Academic literature on the topic 'Local binary pattern'

<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>

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.

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.

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.

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

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.

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.

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.

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.