mostrou ser uma técnica que busca mitigar o problema da falta de informação espacial pelos histogramas, expressando a imagem em pixeis coerentes e pixeis incoerentes sem que aumente a dimensionalidade dos dados. Nesse sentido, uma primeira abordagem foi a proposta das técnicas LBP Incoerente e LBP Coerente na classificação de cenas. Resultados preliminares, empregando-se K-NN como classificador, demonstraram que o LBP Incoerente apresenta um bom compromisso entre
acurácia e dimensão de representação dos dados. Em seguida, no intuito de se incluir o conceito de contexto, para mitigar o problema da localidade do LBP, foi proposto o Contextual Modified Local Binary Pattern Incoerente (CMLBP Incoerente), que modela a distribuição das estruturas locais através do LBP,
adicionando informação contextual, inspirado no algoritmo Contextual Modified Census Transform (CMCT). Entre outras características, o CMLBP Incoerente demonstrou capacidade em descartar regiões homogêneas, representadas pelos pixeis coerentes através do algoritmo CCV. Em experimentos realizados com bancos de dados consagrados na literatura, o CMLBP apresentou resultados melhores que as técnicas originais que não descartam os pixeis
coerentes, em quase todas as situações. Para cenas com muitos detalhes e informações os resultados foram satisfatórios e com um maior destaque, superando técnicas conhecidas na literatura. Os resultados obtidos foram encorajadores para a busca de um descritor com boa capacidade discriminante e baixa dimensionalidade na representação de imagens.
5
Doshi, Niraj P. "Multi-dimensional local binary pattern texture descriptors and their application for medical image analysis." Thesis, Loughborough University, 2014. https://dspace.lboro.ac.uk/2134/17332.
Full textAbstract:
Texture can be broadly stated as spatial variation of image intensities. Texture analysis and classification is a well researched area for its importance to many computer vision applications. Consequently, much research has focussed on deriving powerful and efficient texture descriptors. Local binary patterns (LBP) and its variants are simple yet powerful texture descriptors. LBP features describe the texture neighbourhood of a pixel using simple comparison operators, and are often calculated based on varying neighbourhood radii to provide multi-resolution texture descriptions. A comprehensive evaluation of different LBP variants on a common benchmark dataset is missing in the literature. This thesis presents the performance for different LBP variants on texture classification and retrieval tasks. The results show that multi-scale local binary pattern variance (LBPV) gives the best performance over eight benchmarked datasets. Furthermore, improvements to the Dominant LBP (D-LBP) by ranking dominant patterns over complete training set and Compound LBP (CM-LBP) by considering 16 bits binary codes are suggested which are shown to outperform their original counterparts. The main contribution of the thesis is the introduction of multi-dimensional LBP features, which preserve the relationships between different scales by building a multi-dimensional histogram. The results on benchmarked classification and retrieval datasets clearly show that the multi-dimensional LBP (MD-LBP) improves the results compared to conventional multi-scale LBP. The same principle is applied to LBPV (MD-LBPV), again leading to improved performance. The proposed variants result in relatively large feature lengths which is addressed using three different feature length reduction techniques. Principle component analysis (PCA) is shown to give the best performance when the feature length is reduced to match that of conventional multi-scale LBP. The proposed multi-dimensional LBP variants are applied for medical image analysis application. The first application is nailfold capillary (NC) image classification. Performance of MD-LBPV on NC images is highest, whereas for second application, HEp-2 cell classification, performance of MD-LBP is highest. It is observed that the proposed texture descriptors gives improved texture classification accuracy.
6
Eriksson, Josefine, and Lindelöf Anna. "Measuring Student Attention with Face Detection: : Viola-Jones versus Multi-Block Local Binary Pattern using OpenCV." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166416.
Full textAbstract:
The purpose of this study is to discuss and attempt to approach an answer to the question of how face detection could be used to measure attention in a lecture hall.The conclusion might help further studies in using face detection to provide teachers with tools which can be used to improve learning during lectures. Face detection in real time applications became possible in 2001 when Viola and Jones presented a new method several times faster than any previous attempt. In 2007 Liao et al. presented a method using multi-block local binary patterns (MB-LBP) for the purpose of overcoming the simplicity and limitations of the Viola-Jones method. Computer vision libraries such as OpenCV make it easy to implement such algorithms. It currently supports both the Viola-Jones algorithm and the MB-LBP algorithm. This study compared these two face detection methods to see how they perform in terms of sensitivity and precision and attempted to identified limitations of both methods when used to detect attention in a simulated lecture environment. The study was conducted using boosted algorithms and functionality provided by OpenCV. The input data consisted of a recorded simulated lecture with 6 subjects performing different poses, labeled either attention or no attention, during certain periods of time, each pose recognized from a previously recorded actual lecture as a commonly occurring pose. The most significant difference of performance identified in the study was that the MB-LBP method performed face detection in an image three times faster than for Viola-Jones which confirmed previous reported results. Both methods generated high sensitivity values for all poses, but low precision values for two of the poses.The ability of both methods to detect downward tilted faces contributed to a high number of false positives returned when subjects performed the two poses of subjects taking notes or subjects performing activities labeled as no attention. Due to the low precision values caused by this, both methods were not considered to measure attention effectively. It is therefore suggested to instead train a MB-LBP-based method for the specific task of measuring attention in a lecture hall by training it to reject downward-tilted faces and to accept only instances conforming to the chosen definition of attention.
7
Ylioinas, J. (Juha). "Towards optimal local binary patterns in texture and face description." Doctoral thesis, Oulun yliopisto, 2016. http://urn.fi/urn:isbn:9789526214498.
Full textAbstract:
Abstract Local binary patterns (LBP) are among the most popular image description methods and have been successfully applied in a diverse set of computer vision problems, covering texture classification, material categorization, face recognition, and image segmentation, to name only a few. The popularity of the LBP methodology can be verified by inspecting the number of existing studies about its different variations and extensions. The number of those studies is vast. Currently, the methodology has been acknowledged as one of the milestones in face recognition research. The starting point of this research is to gain more understanding of which principles the original LBP descriptor is based on. After gaining some degree of insight, yet another try is made to improve some steps of the LBP pipeline, consisted of image pre-processing, pattern sampling, pattern encoding, binning, and further histogram post-processing. The main contribution of this thesis is a bunch of novel LBP extensions that partly try to unify some of the existing derivatives and extensions. The basis for the design of the new additional LBP methodology is to maximise data-driven premises, at the same time minimizing the need for tuning by hand. Prior to local binary pattern extraction, the thesis presents an image upsampling step dubbed as image pre-interpolation. As a natural consequence of upsampling, a greater number of patterns can be extracted and binned to a histogram improving the representational performance of the final descriptor. To improve the following two steps of the LBP pipeline, namely pattern sampling and encoding, three different learning-based methods are introduced. Finally, a unifying model is presented for the last step of the LBP pipeline, namely for local binary pattern histogram post-processing. As a special case of this, a novel histogram smoothing scheme is proposed, which shares the motivation and the effects with the image pre-interpolation for the most of its part. Deriving descriptors for such face recognition problems as face verification or age estimation has been and continues to be among the most popular domains where LBP has ever been applied. This study is not an exception in that regard as the main investigations and conclusions here are made on the basis of how the proposed LBP variations perform especially in the problems of face recognition. The experimental part of the study demonstrates that the proposed methods, experimentally validated using publicly available texture and face datasets, yield results comparable to the best performing LBP variants found in the literature, reported with the corresponding benchmarks<br>Tiivistelmä Paikalliset binäärikuviot kuuluvat suosituimpiin menetelmiin kuville suoritettavassa piirteenirrotuksessa. Menetelmää on sovellettu moniin konenäön ongelmiin, kuten tekstuurien luokittelu, materiaalien luokittelu, kasvojen tunnistus ja kuvien segmentointi. Menetelmän suosiota kuvastaa hyvin siitä kehitettyjen erilaisten johdannaisten suuri lukumäärä ja se, että nykyään kyseinen menetelmien perhe on tunnustettu yhdeksi virstanpylvääksi kasvojentunnistuksen tutkimusalueella. Tämän tutkimuksen lähtökohtana on ymmärtää periaatteita, joihin tehokkaimpien paikallisten binäärikuvioiden suorituskyky perustuu. Tämän jälkeen tavoitteena on kehittää parannuksia menetelmän eri askelille, joita ovat kuvan esikäsittely, binäärikuvioiden näytteistys ja enkoodaus, sekä histogrammin koostaminen ja jälkikäsittely. Esiteltävien uusien menetelmien lähtökohtana on hyödyntää mahdollisimman paljon kohdesovelluksesta saatavaa tietoa automaattisesti. Ensimmäisenä menetelmänä esitellään kuvan ylösnäytteistykseen perustuva paikallisten binäärikuvioiden johdannainen. Ylösnäytteistyksen luonnollisena seurauksena saadaan näytteistettyä enemmän binäärikuvioita, jotka histogrammiin koottuna tekevät piirrevektorista alkuperäistä erottelevamman. Seuraavaksi esitellään kolme oppimiseen perustuvaa menetelmää paikallisten binäärikuvioiden laskemiseksi ja niiden enkoodaukseen. Lopuksi esitellään paikallisten binäärikuvioiden histogrammin jälkikäsittelyn yleistävä malli. Tähän malliin liittyen esitellään histogrammin silottamiseen tarkoitettu operaatio, jonka eräs tärkeimmistä motivaatioista on sama kuin kuvan ylösnäytteistämiseen perustuvalla johdannaisella. Erilaisten piirteenirrotusmenetelmien kehittäminen kasvojentunnistuksen osa-alueille on erittäin suosittu paikallisten binäärikuvioiden sovellusalue. Myös tässä työssä tutkittiin miten kehitetyt johdannaiset suoriutuvat näissä osa-ongelmissa. Tutkimuksen kokeellinen osuus ja siihen liittyvät numeeriset tulokset osoittavat, että esitellyt menetelmät ovat vertailukelpoisia kirjallisuudesta löytyvien parhaimpien paikallisten binäärikuvioiden johdannaisten kanssa
8
Nguyen, Thanh Le Vi. "Local Binary Pattern based algorithms for the discrimination and detection of crops and weeds with similar morphologies." Thesis, Edith Cowan University, Research Online, Perth, Western Australia, 2020. https://ro.ecu.edu.au/theses/2359.
Full textAbstract:
In cultivated agricultural fields, weeds are unwanted species that compete with the crop plants for nutrients, water, sunlight and soil, thus constraining their growth. Applying new real-time weed detection and spraying technologies to agriculture would enhance current farming practices, leading to higher crop yields and lower production costs. Various weed detection methods have been developed for Site-Specific Weed Management (SSWM) aimed at maximising the crop yield through efficient control of weeds. Blanket application of herbicide chemicals is currently the most popular weed eradication practice in weed management and weed invasion. However, the excessive use of herbicides has a detrimental impact on the human health, economy and environment. Before weeds are resistant to herbicides and respond better to weed control strategies, it is necessary to control them in the fallow, pre-sowing, early post-emergent and in pasture phases. Moreover, the development of herbicide resistance in weeds is the driving force for inventing precision and automation weed treatments. Various weed detection techniques have been developed to identify weed species in crop fields, aimed at improving the crop quality, reducing herbicide and water usage and minimising environmental impacts.
In this thesis, Local Binary Pattern (LBP)-based algorithms are developed and tested experimentally, which are based on extracting dominant plant features from camera images to precisely detecting weeds from crops in real time. Based on the efficient computation and robustness of the first LBP method, an improved LBP-based method is developed based on using three different LBP operators for plant feature extraction in conjunction with a Support Vector Machine (SVM) method for multiclass plant classification. A 24,000-image dataset, collected using a testing facility under simulated field conditions (Testbed system), is used for algorithm training, validation and testing. The dataset, which is published online under the name “bccr-segset”, consists of four subclasses: background, Canola (Brassica napus), Corn (Zea mays), and Wild radish (Raphanus raphanistrum). In addition, the dataset comprises plant images collected at four crop growth stages, for each subclass. The computer-controlled Testbed is designed to rapidly label plant images and generate the “bccr-segset” dataset. Experimental results show that the classification accuracy of the improved LBP-based algorithm is 91.85%, for the four classes.
Due to the similarity of the morphologies of the canola (crop) and wild radish (weed) leaves, the conventional LBP-based method has limited ability to discriminate broadleaf crops from weeds. To overcome this limitation and complex field conditions (illumination variation, poses, viewpoints, and occlusions), a novel LBP-based method (denoted k-FLBPCM) is developed to enhance the classification accuracy of crops and weeds with similar morphologies. Our contributions include (i) the use of opening and closing morphological operators in pre-processing of plant images, (ii) the development of the k-FLBPCM method by combining two methods, namely, the filtered local binary pattern (LBP) method and the contour-based masking method with a coefficient k, and (iii) the optimal use of SVM with the radial basis function (RBF) kernel to precisely identify broadleaf plants based on their distinctive features. The high performance of this k-FLBPCM method is demonstrated by experimentally attaining up to 98.63% classification accuracy at four different growth stages for all classes of the “bccr-segset” dataset.
To evaluate performance of the k-FLBPCM algorithm in real-time, a comparison analysis between our novel method (k-FLBPCM) and deep convolutional neural networks (DCNNs) is conducted on morphologically similar crops and weeds. Various DCNN models, namely VGG-16, VGG-19, ResNet50 and InceptionV3, are optimised, by fine-tuning their hyper-parameters, and tested. Based on the experimental results on the “bccr-segset” dataset collected from the laboratory and the “fieldtrip_can_weeds” dataset collected from the field under practical environments, the classification accuracies of the DCNN models and the k-FLBPCM method are almost similar. Another experiment is conducted by training the algorithms with plant images obtained at mature stages and testing them at early stages. In this case, the new k-FLBPCM method outperformed the state-of-the-art CNN models in identifying small leaf shapes of canola-radish (crop-weed) at early growth stages, with an order of magnitude lower error rates in comparison with DCNN models. Furthermore, the execution time of the k-FLBPCM method during the training and test phases was faster than the DCNN counterparts, with an identification time difference of approximately 0.224ms per image for the laboratory dataset and 0.346ms per image for the field dataset. These results demonstrate the ability of the k-FLBPCM method to rapidly detect weeds from crops of similar appearance in real time with less data, and generalize to different size plants better than the CNN-based methods.
9
Cui, Chen. "Adaptive weighted local textural features for illumination, expression and occlusion invariant face recognition." University of Dayton / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1374782158.
Full text
10
Guo, Y. (Yimo). "Image and video analysis by local descriptors and deformable image registration." Doctoral thesis, Oulun yliopisto, 2013. http://urn.fi/urn:isbn:9789526201412.
Full textAbstract:
Abstract Image description plays an important role in representing inherent properties of entities and scenes in static images. Within the last few decades, it has become a fundamental issue of many practical vision tasks, such as texture classification, face recognition, material categorization, and medical image processing. The study of static image analysis can also be extended to video analysis, such as dynamic texture recognition, classification and synthesis. This thesis contributes to the research and development of image and video analysis from two aspects. In the first part of this work, two image description methods are presented to provide discriminative representations for image classification. They are designed in unsupervised (i.e., class labels of texture images are not available) and supervised (i.e., class labels of texture images are available) manner, respectively. First, a supervised model is developed to learn discriminative local patterns, which formulates the image description as an integrated three-layered model to estimate an optimal pattern subset of interest by simultaneously considering the robustness, discriminative power and representation capability of features. Second, in the case that class labels of training images are unavailable, a linear configuration model is presented to describe microscopic image structures in an unsupervised manner, which is subsequently combined together with a local descriptor: local binary pattern (LBP). This description is theoretically verified to be rotation invariant and is able to provide a discriminative complement to the conventional LBPs. In the second part of the thesis, based on static image description and deformable image registration, video analysis is studied for the applications of dynamic texture description, synthesis and recognition. First, a dynamic texture synthesis model is proposed to create a continuous and infinitely varying stream of images given a finite input video, which stitches video clips in the time domain by selecting proper matching frames and organizing them into a logical order. Second, a method for the application of facial expression recognition, which formulates the dynamic facial expression recognition problem as the construction of longitudinal atlases and groupwise image registration problem, is proposed<br>Tiivistelmä Kuvan deskriptiolla on tärkeä rooli staattisissa kuvissa esiintyvien luontaisten kokonaisuuksien ja näkymien kuvaamisessa. Viime vuosikymmeninä se on tullut perustavaa laatua olevaksi ongelmaksi monissa käytännön konenäön tehtävissä, kuten tekstuurien luokittelu, kasvojen tunnistaminen, materiaalien luokittelu ja lääketieteellisten kuvien analysointi. Staattisen kuva-analyysin tutkimusala voidaan myös laajentaa videoanalyysiin, kuten dynaamisten tekstuurien tunnistukseen, luokitteluun ja synteesiin. Tämä väitöskirjatutkimus myötävaikuttaa kuva- ja videoanalyysin tutkimukseen ja kehittymiseen kahdesta näkökulmasta. Työn ensimmäisessä osassa esitetään kaksi kuvan deskriptiomenetelmää erottelukykyisten esitystapojen luomiseksi kuvien luokitteluun. Ne suunnitellaan ohjaamattomiksi (eli tekstuurikuvien luokkien leimoja ei ole käytettävissä) tai ohjatuiksi (eli luokkien leimat ovat saatavilla). Aluksi kehitetään ohjattu malli oppimaan erottelukykyisiä paikallisia kuvioita, mikä formuloi kuvan deskriptiomenetelmän integroituna kolmikerroksisena mallina - tavoitteena estimoida optimaalinen kiinnostavien kuvioiden alijoukko ottamalla samanaikaisesti huomioon piirteiden robustisuus, erottelukyky ja esityskapasiteetti. Seuraavaksi, sellaisia tapauksia varten, joissa luokkaleimoja ei ole saatavilla, esitetään työssä lineaarinen konfiguraatiomalli kuvaamaan kuvan mikroskooppisia rakenteita ohjaamattomalla tavalla. Tätä käytetään sitten yhdessä paikallisen kuvaajan, eli local binary pattern (LBP) –operaattorin kanssa. Teoreettisella tarkastelulla osoitetaan kehitetyn kuvaajan olevan rotaatioinvariantti ja kykenevän tuottamaan erottelukykyistä, täydentävää informaatiota perinteiselle LBP-menetelmälle. Työn toisessa osassa tutkitaan videoanalyysiä, perustuen staattisen kuvan deskriptioon ja deformoituvaan kuvien rekisteröintiin – sovellusaloina dynaamisten tekstuurien kuvaaminen, synteesi ja tunnistaminen. Aluksi ehdotetaan sellainen malli dynaamisten tekstuurien synteesiin, joka luo jatkuvan ja äärettömän kuvien virran annetusta äärellisen mittaisesta videosta. Menetelmä liittää yhteen videon pätkiä aika-avaruudessa valitsemalla keskenään yhteensopivia kuvakehyksiä videosta ja järjestämällä ne loogiseen järjestykseen. Seuraavaksi työssä esitetään sellainen uusi menetelmä kasvojen ilmeiden tunnistukseen, joka formuloi dynaamisen kasvojen ilmeiden tunnistusongelman pitkittäissuuntaisten kartastojen rakentamisen ja ryhmäkohtaisen kuvien rekisteröinnin ongelmana
11
Björkeson, Felix. "Autonomous Morphometrics using Depth Cameras for Object Classification and Identification." Thesis, Linköpings universitet, Datorseende, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-95240.
Full textAbstract:
Identification of individuals has been solved with many different solutions around the world, either using biometric data or external means of verification such as id cards or RFID tags. The advantage of using biometric measurements is that they are directly tied to the individual and are usually unalterable. Acquiring dependable measurements is however challenging when the individuals are uncooperative. A dependable system should be able to deal with this and produce reliable identifications. The system proposed in this thesis can autonomously classify uncooperative specimens from depth data. The data is acquired from a depth camera mounted in an uncontrolled environment, where it was allowed to continuously record for two weeks. This requires stable data extraction and normalization algorithms to produce good representations of the specimens. Robust descriptors can therefore be extracted from each sample of a specimen and together with different classification algorithms, the system can be trained or validated. Even with as many as 138 different classes the system achieves high recognition rates. Inspired by the research field of face recognition, the best classification algorithm, the method of fisherfaces, was able to accurately recognize 99.6% of the validation samples. Followed by two variations of the method of eigenfaces, achieving recognition rates of 98.8% and 97.9%. These results affirm that the capabilities of the system are adequate for a commercial implementation.
12
Zbranek, Miroslav. "Metody detekce a rozpoznání obličeje v obrazu." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219650.
Full textAbstract:
The aim of this diploma thesis is to explore methods of face detection and recognition in the picture. The method for face detection and the method for face recognition will be chosen according to literature survey. Both methods will be implemented using the OpenCV library and a program language C/C++. The result of this project is creation of graphic interface which use programmed function for face detection and recognition from a picture and also a camcorder.
13
Sierra, Brandon Luis. "COMPARING AND IMPROVING FACIAL RECOGNITION METHOD." CSUSB ScholarWorks, 2017. https://scholarworks.lib.csusb.edu/etd/575.
Full textAbstract:
Facial recognition is the process in which a sample face can be correctly identified by a machine amongst a group of different faces. With the never-ending need for improvement in the fields of security, surveillance, and identification, facial recognition is becoming increasingly important. Considering this importance, it is imperative that the correct faces are recognized and the error rate is as minimal as possible. Despite the wide variety of current methods for facial recognition, there is no clear cut best method. This project reviews and examines three different methods for facial recognition: Eigenfaces, Fisherfaces, and Local Binary Patterns to determine which method has the highest accuracy of prediction rate. The three methods are reviewed and then compared via experiments. OpenCV, CMake, and Visual Studios were used as tools to conduct experiments. Analysis were conducted to identify which method has the highest accuracy of prediction rate with various experimental factors. By feeding a number of sample images of different people which serve as experimental subjects. The machine is first trained to generate features for each person among the testing subjects. Then, a new image was tested against the “learned” data and be labeled as one of the subjects. With experimental data analysis, the Eigenfaces method was determined to have the highest prediction rate of the three algorithms tested. The Local Binary Pattern Histogram (LBP) was found to have the lowest prediction rate. Finally, LBP was selected for the algorithm improvement. In this project, LBP was improved by identifying the most significant regions of the histograms for each person in training time. The weights of each region are assigned depending on the gray scale contrast. At recognition time, given a new face, different weights are assigned to different regions to increase prediction rate and also speed up the real time recognition. The experimental results confirmed the performance improvement.
14
Huang, X. (Xiaohua). "Methods for facial expression recognition with applications in challenging situations." Doctoral thesis, Oulun yliopisto, 2014. http://urn.fi/urn:isbn:9789526206561.
Full textAbstract:
Abstract In recent years, facial expression recognition has become a useful scheme for computers to affectively understand the emotional state of human beings. Facial representation and facial expression recognition under unconstrained environments have been two critical issues for facial expression recognition systems. This thesis contributes to the research and development of facial expression recognition systems from two aspects: first, feature extraction for facial expression recognition, and second, applications to challenging conditions. Spatial and temporal feature extraction methods are introduced to provide effective and discriminative features for facial expression recognition. The thesis begins with a spatial feature extraction method. This descriptor exploits magnitude while it improves local quantized pattern using improved vector quantization. It also makes the statistical patterns domain-adaptive and compact. Then, the thesis discusses two spatiotemporal feature extraction methods. The first method uses monogenic signal analysis as a preprocessing stage and extracts spatiotemporal features using local binary pattern. The second method extracts sparse spatiotemporal features using sparse cuboids and spatiotemporal local binary pattern. Both methods increase the discriminative capability of local binary pattern in the temporal domain. Based on feature extraction methods, three practical conditions, including illumination variations, facial occlusion and pose changes, are studied for the applications of facial expression recognition. First, with near-infrared imaging technique, a discriminative component-based single feature descriptor is proposed to achieve a high degree of robustness and stability to illumination variations. Second, occlusion detection is proposed to dynamically detect the occluded face regions. A novel system is further designed for handling effectively facial occlusion. Lastly, multi-view discriminative neighbor preserving embedding is developed to deal with pose change, which formulates multi-view facial expression recognition as a generalized eigenvalue problem. Experimental results on publicly available databases show that the effectiveness of the proposed approaches for the applications of facial expression recognition<br>Tiivistelmä Kasvonilmeiden tunnistamisesta on viime vuosina tullut tietokoneille hyödyllinen tapa ymmärtää affektiivisesti ihmisen tunnetilaa. Kasvojen esittäminen ja kasvonilmeiden tunnistaminen rajoittamattomissa ympäristöissä ovat olleet kaksi kriittistä ongelmaa kasvonilmeitä tunnistavien järjestelmien kannalta. Tämä väitöskirjatutkimus myötävaikuttaa kasvonilmeitä tunnistavien järjestelmien tutkimukseen ja kehittymiseen kahdesta näkökulmasta: piirteiden irrottamisesta kasvonilmeiden tunnistamista varten ja kasvonilmeiden tunnistamisesta haastavissa olosuhteissa. Työssä esitellään spatiaalisia ja temporaalisia piirteenirrotusmenetelmiä, jotka tuottavat tehokkaita ja erottelukykyisiä piirteitä kasvonilmeiden tunnistamiseen. Ensimmäisenä työssä esitellään spatiaalinen piirteenirrotusmenetelmä, joka parantaa paikallisia kvantisoituja piirteitä käyttämällä parannettua vektorikvantisointia. Menetelmä tekee myös tilastollisista malleista monikäyttöisiä ja tiiviitä. Seuraavaksi työssä esitellään kaksi spatiotemporaalista piirteenirrotusmenetelmää. Ensimmäinen näistä käyttää esikäsittelynä monogeenistä signaalianalyysiä ja irrottaa spatiotemporaaliset piirteet paikallisia binäärikuvioita käyttäen. Toinen menetelmä irrottaa harvoja spatiotemporaalisia piirteitä käyttäen harvoja kuusitahokkaita ja spatiotemporaalisia paikallisia binäärikuvioita. Molemmat menetelmät parantavat paikallisten binärikuvioiden erottelukykyä ajallisessa ulottuvuudessa. Piirteenirrotusmenetelmien pohjalta työssä tutkitaan kasvonilmeiden tunnistusta kolmessa käytännön olosuhteessa, joissa esiintyy vaihtelua valaistuksessa, okkluusiossa ja pään asennossa. Ensiksi ehdotetaan lähi-infrapuna kuvantamista hyödyntävää diskriminatiivistä komponenttipohjaista yhden piirteen kuvausta, jolla saavutetaan korkea suoritusvarmuus valaistuksen vaihtelun suhteen. Toiseksi ehdotetaan menetelmä okkluusion havainnointiin, jolla dynaamisesti havaitaan peittyneet kasvon alueet. Uudenlainen menetelmä on kehitetty käsittelemään kasvojen okkluusio tehokkaasti. Viimeiseksi työssä on kehitetty moninäkymäinen diskriminatiivisen naapuruston säilyttävään upottamiseen pohjautuva menetelmä käsittelemään pään asennon vaihtelut. Menetelmä kuvaa moninäkymäisen kasvonilmeiden tunnistamisen yleistettynä ominaisarvohajotelmana. Kokeelliset tulokset julkisilla tietokannoilla osoittavat tässä työssä ehdotetut menetelmät suorituskykyisiksi kasvonilmeiden tunnistamisessa
15
Kremličková, Lenka. "Hodnocení viability kardiomyocytů." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2017. http://www.nusl.cz/ntk/nusl-316800.
Full textAbstract:
The aim of this diploma thesis is to get acquainted with the properties of image data and the principle of their capture. Literary research on methods of image segmentation in the area of cardiac tissue imaging and, last but not least, efforts to find methods for classification of dead cardiomyocytes and analysis of their viability. Dead cardiomyocytes were analyzed for their shape and similarity to the template created as a mean of dead cells. Another approach was the application of the method based on local binary characters and the computation of symptoms from a simple and associated histogram.
16
Kadlček, Filip. "Implementace obrazových klasifikátorů v FPGA." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2010. http://www.nusl.cz/ntk/nusl-237091.
Full textAbstract:
The thesis deals with image classifiers and their implementation using FPGA technology. There are discussed weak and strong classifiers in the work. As an example of strong classifiers, the AdaBoost algorithm is described. In the case of weak classifiers, basic types of feature classifiers are shown, including Haar and Gabor wavelets. The rest of work is primarily focused on LBP, LRP and LR classifiers, which are well suitable for efficient implementation in FPGAs. With these classifiers is designed pseudo-parallel architecture. Process of classifications is divided on software and hardware parts. The thesis deals with hardware part of classifications. The designed classifier is very fast and produces results of classification every clock cycle.
17
ROCHA, Simara Vieira da. "Diferenciação do padrão de malignidade e benignidade de massas em imagens de mamografias usando padrões locais binários, geoestatística e índice de diversidade." Universidade Federal do Maranhão, 2014. http://tedebc.ufma.br:8080/jspui/handle/tede/1822.
Full textAbstract:
Submitted by Rosivalda Pereira (mrs.pereira@ufma.br) on 2017-08-14T19:19:25Z
No. of bitstreams: 1
SimaraRocha.pdf: 3984461 bytes, checksum: 04243e2b6ab9b63b0b73e436ebc9fc23 (MD5)<br>Made available in DSpace on 2017-08-14T19:19:25Z (GMT). No. of bitstreams: 1
SimaraRocha.pdf: 3984461 bytes, checksum: 04243e2b6ab9b63b0b73e436ebc9fc23 (MD5)
Previous issue date: 2014-05-22<br>Breast cancer is the second most frequent type of cancer in the world, being more common among women, and representing 22% of the new cases every year. A precocious diagnosis improves the chances of a successful treatment. Mammography is one of the best ways to precocious detection of non-palpable tumor that could lead to a breast cancer. However, it is well known that this exam's sensibility may vary a lot. This is due to factors such as: the specialist's experience, patient's age and the quality of the exam image. The use of Image Processing and Machine Learning techniques has becoming a strong contribution to the specialist diagnosis task. Thes thesis proposes a methodology to discriminate patterns of malignancy and benignity of masses in mammographic images using texture analysis and machine learning. For this purpose, the methodology combines structural and statistical approaches for the analysis of texture regions extracted from mammograms. Furthermore, this research extends the concept of Diversity Index through the use of species co-occurrence information in order to increase the efficiency of extraction of texture features. The techniques used are Local Binary Pattern, Ripley's K function and diversity indexes (Shannon, Mcintosh, Simpson, Gleason and Menhinick indexes). The extracted texture is classified using a Support Vector Machine into benign and malignant classes. The best results obrained with Ripley's K function were 92,20% of accuracy, 92,96% of sensibility, 91,26% of specificity, 10.63 of likelihood positive ratio, 0,07 of likelihood negative ratio and an area under ROC curve Az of 0,92.<br>O câncer de mama é o segundo tipo de câncer mais frequente no mundo, sendo mais comum entre as mulheres, respondendo por 22% dos casos novos a cada ano. Quanto mais precocemente for diagnosticado, maiores serão as chances de se realizar um tratamento bem sucedido. A mamogra fia é uma das formas de detectar os tumores não palpáveis que causam câncer de mama. Todavia, sabe-se que a sensibilidade desse exame pode variar bastante, devido a fatores como: a experiência do especialista, a idade do paciente e a qualidade das imagens obtidas no exame. O uso de técnicas de Processamento de Imagens e Aprendizagem de Máquina tem contribuído, cada vez mais, para auxiliar os especialistas na realização de diagnósticos mais precisos. Esta tese propõe uma metodologia para discriminar padrões de malignidade e benignidade de massas em imagens de mamogra fias, utilizando análise de textura e aprendizado de máquina. Para tanto, a metodologia combina as abordagens estrutural e estatística para a análise de textura de regiões extraídas das mamogra fias. Além disso, esta pesquisa amplia o conceito de Índice de Diversidade, através do uso da informação de co-ocorrência de espécies, com o propósito de aumentar a e ficiência da extração de características de textura. Assim, são usadas as técnicas de Local Binary Pattern, Função K de Ripley e os Índices de Shannon, Mcintosh, Simpson, Gleason e de Menhinick. Por fi m, a textura extraída e classi ficada utilizando a Máquina de Vetores de Suporte, visando diferenciar as massas malignas das benignas. O melhor resultado foi obtido usando a função K de Ripley com 92,20% de acurácia, 92,96% de sensibilidade, 91,26% de especi cidade, 10,63 de razão de probabilidade positiva, 0,07% de razão de probabilidade negativa e uma área sob a curva ROC (Az) de 0,92.
18
Kellokumpu, V. P. (Vili-Petteri). "Vision-based human motion description and recognition." Doctoral thesis, Oulun yliopisto, 2011. http://urn.fi/urn:isbn:9789514296758.
Full textAbstract:
Abstract This thesis investigates vision based description and recognition of human movements. Automated vision based human motion analysis is a fundamental technology for creating video based human computer interaction systems. Because of its wide range of potential applications, the topic has become an active area of research in the computer vision community. This thesis proposes the use of low level description of dynamics for human movement description and recognition. Two groups of approaches are developed: first, texture based methods that extract dynamic features for human movement description, and second, a framework that considers ballistic dynamics for human movement segmentation and recognition. Two texture based descriptions for human movement analysis are introduced. The first method uses the temporal templates as a preprocessing stage and extracts a motion description using local binary pattern texture features. This approach is then extended to a spatiotemporal space and a dynamic texture based method that uses local binary patterns from three orthogonal planes is proposed. The method needs no accurate segmentation of silhouettes, rather, it is designed to work on image data. The dynamic texture based description is also applied to gait recognition. The proposed descriptions have been experimentally validated on publicly available databases. Psychological studies on human movement indicate that common movements such as reaching and striking are ballistic by nature. Based on the psychological observations this thesis considers the segmentation and recognition of ballistic movements using low level motion features. Experimental results on motion capture and video data show the effectiveness of the method<br>Tiivistelmä Tässä väitöskirjassa tutkitaan ihmisen liikkeen kuvaamista ja tunnistamista konenäkömenetelmillä. Ihmisen liikkeen automaattinen analyysi on keskeinen teknologia luotaessa videopohjaisia järjestelmiä ihmisen ja koneen vuorovaikutukseen. Laajojen sovellusmahdollisuuksiensa myötä aiheesta on tullut aktiivinen tutkimusalue konenäön tutkimuksen piirissä. Väitöskirjassa tutkitaan matalan tason piirteiden käyttöä ihmisen liikkeen dynaamiikan kuvaamiseen ja tunnistamiseen. Työssä esitetään kaksi tekstuuripohjaista mentelmää ihmisen liikkeen kuvaamiseen ja viitekehys ballististen liikkeiden segmentointiin ja tunnistamiseen. Työssä esitetään kaksi tekstuuripohjaista menetelmää ihmisen liikkeen analysointiin. Ensimmäinen menetelmä käyttää esikäsittelynä ajallisia kuvamalleja ja kuvaa mallit paikallisilla binäärikuvioilla. Menetelmä laajennetaan myös tila-aika-avaruuteen. Dynaamiseen tekstuuriin perustuva menetelmä irroittaa paikalliset binäärikuviot tila-aika-avaruuden kolmelta ortogonaaliselta tasolta. Menetelmä ei vaadi ihmisen siluetin tarkkaa segmentointia kuvista, koska se on suunniteltu toimimaan suoraan kuvatiedon perusteella. Dynaamiseen tekstuuriin pohjautuvaa menetelmää sovelletaan myös henkilön tunnistamiseen kävelytyylin perusteella. Esitetyt menetelmät on kokeellisesti vahvistettu yleisesti käytetyillä ja julkisesti saatavilla olevilla tietokannoilla. Psykologiset tutkimukset ihmisen liikkumisesta osoittavat, että yleiset liikkeet, kuten kurkoittaminen ja iskeminen, ovat luonteeltaan ballistisia. Tässä työssä tarkastellaan ihmisen liikkeen ajallista segmentointia ja tunnistamista matalan tason liikepiirteistä hyödyntäen psykologisia havaintoja. Kokeelliset tulokset liikkeenkaappaus ja video aineistolla osoittavat menetelmän toimivan hyvin
19
Jebelli, Ali. "Design of an Autonomous Underwater Vehicle with Vision Capabilities." Thesis, Université d'Ottawa / University of Ottawa, 2016. http://hdl.handle.net/10393/35358.
Full textAbstract:
In the past decade, the design and manufacturing of intelligent multipurpose underwater
vehicles has increased significantly. In the wide range of studies conducted in this field, the
flexibility and autonomy of these devices with respect to their intended performance had
been widely investigated.
This work is related to the design and manufacturing of a small and lightweight
autonomous underwater vehicle (AUV) with vision capabilities allowing detecting and
contouring obstacles.
It is indeed an exciting challenge to build a small and light submarine AUV, while making
tradeoffs between performance and minimum available space as well as energy
consumption. In fact, due to the ever-increasing in equipment complexity and performance,
designers of AUVs are facing the issues of limited size and energy consumption.
By using a pair of thrusters capable to rotate 360o on their axis and implementing a mass
shifter with a control loop inside the vehicle, this later can efficiently adapt its depth and
direction with minimal energy consumption. A prototype was fabricated and successfully
tested in real operating conditions (in both pool and ocean). It includes the design and
embedding of accurate custom multi-purpose sensors for multi-task operation as well as an
enhanced coordinated system between a high-speed processor and accustomed
electrical/mechanical parts of the vehicle, to allow automatic controlling its movements.
Furthermore, an efficient tracking system was implemented to automatically detect and
bypass obstacles. Then, fuzzy-based controllers were coupled to the main AUV processor
system to provide the best commands to safely get around obstacles with minimum energy
consumption. The fabricated prototype was able to work for a period of three hours with
object tracking options and five hours in a safe environment, at a speed of 0.6 m/s at a
depth of 8 m.
20
Babinec, Adam. "Monitorování dopravy z leteckých videí." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2015. http://www.nusl.cz/ntk/nusl-264938.
Full textAbstract:
This thesis proposes a system for extraction of vehicle trajectories from aerial video data for traffic analysis. The system is designed to analyse video sequence of a single traffic scene captured by an action camera mounted on an arbitrary UAV flying at the altitudes of approximately 150 m. Each video frame is geo-registered using visual correspondence of extracted ORB features. For the detection of vehicles, MB-LBP classifier cascade is deployed, with additional step of pre-filtering of detection candidates based on movement and scene context. Multi-object tracking is achieved by Bayesian bootstrap filter with an aid of the detection algorithm. The performance of the system was evaluated on three extensively annotated datasets. The results show that on the average, 92% of all extracted trajectories are corresponding to the reality. The system is already being used in the research to aid the process of design and analysis of road infrastructures.
21
Khan, Rizwan Ahmed. "Détection des émotions à partir de vidéos dans un environnement non contrôlé." Thesis, Lyon 1, 2013. http://www.theses.fr/2013LYO10227/document.
Full textAbstract:
Dans notre communication quotidienne avec les autres, nous avons autant de considération pour l’interlocuteur lui-même que pour l’information transmise. En permanence coexistent en effet deux modes de transmission : le verbal et le non-verbal. Sur ce dernier thème intervient principalement l’expression faciale avec laquelle l’interlocuteur peut révéler d’autres émotions et intentions. Habituellement, un processus de reconnaissance d’émotions faciales repose sur 3 étapes : le suivi du visage, l’extraction de caractéristiques puis la classification de l’expression faciale. Pour obtenir un processus robuste apte à fournir des résultats fiables et exploitables, il est primordial d’extraire des caractéristiques avec de forts pouvoirs discriminants (selon les zones du visage concernées). Les avancées récentes de l’état de l’art ont conduit aujourd’hui à diverses approches souvent bridées par des temps de traitement trop couteux compte-tenu de l’extraction de descripteurs sur le visage complet ou sur des heuristiques mathématiques et/ou géométriques.En fait, aucune réponse bio-inspirée n’exploite la perception humaine dans cette tâche qu’elle opère pourtant régulièrement. Au cours de ces travaux de thèse, la base de notre approche fut ainsi de singer le modèle visuel pour focaliser le calcul de nos descripteurs sur les seules régions du visage essentielles pour la reconnaissance d’émotions. Cette approche nous a permis de concevoir un processus plus naturel basé sur ces seules régions émergentes au regard de la perception humaine. Ce manuscrit présente les différentes méthodologies bio-inspirées mises en place pour aboutir à des résultats qui améliorent généralement l’état de l’art sur les bases de référence. Ensuite, compte-tenu du fait qu’elles se focalisent sur les seules parties émergentes du visage, elles améliorent les temps de calcul et la complexité des algorithmes mis en jeu conduisant à une utilisation possible pour des applications temps réel<br>Communication in any form i.e. verbal or non-verbal is vital to complete various daily routine tasks and plays a significant role inlife. Facial expression is the most effective form of non-verbal communication and it provides a clue about emotional state, mindset and intention. Generally automatic facial expression recognition framework consists of three step: face tracking, feature extraction and expression classification. In order to built robust facial expression recognition framework that is capable of producing reliable results, it is necessary to extract features (from the appropriate facial regions) that have strong discriminative abilities. Recently different methods for automatic facial expression recognition have been proposed, but invariably they all are computationally expensive and spend computational time on whole face image or divides the facial image based on some mathematical or geometrical heuristic for features extraction. None of them take inspiration from the human visual system in completing the same task. In this research thesis we took inspiration from the human visual system in order to find from where (facial region) to extract features. We argue that the task of expression analysis and recognition could be done in more conducive manner, if only some regions are selected for further processing (i.e.salient regions) as it happens in human visual system. In this research thesis we have proposed different frameworks for automatic recognition of expressions, all getting inspiration from the human vision. Every subsequently proposed addresses the shortcomings of the previously proposed framework. Our proposed frameworks in general, achieve results that exceeds state-of-the-artmethods for expression recognition. Secondly, they are computationally efficient and simple as they process only perceptually salient region(s) of face for feature extraction. By processing only perceptually salient region(s) of the face, reduction in feature vector dimensionality and reduction in computational time for feature extraction is achieved. Thus making them suitable for real-time applications
22
Novotný, Adam. "Texturní analýza vrstvy nervových vláken na snímcích sítnice." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2010. http://www.nusl.cz/ntk/nusl-218649.
Full textAbstract:
This work describes completely new approach to detection of retinal nerve fibre layer (RNFL) loss in colour fundus images. Such RNFL losses indicate eye glaucoma illness and an early diagnosis of RNFL changes is very important for successful treatment. Method is presented with the purpose of supporting glaucoma diagnosis in ophthalmology. The proposed textural analysis method utilizes local binary patterns (LBP). This approach is characterized especially by computational simplicity and insensitivity to monotonic changes of illumination. Image histograms of LBP distributions are used to gain several textural features aimed to classify healthy or glaucomatous tissue of the retina. The method was experimentally tested using fundus images of glaucomatous patients with focal RNFL loss. The results show that the proposed method can be used in order to supporting diagnosis of glaucoma with satisfactory efficiency.
23
Hussain, Sibt Ul. "Apprentissage machine pour la détection des objets." Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00722632.
Full textAbstract:
Le but de cette thèse est de développer des méthodes pratiques plus performantes pour la détection d'instances de classes d'objets de la vie quotidienne dans les images. Nous présentons une famille de détecteurs qui incorporent trois types d'indices visuelles performantes - histogrammes de gradients orientés (Histograms of Oriented Gradients, HOG), motifs locaux binaires (Local Binary Patterns, LBP) et motifs locaux ternaires (Local Ternary Patterns, LTP) - dans des méthodes de discrimination efficaces de type machine à vecteur de support latent (Latent SVM), sous deux régimes de réduction de dimension - moindres carrées partielles (Partial Least Squares, PLS) et sélection de variables par élagage de poids SVM (SVM Weight Truncation). Sur plusieurs jeux de données importantes, notamment ceux du PASCAL VOC2006 et VOC2007, INRIA Person et ETH Zurich, nous démontrons que nos méthodes améliorent l'état de l'art du domaine. Nos contributions principales sont : Nous étudions l'indice visuelle LTP pour la détection d'objets. Nous démontrons que sa performance est globalement mieux que celle des indices bien établies HOG et LBP parce qu'elle permet d'encoder à la fois la texture locale de l'objet et sa forme globale, tout en étant résistante aux variations d'éclairage. Grâce à ces atouts, LTP fonctionne aussi bien pour les classes qui sont caractérisées principalement par leurs structures que pour celles qui sont caractérisées par leurs textures. En plus, nous démontrons que les indices HOG, LBP et LTP sont bien complémentaires, de sorte qu'un jeux d'indices étendu qui intègre tous les trois améliore encore la performance. Les jeux d'indices visuelles performantes étant de dimension assez élevée, nous proposons deux méthodes de réduction de dimension afin d'améliorer leur vitesse et réduire leur utilisation de mémoire. La première, basée sur la projection moindres carrés partielles, diminue significativement le temps de formation des détecteurs linéaires, sans réduction de précision ni perte de vitesse d'exécution. La seconde, fondée sur la sélection de variables par l'élagage des poids du SVM, nous permet de réduire le nombre d'indices actives par un ordre de grandeur avec une réduction minime, voire même une petite augmentation, de la précision du détecteur. Malgré sa simplicité, cette méthode de sélection de variables surpasse toutes les autres approches que nous avons mis à l'essai.
24
Faula, Yannick. "Extraction de caractéristiques sur des images acquises en contexte mobile : Application à la reconnaissance de défauts sur ouvrages d’art." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEI077.
Full textAbstract:
Le réseau ferroviaire français dispose d’une infrastructure de grande ampleur qui se compose de nombreux ouvrages d’art. Ces derniers subissent les dégradations du temps et du trafic et font donc l’objet d’une surveillance périodique pour détecter l’apparition de défauts. Aujourd’hui, cette inspection se fait en grande partie, visuellement par des opérateurs experts. Plusieurs entreprises testent de nouveaux vecteurs d’acquisition photo comme le drone, destinés à la surveillance des ouvrages de génie civil. Dans cette thèse, l’objectif principal est de développer un système capable de détecter, localiser et enregistrer d’éventuels défauts de l’ouvrage. Un grand défi est de détecter des défauts sous-pixels comme les fissures en temps réel pour améliorer l’acquisition. Pour cela, une analyse par seuillage local a été conçue pour traiter de grandes images. Cette analyse permet d’extraire des points d’intérêts (Points FLASH: Fast Local Analysis by threSHolding) où une ligne droite peut se faufiler. La mise en relation intelligente de ces points permet de détecter et localiser les fissures fines. Les résultats de détection de fissures de surfaces altérées issues d'images d'ouvrages d'art démontrent de meilleures performances en temps de calcul et robustesse que les algorithmes existants. En amont de l'étape de détection, il est nécessaire de s’assurer que les images acquises soient de bonne qualité pour réaliser le traitement. Une mauvaise mise au point ou un flou de bougé sont à bannir. Nous avons développé une méthode réutilisant les calculs de la détection en extrayant des mesures de Local Binary Patterns (LBP) afin de vérifier la qualité en temps réel. Enfin, pour réaliser une acquisition permettant une reconstruction photogrammétrique, les images doivent avoir un recouvrement suffisant. Notre algorithme, réutilisant les points d’intérêts de la détection, permet un appariement simple entre deux images sans passer par des algorithmes de type RANSAC. Notre méthode est invariante en rotation, translation et à une certaine plage de changements d’échelle. Après l’acquisition, sur les images de qualité optimale, il est possible d'employer des méthodes plus coûteuses en temps comme les réseaux de neurones à convolution. Ces derniers bien qu'incapables d’assurer une détection de fissures en temps réel peuvent être utilisés pour détecter certains types d’avaries. Cependant, le manque de données impose la constitution de notre propre jeu de données. A l'aide d'approches de classification indépendante (classifieurs SVM one-class), nous avons développé un système flexible capable d’évoluer dans le temps, de détecter puis de classifier les différents types de défauts. Aucun système de ce type n’apparaît dans la littérature. Les travaux réalisés sur l’extraction de caractéristiques sur des images pour la détection de défauts pourront être utiles dans d’autres applications telles que la navigation de véhicules intelligents ou le word-spotting<br>The french railway network has a huge infrastructure which is composed of many civil engineering structures. These suffer from degradation of time and traffic and they are subject to a periodic monitoring in order to detect appearance of defects. At the moment, this inspection is mainly done visually by monitoring operators. Several companies test new vectors of photo acquisition like the drone, designed for civil engineering monitoring. In this thesis, the main goal is to develop a system able to detect, localize and save potential defects of the infrastructure. A huge issue is to detect sub-pixel defects like cracks in real time for improving the acquisition. For this task, a local analysis by thresholding is designed for treating large images. This analysis can extract some points of interest (FLASH points: Fast Local Analysis by threSHolding) where a straight line can sneak in. The smart spatial relationship of these points allows to detect and localise fine cracks. The results of the crack detection on concrete degraded surfaces coming from images of infrastructure show better performances in time and robustness than the state-of-art algorithms. Before the detection step, we have to ensure the acquired images have a sufficient quality to make the process. A bad focus or a movement blur are prohibited. We developed a method reusing the preceding computations to assess the quality in real time by extracting Local Binary Pattern (LBP) values. Then, in order to make an acquisition for photogrammetric reconstruction, images have to get a sufficient overlapping. Our algorithm, reusing points of interest of the detection, can make a simple matching between two images without using algorithms as type RANSAC. Our method has invariance in rotation, translation and scale range. After the acquisition, with images with optimal quality, it is possible to exploit methods more expensive in time like convolution neural networks. These are not able to detect cracks in real time but can detect other kinds of damages. However, the lack of data requires the constitution of our database. With approaches of independent classification (classifier SVM one-class), we developed a dynamic system able to evolve in time, detect and then classify the different kinds of damages. No system like ours appears in the literature for the defect detection on civil engineering structure. The implemented works on feature extraction on images for damage detection will be used in other applications as smart vehicle navigation or word spotting
25
Chen, Mei-Shuo, and 陳玫碩. "Extension of Local Binary Pattern and Weber Local Descriptor and Color Image to Grayscale Conversion." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/33529128534705143147.
Full textAbstract:
碩士<br>國立臺灣大學<br>電信工程學研究所<br>104<br>With the advent of the technological era, computer vision is used widely in many fields such as face recognition, object detection, image retrieval and surveillance systems. In image processing, feature extraction is an indispensable step, which can reflect the intrinsic content (information) from the images (data). I utilized Local Binary Pattern (LBP) and Weber Local Descriptor
(WLD), these two powerful descriptors to do experiments including face recognition, and Chinese Calligraphy Recognition. LBP is a spatial gray-level dependence method (co-occurrence method) and can be computed efficiently by thresholding the neighborhood of each pixel with the center pixel value to form a gray-scale invariant pattern. Weber local descriptor was inspired by
Weber’s Law and was deemed to base on the fact of human perception.
Besides, I revised the disadvantage of Local Binary Pattern algorithm and made a combination of conventional LBP with direction information to form a robust descriptor named “Magnitude and Direction Difference Local Binary Descriptor”. Furthermore, Local Binary Pattern was used to apply to grayscale images. I attempted to make use of the descriptor on color images. I also revised the traditional method but preserving the spirit when dealing with color images, called “HSV-LBP”. My results show that the revised version can extract clear features than previous LBP on color images.
Last, I put emphasis on the topic about converting color images to grayscale images and not only preserving contrast but enhancing contrast.
26
Shen, Yi-Kang, and 沈怡康. "LOCAL BINARY PATTERN ORIENTATION BASED FACE RECOGNITION." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/12911006925009521470.
Full textAbstract:
碩士<br>國立清華大學<br>資訊工程學系<br>103<br>Illumination variation and facial expression generally causes performance degradation of face recognition systems under real-life environments. In traditionally, Scale-invariant feature transform (SIFT) has good result for scale-variance and rotation, but the recognition is lower in illumination variation, and requires high computation complexity. Therefore, we propose a fast descriptor and matching method on SIFT, using the local binary patterns orientation and histogram equalization to remove the lighting effects. This method has the following advantages: (1) Remove the lighting influence effectively. (2) Extract different face details. (3) Reduce computational cost. We also propose using region of interest to remove the useless interest points for saving our computation time and maintaining the recognition rate. Experimental results demonstrate that our proposed has 0.8\% higher recognition rate than original and reduces 28.3\% computation time for FERET database has 1.2\% higher recognition rate than original and reduces 28.6\% computational time compared to original. In the ROI systems, experimental results demonstrate that our proposed reduces 61.9\% computation time and has 75.7\# recognition rates for FERET database has 95.2\% recognition rate original and reduces 57.4\% computational time.
27
Huang, Yu-Hsin, and 黃宇欣. "Improving Non-Local Mean Denoising Using Local Binary Pattern Classification." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/94809419710422118746.
Full textAbstract:
碩士<br>國立中興大學<br>電機工程學系所<br>103<br>The image denoising capability of non-local mean (NLM) algorithm is based on the weighted sum of neighboring pixels. The weights are calculated from the similarity between image patches. However, when there is lighting difference between two similar patches, the lighting difference will be incorporated into the similarity metrics and makes them appear much more dissimilar than their true status.
Because the popular image descriptor, local binary pattern (LBP), is calculated by comparing intensity between pixels, it is relative insensitive to lighting difference between image patches. Thus, we propose to incorporate LBP into NLM in this thesis. In order to consider the lighting difference, the calculation of weights in NLM is also modified. We also find that the lighting difference is especially significant in image background. Therefore, we add two kinds of LBP to classify lighter and darker backgrounds.
Experiments show that our new approach does indeed produce better PSNR when compared with NLM.
28
Chuang, Shun-Hsu, and 莊順旭. "Facial Expression Recognition based on Fusing Weighted Local Directional Pattern and Local Binary Pattern." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/13073845934835992163.
Full textAbstract:
碩士<br>中華大學<br>資訊工程學系(所)<br>98<br>A method of combining Weighted Local Directional Pattern (WLDP) and Local Binary Pattern (LBP) for facial expression recognition is proposed. First, WLDP and LBP are applied to extract human facial features. Second, principle component analysis (PCA) is used to reduce their feature dimensions respectively. Third, both reduced facial features are merged to form the final feature vector. Fourth, support vector machine (SVM) is used to recognize facial expressions. Experiment on the well known Cohn-Kanade expression database, a high accuracy rate up to 91.1% for recognizing seven expressions can be achieved with a person-independent 10-fold cross-validation scheme.
29
Pei-HsunWu and 吳沛勳. "Metric-Learning Face Verification Using Local Binary Pattern." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/49593027304201220818.
Full text
30
Shi, Chao-Chi, and 許晁齊. "Iris Recognition System Based on Local Binary Pattern Method." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/97670447558970931340.
Full textAbstract:
碩士<br>國立中正大學<br>電機工程研究所<br>103<br>In today's advanced information age, security plays a very important position. The popular PIN (Personal Identification Number) Identification is usually lost because of negligence, so " biometric identification system " which has higher security will be used. The people does not need to memory a long list of password. Iris recognition is one of the most accurate biometric identification methods. Iris of each person is different, and its feature is not easily changed and has high accuracy. In the thesis, firstly we capture the iris image, and then using pre-processing algorithm to remove noise and complete the location to be the iris features ROI. Then it lets the features turn into iris code. In order to verify the correctness of the system, two databases are used. The first one is CASIA iris image database which is provided by the Chinese Academy of Sciences Institute of Automation, the other is CCU-database iris image database which is provided by Taiwan National Chung Cheng University. The matching rates of our sample are respectively 97.36% and 92.40%.
31
Tsai, Ming-Yuan, and 蔡明遠. "RGB-D Object Retrieval with Local Binary Pattern Features." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/qsfpkp.
Full textAbstract:
碩士<br>義守大學<br>資訊工程學系<br>106<br>As sensing technology continues to advance, the use of RGB-D cameras in daily life has become routine, for various purposes such as three-dimensional reconstruction, moving tracking, and human-computer interaction. The research is mainly about object retrieval of large size RGB-D images. The first step is image segmentation by background difference. Then, obtain geometric features by gathering the statistics of depth image and image gradient; obtain color features by gathering the statistics of color quantification. Since the color and depth of the object’s surface slightly changes, local binary pattern is used in order to obtain the texture features, and to meet the rotational invariance and scale invariance of the object. Therefore, better results of object-detecting can be expected because of data matching of the various features.
32
Verma, Rohit. "Local Binary Pattern Approach for Fast Block Based Motion Estimation." Thesis, 2013. http://hdl.handle.net/10012/7998.
Full textAbstract:
With the rapid growth of video services on smartphones such as video conferencing, video telephone and WebTV, implementation of video compression on mobile terminal becomes extremely important. However, the low computation capability of mobile devices becomes a bottleneck which calls for low complexity techniques for video coding. This work presents two set of algorithms for reducing the complexity of motion estimation. Binary motion estimation techniques using one-bit and two-bit transforms reduce the computational complexity of matching error criterion, however sometimes generate inaccurate motion vectors. The first set includes two neighborhood matching based algorithms which attempt to reduce computations to only a fraction of other methods. Simulation results demonstrate that full search local binary pattern (FS-LBP) algorithm reconstruct visually more accurate frames compared to full search algorithm (FSA). Its reduced complexity LBP (RC-LBP) version decreases computations significantly to only a fraction of the other methods while maintaining acceptable performance. The second set introduces edge detection approach for partial distortion elimination based on binary patterns. Spiral partial distortion elimination (SpiralPDE) has been proposed in literature which matches the pixel-to-pixel distortion in a predefined manner. Since, the contribution of all the pixels to the distortion function is different, therefore, it is important to analyze and extract these cardinal pixels. The proposed algorithms are called lossless fast full search partial distortion
elimination ME based on local binary patterns (PLBP) and lossy edge-detection pixel decimation technique based on local binary patterns (ELBP). PLBP reduces the matching complexity by matching more contributable pixels early by identifying the most diverse pixels in a local neighborhood. ELBP captures the most representative pixels in a block in order of contribution to the distortion function by evaluating whether the individual pixels belong to the edge or background. Experimental results demonstrate substantial reduction in computational complexity of ELBP with only a marginal loss in prediction quality.
33
Chang, Chao-Yi, and 張兆逸. "Hardware Design and Implementation of the Local Binary Pattern Algorithm." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/51819523071572446146.
Full textAbstract:
碩士<br>國立臺灣海洋大學<br>電機工程學系<br>96<br>Abstract
The Local Binary Pattern (LBP) algorithm is one of the major traditional texture analysis methods. It is both rotation and gray-scale invariant. These characteristics make it an ideal method for image recognition.
In most image processing systems, certain features are often extracted first from the image before performing any further analysis. This is called front-end processing. For many embedded image processing systems, the front-end processing is both very time-consuming and resource-demanding. To facilitate embedded systems with limited resources to process the front-end data more efficiently, we have designed and implemented a digital circuit for the computation of LBP statistical values. Our design consists of two major parts: an LBP computing unit and a memory controller. It outputs a set of LBP data every ten clock cycles. The circuit synthesized by Design Compiler operates at a maximum clock rate of 500 MHz. We verify the correctness of the circuit by running simulations with ModelSim. The results, also confirmed by an FPGA verification board, show that our design calculates the LBP values accurately.
Keywords: Local binary pattern, texture analysis, image processing.
34
HUANG, WEN-HSIAO, and 黃文孝. "A Study on Texture Classification Using Various Local Binary Pattern." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/18752012162663303687.
Full textAbstract:
碩士<br>玄奘大學<br>資訊管理學系碩士班<br>103<br>Texture represents pivotal features in images for classification and analysis. The occurrence of texture pattern surrounded object surface played important roles in different kinds of image processing areas such as face recognition, medical image analysis, and biological features processing. Generally, they can be divided into structural and random texture patterns. Local binary pattern abbreviated as LBP is a kind of operation based on local grayscale comparison. This operator can statistically find out the local texture characteristic in an image as a representation of it. In this study, four kinds of various local binary pattern operators are discussed and evaluated. They are LBP, improved LBP (ILBP), Median LBP (MLBP), and adaptive Ni-black threshold LBP (NLB), respectively. In our experiments, textures pattern are usually everywhere in the same texture image. So, we divide each texture benchmarks into training and testing sub-image sets. All sub-images of training set intuitively represent with the average histogram of various LBP operators. The histogram predication classificator and popular learning mechanism, the support vector machine (SVM), are applied in our experiments. More, the rotated texture classification also is discussed on different degrees of angle scales. The experimental results show that ILBP obtains the best precision than others in our designed scheme no matter what about learning modes, sub-images and rotated images.
35
Yu-KaiTseng and 曾郁凱. "Local Binary Pattern Histogram-Based Gender Classification Using Real AdaBoost." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/63733223508488000465.
Full textAbstract:
碩士<br>國立成功大學<br>資訊工程學系碩博士班<br>101<br>Gender classification is a hot research topic in recent years, which could be applied to many categories, e.g. electronic advertising, surveillance systems, etc. In this thesis, we present a gender classification system using local binary pattern histogram and Real AdaBoost learning method to create a strong classifier. The strong classifier outputs confidence value which presents the judgments with trust degrees. According to the error between manually labeled inner eye corner points and the eye corner points calculated by Shape Optimized Search algorithm, we present a statistical method to get the reference points which are close to the manually label inner eye corner points. In addition, in order to reduce the noise caused by facial expression changes and face’s small amplitude movements, the output of gender classification is determined by accumulating previous judgment results. The experimental results demonstrate that the system we purposed not only works effectively on single frame but could also applied in real-time systems.
36
Chen, Qi-Hui, and 陳琪惠. "Low-Cost Face Recognition System Based on Extended Local Binary Pattern." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/49329530039264587452.
Full textAbstract:
碩士<br>國立交通大學<br>電控工程研究所<br>104<br>In recent years, the IoT application and the biometric-based authorization become popular. This thesis proposes a face recognition system with high accuracy rate based on extended Local Binary Pattern, and applies it as an access control system on an IoT device which is always low-cost, low-power and small-footprint. The proposed face recognition system includes three parts, face detection, feature extraction and face recognition. For the face detection, the Viola-Jones face detector is adopted to find out the face information. The extended Local Binary Pattern then extracts the local features of the face. Further transform these features to a low-dimension subspace by Principle Component Analysis method. Finally, use the classification based on the sparse representation of L2 norm minimization to identify and verify the face. From the experimental results, the proposed method can achieve a high recognition rate better than 95% in several face databases, even reach 99% for the Cohn-Kanade face database. The access control system implemented on Raspberry Pi 3 is able to complete the whole face recognition in a second, which makes it indeed a real-time system.
37
Chen, Chin-Ning, and 陳親寧. "Finger Spelling Recognition Design Using Local Binary Pattern and Template Matching." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/49889279373915077417.
Full textAbstract:
碩士<br>國立交通大學<br>電控工程研究所<br>104<br>Finger spelling recognition is a popular communication way for Human-Computer Interaction (HCI). This thesis proposes a finger spelling recognition system with high accuracy rate based on RGB-D image. The system is divided into three main parts, including hand region detection, feature extraction, and finger spelling recognition. For the hand region detection, first, utilize depth information to distinguish the hand region and background and then extract the palm region. Further, use texture operator Local Binary Pattern to extract image feature. After getting the feature, use Principal Component Analysis to reduce data dimension and decrease computational time. Finally, decide the number of templates by Gap Statistic, find the template using K-means Clustering, and classify data with Template Matching Method. The experimental results show that the combination of simple feature extraction method and unsupervised classifier has the accuracy higher than 98% in finger spelling recognition.
38
Yang, Qing hong, and 楊慶鴻. "An Age Classification System Using Gabor Filter And Local Binary Pattern." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/41857639716028708545.
Full textAbstract:
碩士<br>長庚大學<br>電機工程學系<br>99<br>Abstract
In age-based classification studies, it is found that accuracy and feature extraction are the two most important areas that need further improvement in the facial identification technique. Pre-processing and the actual content of input image also significantly affect the accuracy of facial identification. In previous studies, many researchers had adopted the complete image domain approach in the image processing, such as Principal Component Analysis (PCA) and Linear Discriminate Analysis (LDA). Since the complete image domain analysis method often causes the degradation of facial identification quality as affected by the distortion of image acquisition, texture descriptor has in recent years gradually gained significance in pattern recognition. Based on this concept, the study proposes a new age-based classification system by combing the advantages of several methods. The framework of this study consists of three components: image pre-processing, feature extraction and classification of recognizable modules. This study mainly relies on Local Binary Graphics Pattern (LBP) and Gabor Filters (GF) to extract texture features from the face. Distinguishing from traditional methods, the study employs a new method for reducing the number of dimensions by using the Principal Component Analysis (PCA) for multi-dimensional reduction of the acquired data while maintaining the data features in the original high-dimensional feature space. This method can facilitate the classification of recognizable modules using the Support Vector Machine (SVM) classification, of which the results will be integrated through voting, and thereby establishing a voting mechanism for age-based classification. The study utilizes 800 images of facial data, including 400 adults and 400 children. From each group, 300 facial images were selected, totaling 600 for image training, and the remaining 200 were used for image testing. Our experimental results show that Local Binary Graphics Pattern, Gabor Filters, and Principal Component Analysis can be used to compliment each other (LBP + GF + PCA) in order to obtain the best recognition rate with 100% accuracy.
39
SiongNg, Kiat, and 黃傑翔. "Local Binary Pattern Circuit Generator with Adjustable Parameters for Feature Extraction." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/pe69hh.
Full textAbstract:
博士<br>國立成功大學<br>資訊工程學系<br>106<br>In the field of computer vision, local binary pattern (LBP) is one of the most popular feature extraction method and has been used in many object detection frameworks. To efficiently extract LBP features in high-resolution images, a hardware architecture is needed to disperse CPU burden and to improve the entire object detection performance. In this thesis, a hardware implementation of an approximated LBP method with adjustable parameters is introduced. For simulation, Taiwan Semiconductor Manufacturing Company 0.18} micrometer technology is used to implement the LBP hardware, in which the hardware can achieve 500 MHz with lower gate count than the previous study. The proposed LBP circuit is applied to the pedestrian classification application and the evaluation results show that the approximated LBP values generated by our circuit can achieve comparable classification accuracy with the primitive LBP method. Additionally, the proposed LBP hardware provides adjustable parameters to fit different applications while requires fewer hardware costs as compared with the existing work.
40
Wang, Ting-Chih, and 王鼎智. "Image Forgery Detection Based on Local Binary Pattern and Gradient Operator." Thesis, 2019. http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5394067%22.&searchmode=basic.
Full textAbstract:
碩士<br>國立中興大學<br>資訊科學與工程學系所<br>107<br>In this age of advanced Internet, tampered image have become the most dangerous method to mislead humans or cause panic, especially in this era of platform for online socializing. The above description shows that the importance of forgery image detection. Our proposed method uses YCbCr color model for pre-process. In order to enhance the accuracy of the forgery image deteciotn, we use two methods to get the features.The first method uses Local Binary Pattern for image to extract the local texture feature of image.The second is to sharpen the image and then use the Gradient Operator to find the edge. The main purpose of these two steps is to first enhance the details of the image before finding the edge of the image. The outstanding effect of block discrete cosine transform (BDCT) in detecting the image decorrelation is used in our method. So we calculate the standard deviations of the BDCTs got from the pre-processing computed separately are considered as the features for forgery detection in our method. We can get two different sets of features by the above two methods, and our proposed method combines the two features. Because the dimension of the feature is too large, we use feature selection to reduce the dimension. Finally, we can see from the experimental results that our method can effectively increase the detection accuracy by adding the edge of the enhanced image.
41
Lee, Wei-Shan, and 李偉聖. "Classification in Chronic Kidney Disease by Nakagami Distribution and Local Binary Pattern." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/84007010859684925386.
Full textAbstract:
碩士<br>國立臺灣海洋大學<br>資訊工程學系<br>103<br>Ultrasound imaging can provide radiation-free, non-invasive, low cost, and convenient to detect diseases and thus becomes an incontestable vital tool for clinical diagnosis. However, speckle effect makes it very noisy and thus reduces its overall diagnostic abilities and diversities to detect different kinds of diseases. This paper develops a real time system to analyze chronic kidney disease (CKD) using only Ultrasound images. As we know, this is the first work to analyze CKD stages of patients directly from ultrasound images without using any blood examination such as Creatinine index. To build the scoring index for CKD stage classification, this paper uses Nakagami distribution and Local Binary Pattern (LBP) to model the scattering properties of CKD ultrasound images. In addition, we find the age distribution is also important for CKD stage analysis. After integration, a codebook concept is adopted to extract important visual codes to describe the texture and scattering characteristics of each CKD stage. Then, we build a strong CKD stage classifier via SVM for CKD stage prediction and classification. Experimental results demonstrate the sensitivity and specificity of this system up to 97.40% and 86.67%, respectively.
42
Yu-JungHsiao and 蕭鈺融. "Hardware Implementation of Local Binary Pattern with Variable Parameters for Human Detection." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/84220149156736980928.
Full textAbstract:
碩士<br>國立成功大學<br>資訊工程學系<br>103<br>With the advancement in technology, computer vision is now the achieving goal where computers can imitate human vision and can help identifying and analyzing data automatically. In computer vision, human detection has been an important research topic, which can be widely used in many applications in ensuring human safety, such as surveillance systems and automotive systems. Therefore, high accuracy human detection algorithm can greatly enhance the practicability of these systems. Local Binary Pattern (LBP) is a robust feature extraction algorithm. It can efficiently describe the text features of the target object. As compared to other feature extraction algorithm, Local Binary Pattern (LBP) has excellent achievement in the researches of human detection.
Since human detection technique are performed in embedded devices to make applications practical, such as dashboard cameras, the hardware approximation technique is used to propose an approximate method to replace the complex computations like trigonometric functions and square roots in this thesis. The hardware architecture of the proposed design is implemented to decrease the computation time of the system so that it can reach real-time human detection processing. Meanwhile, the Soft-IP methodology is also used in designing the hardware. Users are able to adjust the parameters to generate different hardware design to meet their needs.
Our proposed design is an 8-stage pipelined hardware architecture, synthesized with SYNOPSYS Design Compiler in the TSMC 0.13μm cell library. It is made of 12.3k gate counts, and achieves a clock frequency of 500MHz. The throughputs are able to process 268M pixels per second. The accuracy rate for human detection is regularly higher than 95% on average.
43
Hsu, Chao-Tsun, and 徐兆村. "Face Verification Based on Local Binary Pattern Applied to Mobile Remote Surveillance System." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/vtdws5.
Full textAbstract:
碩士<br>國立交通大學<br>電控工程研究所<br>101<br>This thesis develops a mobile remote surveillance system (MRSS) for users to watch a specific location via the wireless Internet. The aim is to design an App running on Android mobile devices to connect an operational server. The proposed MRSS adopts a PC-based operational server with fast calculating ability and large data capacity to fulfill the functions in remote surveillance and control, such as multimedia transmission through TCP protocol, access of user’s data, human face detection and verification and remote control of IP camera. To promote the level of personal privacy and information security, besides the password it is required to execute face verifications before the user watches the desired images. To increase the accuracy of face verification, this thesis develops an NN-Based face verification system which adopts the LBP operation to extract the face features. To demonstrate the performance of the MRSS system, the proposed Apps are executed on a SAMSUNG Galaxy SII phone and an Acer ICONIA Tab. Under the frame rate of 15 frames per second, the accuracy of human face verification is up to 95.77%.
44
Lin, Jou, and 林柔. "Local Binary Pattern Edge-Mapped Descriptor Using MGM Interest Points for Face Recognition." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/62736447907594867411.
Full textAbstract:
碩士<br>國立清華大學<br>通訊工程研究所<br>104<br>Face recognition is one of popular topics in academic and industrial areas in recent years. Numerous approaches have been developed nowadays, but there are still several challenges in real-world circumstances. Present local methods such as local binary pattern (LBP) [4], [6], local derivative pattern (LDP) [10] and scale invariant feature transform (SIFT) [14] own better performance than holistic methods; however, high complexity results in some limitations for applications such as mobile devices. In addition, SIFT-based schemes are sensitive to illumination variation. Thus we propose a LBP Edge-mapped descriptor by using Maxima of Gradient Magnitude (MGM) [20] points. It is a robust, simple and fast descriptor. LBP Edge-mapped descriptor is a string of binary codes which record surrounding information of illumination and edges of MGM [20]. It can illustrate facial contours completely and have low computational complexity simultaneously. Due to binary codes, a simple matching method can be adopted for face recognition. Under variable lighting, experimental results show that our method has 16.5% higher recognition rate and spends 9.06 times less execution time than SIFT in FERET fc [22]. Besides, our method outperforms SIFT-based approaches and saves about 70.9% execution time compared with SIFT in the Extended Yale Face Database B [32]. In the variation of expression, our method maintains acceptable recognition rate and has 7.50 times less computational time than SIFT in FERET fb [22]. Furthermore, in uncontrolled conditions, our method owns 0.82% higher recognition rate than local derivative pattern histogram sequences (LDPHS) [10] in Unconstrained Facual Images (UFI) Database [30].
45
Dai, Yi-Jhe, and 戴義哲. "Conditional Sorting Local Binary Pattern Based on Gait Energy Image for Human Gait Recognition." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/93793045511178995931.
Full textAbstract:
碩士<br>淡江大學<br>電機工程學系碩士班<br>101<br>Biometric identification techniques allow the identification of a person according to some geometric or behavioral traits that are uniquely associated with him or her. Commonly used biometrics are face, iris, fingerprints, handwriting, pal, vena and gait. An important limitation of most contemporary biometric identification system is related to the fact that they require the cooperation of individual that is to be identified and some special capturing devices. Gait recognition is an emerging biometric technology which aims to identify individuals using their walking style. The apparent advantage of gait recognition in comparison to other biometrics is that it doesn’t require the attention or cooperation of the observed subject. This work proposes a new feature extraction method for gait representation and recognition. The new method is extended from the technique of Local Binary Pattern (LBP) by changing the sorting method of LBP according to the blend direction to create a new approach, Conditional-Sorting Local Binary Pattern (CS-LBP). We then apply the CS-LBP on GEI to derive different blend direction images and calculate the recognition ability for each blend direction image for feature selections. From the experimental result, we proposed a new feature description method which can be effectively applied in gait recognition, also has a higher recognition results than other existing literature.
46
Hsiao, Chih-Yu, and 蕭智予. "A Scheme based on Local Binary Pattern Combined with Tamura Feature for Texture Recognition." Thesis, 2019. http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5394068%22.&searchmode=basic.
Full text
47
SINGH, SURJEET. "CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE FEATURES." Thesis, 2016. http://dspace.dtu.ac.in:8080/jspui/handle/repository/14621.
Full textAbstract:
Content based image retrieval is one of the most important tasks in computer vision.
Images have two important visual features, Color and texture which play an important
role in content based image retrieval system. In this report, an efficient content-based
image retrieval system is proposed based on color and texture feature. We are
extracting the color feature by quantifying the Intensity images or gray scale image. It
represents an image as a 2D component carrying values between 0 and 255 matrix
where every element has a value corresponding to how bright/dark the pixel at the
corresponding position should be colored. Texture feature is obtained by using local
binary pattern. LBP is defined as a gray scale invariant texture measure and is a useful
tool to model texture images. The original LBP operator labels the pixels of an image
by thresholding the 3x3 neighbourhood of each pixel with the value of the central pixel
and concatenating the results binomially to form a number.
Image features are extracted and compared using Euclidian distance measure based K
nearest neighbour classification algorithm. The results shows that LBP consistently
performs much better than the remaining other models. For testing the proposed
approach, the WANG database. This database is a subset of Corel stock photo database.
It consists of 10 different categories having 100 images each.
48
Wang, Jeaff Zheng. "Spatially Enhanced Local Binary Patterns for Face Detection and Recognition in Mobile Device Applications." Thesis, 2013. http://hdl.handle.net/1807/43339.
Full textAbstract:
Face detection and recognition has been very popular topics. Recently, its applications for mobile devices have gained tremendous attention due to the rapid expansion of the market.
Although numerous techniques exist for face detection and recognition, only a few solve realistic challenges under the mobile device application environment. In this thesis, we propose an automatic face authentication system including both face detection and recognition components for mobile device applications by using spatially enhanced Local Binary Patterns (LBP) feature extraction.
The first contribution is to propose a fast and accurate face detector by using LBP features and its spatially enhanced variant. The simplicity of LBP ensures low computational complexity and spatially enhanced LBP achieves high accuracy.
The second contribution is to propose color based spatially enhanced LBP features for face recognition. The proposed features achieve high accuracy by extracting complementary information from color channels and spatial correlations between LBP features.
49
"Particle Image Segmentation Based on Bhattacharyya Distance." Master's thesis, 2015. http://hdl.handle.net/2286/R.I.34888.
Full textAbstract:
abstract: Image segmentation is of great importance and value in many applications. In computer vision, image segmentation is the tool and process of locating objects and boundaries within images. The segmentation result may provide more meaningful image data. Generally, there are two fundamental image segmentation algorithms: discontinuity and similarity. The idea behind discontinuity is locating the abrupt changes in intensity of images, as are often seen in edges or boundaries. Similarity subdivides an image into regions that fit the pre-defined criteria. The algorithm utilized in this thesis is the second category.
This study addresses the problem of particle image segmentation by measuring the similarity between a sampled region and an adjacent region, based on Bhattacharyya distance and an image feature extraction technique that uses distribution of local binary patterns and pattern contrasts. A boundary smoothing process is developed to improve the accuracy of the segmentation. The novel particle image segmentation algorithm is tested using four different cases of particle image velocimetry (PIV) images. The obtained experimental results of segmentations provide partitioning of the objects within 10 percent error rate. Ground-truth segmentation data, which are manually segmented image from each case, are used to calculate the error rate of the segmentations.<br>Dissertation/Thesis<br>Masters Thesis Electrical Engineering 2015
50
Lai, Sheng-Lin, and 賴聖霖. "Human and Omnidirectional Service Robot Interactions by Face Expression Recognition with Improved Local Binary Pattern and Localization with Depth Image." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/ths24t.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>電機工程系<br>107<br>By using the RGB-D camera, the omnidirectional service robot (ODSR) searches and detects the human with his/her hand gesture over a specific time interval. After the hand gesture has been detected when ODSR neighbor the detected human between 3m, the RGB-D camera’s depth image will estimate the coordinate of the detected human. Then the ODSR will also receive that information and reaches the position 0.75-1.25m with respect to human and -29°~29° with respect to the camera optical axis such that his/her six face expressions (e.g., anger, disgust, fear, happy, surprise, and sadness) is recognized. These six face expressions are recognized by the improved local binary pattern (ILBP) integrating eyes, nose and mouth regions these three dividing regions segmented by face landmarks and through the individual training and testing of 6 databases (e.g., NTUST-IRL, Cohn-Kanada, JAFFE, FACES, KDEF, MMI) using multiclass SVM to get verified the methodology. It not only improves the recognized rate but also reduce the computation time of off-line training and on-line recognition. Based on the recognized result, the human-robot interaction (HRI), e.g., the text description on screen which is according to the recognition result, simultaneously, the camera detected confirmation through the “raising human hand”, are executed. Based on the information of image processing, the planning pose for searching or tracking human is accurately achieved by the ODSR with the adaptive finite-time hierarchical saturated control (AFTHSC). The effectiveness and robustness of the overall system is validated by a series of HRI experiments.