To see the other types of publications on this topic, follow the link: Alignment of images.
Dissertations / Theses on the topic 'Alignment of images'
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 'Alignment of images.'
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
Gieffers, Amy Christina 1975. "Image alignment algorithms for ultrasound images with contrast." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/46193.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998.Includes bibliographical references (leaves 70-74).
by Amy Christina Gieffers.
M.Eng.
2
Melbourne, A. "Alignment of contrast enhanced medical images." Thesis, University College London (University of London), 2009. http://discovery.ucl.ac.uk/15846/.
Full textAbstract:
The re-alignment of series of medical images in which there are multiple contrast variations is difficult. The reason for this is that the popularmeasures of image similarity used to drive the alignment procedure do not separate the influence of intensity variation due to image feature motion and intensity variation due to feature enhancement. In particular, the appearance of new structure poses problems when it has no representation in the original image. The acquisition of many images over time, such as in dynamic contrast enhanced MRI, requires that many images with different contrast be registered to the same coordinate system, compounding the problem. This thesis addresses these issues, beginning by presenting conditions under which conventional registration fails and proposing a solution in the form of a ’progressive principal component registration’. The algorithm uses a statistical analysis of a series of contrast varying images in order to reduce the influence of contrast-enhancement that would otherwise distort the calculation of the image similarity measures used in image registration. The algorithm is shown to be versatile in that it may be applied to series of images in which contrast variation is due to either temporal contrast enhancement changes, as in dynamic contrast-enhanced MRI or intrinsically in the image selection procedure as in diffusion weighted MRI.
3
Noble, Nicholas Michael Ian. "Information alignment and extraction from cardiac magnetic resonance images." Thesis, King's College London (University of London), 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.415344.
Full text
4
Matos, Luís Miguel de Oliveira. "Lossless compression algorithms for microarray images and whole genome alignments." Doctoral thesis, Universidade de Aveiro, 2015. http://hdl.handle.net/10773/14273.
Full textAbstract:
Doutoramento em InformáticaNowadays, in the 21st century, the never-ending expansion of information is a major global concern. The pace at which storage and communication resources are evolving is not fast enough to compensate this tendency. In order to overcome this issue, sophisticated and efficient compression tools are required. The goal of compression is to represent information with as few bits as possible. There are two kinds of compression, lossy and lossless. In lossless compression, information loss is not tolerated so the decoded information is exactly the same as the encoded one. On the other hand, in lossy compression some loss is acceptable. In this work we focused on lossless methods. The goal of this thesis was to create lossless compression tools that can be used in two types of data. The first type is known in the literature as microarray images. These images have 16 bits per pixel and a high spatial resolution. The other data type is commonly called Whole Genome Alignments (WGA), in particularly applied to MAF files. Regarding the microarray images, we improved existing microarray-specific methods by using some pre-processing techniques (segmentation and bitplane reduction). Moreover, we also developed a compression method based on pixel values estimates and a mixture of finite-context models. Furthermore, an approach based on binary-tree decomposition was also considered. Two compression tools were developed to compress MAF files. The first one based on a mixture of finite-context models and arithmetic coding, where only the DNA bases and alignment gaps were considered. The second tool, designated as MAFCO, is a complete compression tool that can handle all the information that can be found in MAF files. MAFCO relies on several finite-context models and allows parallel compression/decompression of MAF files.
Hoje em dia, no século XXI, a expansão interminável de informação é uma grande preocupação mundial. O ritmo ao qual os recursos de armazenamento e comunicação estão a evoluir não é suficientemente rápido para compensar esta tendência. De forma a ultrapassar esta situação, são necessárias ferramentas de compressão sofisticadas e eficientes. A compressão consiste em representar informação utilizando a menor quantidade de bits possível. Existem dois tipos de compressão, com e sem perdas. Na compressão sem perdas, a perda de informação não é tolerada, por isso a informação descodificada é exatamente a mesma que a informação que foi codificada. Por outro lado, na compressão com perdas alguma perda é aceitável. Neste trabalho, focámo-nos apenas em métodos de compressão sem perdas. O objetivo desta tese consistiu na criação de ferramentas de compressão sem perdas para dois tipos de dados. O primeiro tipo de dados é conhecido na literatura como imagens de microarrays. Estas imagens têm 16 bits por píxel e uma resolução espacial elevada. O outro tipo de dados é geralmente denominado como alinhamento de genomas completos, particularmente aplicado a ficheiros MAF. Relativamente às imagens de microarrays, melhorámos alguns métodos de compressão específicos utilizando algumas técnicas de pré-processamento (segmentação e redução de planos binários). Além disso, desenvolvemos também um método de compressão baseado em estimação dos valores dos pixéis e em misturas de modelos de contexto-finito. Foi também considerada, uma abordagem baseada em decomposição em árvore binária. Foram desenvolvidas duas ferramentas de compressão para ficheiros MAF. A primeira ferramenta, é baseada numa mistura de modelos de contexto-finito e codificação aritmética, onde apenas as bases de ADN e os símbolos de alinhamento foram considerados. A segunda, designada como MAFCO, é uma ferramenta de compressão completa que consegue lidar com todo o tipo de informação que pode ser encontrada nos ficheiros MAF. MAFCO baseia-se em vários modelos de contexto-finito e permite compressão/descompressão paralela de ficheiros MAF.
5
Queimadelas, Cátia Cristina Arranca. "Automated segmentation, tracking and evaluation of bacteria in microscopy images." Master's thesis, Faculdade de Ciências e Tecnologia, 2012. http://hdl.handle.net/10362/8435.
Full textAbstract:
Dissertação para obtenção do Grau de Mestre em
Engenharia BiomédicaMost of the investigation in microbiology relies on microscope imaging and needs to be complemented with reliable methods of computer assisted image processing, in order to avoid manual analysis. In this work, a method to assist the study of the in vivo kinetics of protein expression from Escherichia coli cells was developed. Confocal fluorescence microscopy (CFM) and Differential Interference Contrast (DIC) microscopy images were acquired and processed using the developed method. This method comprises two steps: the first one is focused on the cells detection using DIC images. The latter aligns both DIC and CFM images and computes the fluorescence level emitted by each cell. For the first step, the Gradient Path Labelling (GPL) algorithm was used which produces a moderate over-segmented DIC image. The proposed algorithm, based on decision trees generated by the Classification and Regression Trees (CART) algorithm, discards the backgrounds regions and merges the regions belonging to the same cell. To align DIC/fluorescence images an exhaustive search of the relative position and scale parameters that maximizes the fluorescence inside the cells is made. After the cells have been located on the CFM images, the fluorescence emitted by each cell is evaluated. The discard classifier performed with an error rate of 1:81% 0:98% and the merge classifier with 3:25% 1:37%. The segmentation algorithm detected 93:71% 2:06% of the cells in the tested images. The tracking algorithm correctly followed 64:52% 16:02% of cells and the alignment method successfully aligned all the tested images.
6
Härd, Victoria. "Automatic Alignment of 2D Cine Morphological Images Using 4D Flow MRI Data." Thesis, Linköpings universitet, Datorseende, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-131470.
Full textAbstract:
Cardiovascular diseases are among the most common causes of death worldwide. One of the recently developed flow analysis technique called 4D flow magnetic resonance imaging (MRI) allows an early detection of such diseases. Due to the limited resolution and contrast between blood pool and myocardium of 4D flow images, cine MR images are often used for cardiac segmentation. The delineated structures are then transferred to the 4D Flow images for cardiovascular flow analysis. Cine MR images are however acquired with multiple breath-holds, which can be challenging for some people, especially, when a cardiovascular disease is present. Consequently, unexpected breathing motion by a patient may lead to misalignments between the acquired cine MR images. The goal of the thesis is to test the feasibility of an automatic image registration method to correct the misalignment caused by respiratory motion in morphological 2D cine MR images by using the 4D Flow MR as the reference image. As a registration method relies on a set of optimal parameters to provide desired results, a comprehensive investigation was performed to find such parameters. Different combinations of registration parameters settings were applied on 20 datasets from both healthy volunteers and patients. The best combinations, selected on the basis of normalized cross-correlation, were evaluated using the clinical gold-standard by employing widely used geometric measures of spatial correspondence. The accuracy of the best parameters from geometric evaluation was finally validated by using simulated misalignments. Using a registration method consisting of only translation improved the results for both datasets from healthy volunteers and patients and the simulated misalignment data. For the datasets from healthy volunteers and patients, the registration improved the results from 0.7074 ± 0.1644 to 0.7551 ± 0.0737 in Dice index and from 1.8818 ± 0.9269 to 1.5953 ± 0.5192 for point-to-curve error. These values are a mean value for all the 20 datasets. The results from geometric evaluation on the data from both healthy volunteers and patients show that the developed correction method is able to improve the alignment of the cine MR images. This allows a reliable segmentation of 4D flow MR images for cardiac flow assessment.
7
Bergnéhr, Leo. "Segmentation and Alignment of 3-D Transaxial Myocardial Perfusion Images and Automatic Dopamin Transporter Quantification." Thesis, Linköping University, Department of Biomedical Engineering, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-11716.
Full textAbstract:
Nukleärmedicinska bilder som exempelvis SPECT (Single Photon Emission Tomogra-phy) är en bildgenererande teknik som ofta används i många applikationer vid mätning av fysiologiska egenskaper i den mänskliga kroppen. En vanlig sorts undersökning som använder sig av SPECT är myokardiell perfusion (blodflöde i hjärtvävnaden), som ofta används för att undersöka t.ex. en möjlig hjärtinfarkt. För att göra det möjligt för läkare att ställa en kvalitativ diagnos baserad på dessa bilder, måste bilderna först segmenteras och roteras av en biomedicinsk analytiker. Detta utförs på grund av att hjärtat hos olika patienter, eller hos patienter vid olika examinationstillfällen, inte är lokaliserat och roterat på samma sätt, vilket är ett väsentligt antagande av läkaren vid granskning
av bilderna. Eftersom olika biomedicinska analytiker med olika mängd erfarenhet och expertis roterar bilderna olika uppkommer variation av de slutgiltiga bilder, vilket ofta kan vara ett problem vid diagnostisering.
En annan sorts nukleärmedicinsk undersökning är vid kvantifiering av dopaminreceptorer i de basala ganglierna i hjärnan. Detta utförs ofta på patienter som visar symptom av Parkinsons sjukdom, eller liknande sjukdomar. För att kunna bestämma graden av sjukdomen används ofta ett utförande för att räkna ut olika kvoter mellan områden runt dopaminreceptorerna. Detta är ett tröttsamt arbete för personen som utför kvantifieringen och trots att de insamlade bilderna är tredimensionella, utförs kvantifieringen allt för ofta endast på en eller flera skivor av bildvolymen. I likhet med myokardiell perfusionsundersökningar är variation mellan kvantifiering utförd av olika personer en möjlig felkälla.
I den här rapporten presenteras en ny metod för att automatiskt segmentera hjärtats vänstra kammare i SPECT-bilder. Segmenteringen är baserad på en intensitetsinvariant lokal-fasbaserad lösning, vilket eliminerar svårigheterna med den i myokardiella perfusionsbilder ofta varierande intensiteten. Dessutom används metoden för att uppskatta vinkeln hos hjärtats vänstra kammare. Efter att metoden sedan smått justerats används den som ett förslag på ett nytt sätt att automatiskt kvantifiera dopaminreceptorer i de basala ganglierna, vid användning av den radioaktiva lösningen DaTSCAN.
Nuclear medical imaging such as SPECT (Single Photon Emission Tomography) is an imaging modality which is readily used in many applications for measuring physiological properties of the human body. One very common type of examination using SPECT is when measuring myocardial perfusion (blood flow in the heart tissue), which is often used to examine e.g. a possible myocardial infarction (heart attack). In order for doctors to give a qualitative diagnose based on these images, the images must first be segmented and rotated by a medical technologist. This is performed due to the fact that the heart of different patients, or for patients at different times of examination, is not situated and rotated equally, which is an essential assumption for the doctor when examining the images. Consequently, as different technologists with different amount of experience and expertise will rotate images differently, variability between operators arises and can often become a problem in the process of diagnosing.
Another type of nuclear medical examination is when quantifying dopamine transporters in the basal ganglia in the brain. This is commonly done for patients showing symptoms of Parkinson’s disease or similar diseases. In order to specify the severity of the disease, a scheme for calculating different fractions between parts of the dopamine transporter area is often used. This is tedious work for the person performing the quantification, and despite the acquired three dimensional images, quantification is too often performed on one or more slices of the image volume. In resemblance with myocardial perfusion examinations, variability between different operators can also here present a possible source of errors.
In this thesis, a novel method for automatically segmenting the left ventricle of the heart in SPECT-images is presented. The segmentation is based on an intensity-invariant local-phase based approach, thus removing the difficulty of the commonly varying intensity in myocardial perfusion images. Additionally, the method is used to estimate the angle of the left ventricle of the heart. Furthermore, the method is slightly adjusted, and a new approach on automatically quantifying dopamine transporters in the basal ganglia using the DaTSCAN radiotracer is proposed.
8
Kesler, Joseph Michael. "Automated Alignment of Aircraft Wing Radiography Images Using a Modified Rotation, Scale, and Translation Invariant Phase Correlation Algorithm Employing Local Entropy for Peak Detection." University of Cincinnati / OhioLINK, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1218604857.
Full text
9
Petrovic, Aleksandar. "Connectivity driven registration of magnetic resonance images of the human brain." Thesis, University of Oxford, 2010. http://ora.ox.ac.uk/objects/uuid:fd95c6d4-06d2-41b4-b6f2-5cbd73cb83a9.
Full textAbstract:
Image registration methods underpin many analysis techniques in neuroimaging. They are essential in group studies when images of different individuals or different modalities need to be brought into a common reference frame. This thesis explores the potential of brain connectivity- driven alignment and develops surface registration techniques for magnetic resonance imaging (MRI), which is a noninvasive neuroimaging tool for probing function and structure of the human brain. The first part of this work develops a novel surface registration framework, based on free mesh deformations, which aligns cortical and subcortical surfaces by matching structural connectivity patterns derived using probabilistic tractography (diffusion-weighted MRI). Structural, i.e. white matter, connectivity is a good predictor of functional specialisation and structural connectivity-driven registration can therefore be expected to enhance the alignment of functionally homologous areas across subjects. The second part validates developed methods for cortical surfaces. Resting State Networks are used in an innovative way to delineate several functionally distinct regions, which were then used to quantify connectivity-driven registration performance by measuring the inter- subject overlap before and after registration. Consequently, the proposed method is assessed using an independent imaging modality and the results are compared to results from state-of-the-art cortical geometry-driven surface registration methods. A connectivity-driven registration pipeline is also developed for, and applied to, the surfaces of subcortical structures such as the thalamus. It is carefully validated on a set of artificial test examples and compared to another novel surface registration paradigm based on spherical wavelets. The proposed registration pipeline is then used to explore the differences in the alignment of two groups of subjects, healthy controls and Alzheimer's disease patients, to a common template. Finally, we propose how functional connectivity can be used instead of structural connectivity for driving registrations, as well as how the surface-based framework can be extended to a volumetric one. Apart from providing the benefits such as the improved functional alignment, we hope that the research conducted in this thesis will also represent the basis for the development of templates of structural and functional brain connectivity.
10
Ramírez, Orozco Raissel. "High dynamic range content acquisition from multiple exposures." Doctoral thesis, Universitat de Girona, 2016. http://hdl.handle.net/10803/371162.
Full textAbstract:
The limited dynamic range of digital images can be extended by composing different exposures of the same scene to produce HDR images. This thesis is composed of an overview of the state of the art techniques and three methods to tackle the image alignment and deghosting problems in the HDR imaging domain.
The first method detects the areas affected by motion, registers the dynamic objects over a reference image, and combines low-dynamic range values to recover HDR values in the whole image.
The second approach builds multiscopic HDR images from LDR multi-exposure images. It is based on a patch match algorithm which was adapted and improved to take advantage of epipolar geometry constraints of stereo images.
The last method proposes to replace under/over exposed pixels in the reference image by using valid HDR values from other images in the multi-exposure LDR image sequence.El limitado rango dinámico de las imágenes digitales puede ampliarse mezclando varias imágenes adquiridas con diferentes valores de exposición. Esta tesis incluye un detallado resumen del estado del arte y tres métodos diferentes para alinear las imágenes y corregir el efecto ’ghosting’ en imágenes HDR. El primer método está centrado en detectar las áreas afectadas por el movimiento y registrar los objetos dinámicos sobre una imagen de referencia de modo que se logre recuperar información a lo largo de toda la imagen. Nuestra segunda propuesta es un método para obtener imágenes HDR multiscópicas a partir de diferentes exposiciones LDR. Está basado en un algoritmo de ’patch match’ que ha sido adaptado para aprovechar las ventajas de las restricciones de la geometría epipolar de imágenes estéreo. Por último proponemos reemplazar los píxeles saturados en la imagen de referencia usando valores correctos de otras imágenes de la secuencia.
11
Verguet, Amandine. "Développements méthodologiques et informatiques pour la microscopie électronique en transmission appliqués à des échantillons biologiques Alignment of Tilt Series (Chapter 7 of the Book: Cellular Imaging: Electron Tomography and Related Techniques, Hanssen Eric) An ImageJ tool for simplified post-treatment of TEM phase contrast images (SPCI) Comparison of methods based on feature tracking for fiducial-less image alignment in electron tomography." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS487.
Full textAbstract:
La microscopie électronique en transmission est une technique pertinente pour les études structurales en biologie. Certaines méthodes d’acquisition et d’analyse doivent être améliorées pour permettre l’observation d’échantillons sensibles aux doses d’électrons dans de bonnes conditions de contraste et de rapport signal sur bruit. Au cours de cette thèse, j’ai exploré différentes approches méthodologiques et informatiques dans le but d’améliorer la qualité des images. J’ai ainsi évalué la pertinence de la combinaison de l’imagerie en énergie filtrée avec le mode STEM. Je montre que cette combinaison est prometteuse puisqu’elle permet d’améliorer le rapport signal sur bruit des images. Par ailleurs, j’ai collaboré à des développements algorithmiques et logiciels pour la reconstitution d’images de contraste de phase. Ceci permet l’amélioration du contraste par rapport à une acquisition classique. Je montre aussi qu’à cette fin, la phase plate tout comme les séries focales sont des outils efficaces. En étudiant une approche logicielle pour l’exploitation des séries focales, nous avons déterminé qu’il est possible d’obtenir, en plus de données quantitatives, un résultat qualitatif à partir d’une seule image. J’ai ainsi développé le plugin SPCI pour le logiciel ImageJ, qui permet de traiter de une à trois images focales. Je m’intéresse également à l’optimisation du processus de reconstruction tomographique, tant à l’alignement qu’à la reconstruction proprement dite. L’approche évaluée pour l’alignement utilise des points caractéristiques associés à des descripteurs locaux. Elle s’est montrée performante et permet de traiter des images sans marqueurs fiduciaires. Enfin, je propose une nouvelle méthode unifiée de reconstruction tridimensionnelle de séries tomographiques parcimonieuses. Il en découle une approche innovante mélangeant reconstruction et alignement dont l’ébauche servira de base à des travaux futurs pour le traitement de séries tomographiques parcimonieuses. L’ensemble des méthodes évoquées ici, leur validation, ainsi que les perspectives d’évolution associées sont décrites dans ce manuscritTransmission Electron Microscopy is a major tool for performing structural studies in biology. Some methods used for image sampling and analysis need to be improved in order to observe electron dose sensitive samples with good contrast and good signal to noise ratio. During this thesis, various methodological and computational approaches have been studied which aim to improve image quality. First, I evaluated the relevance of combining energy filtered imaging with the STEM mode. I show that this allows an improvement of the signal to noise ratio of images. Then, I devised an algorithm that generates an image from phase data. This approach allows improving the image contrast over direct imaging. The use of a phase plate and focal tilt series are both efficient tools to achieve this goal. While working on the software approach for processing of tilt series, we found that a qualitative result can be obtained from a single image. I developped the SPCI plugin for the ImageJ software. It allows processing between one and three focal images. My work involves optimization of the tomographic reconstruction process, including working with both alignment algorithms and reconstruction algorithms. I expose my studies on image alignment methods used on tilt series. These methods do rely on the use of key points and associated local descriptors. They have proved to be efficient to process images lacking fiducial markers. Finally, I propose a new unified algorithmic approach for 3D reconstruction of tomographic tilt series acquired with sparse sampling. I then derived another novel method that integrates the image alignment step in the process. Studies and developments will continue on both methods in futur work
12
Wagner, Katharina. "Image Alignment." Bachelor's thesis, Universitätsbibliothek Chemnitz, 2009. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-200901305.
Full textAbstract:
Aligning two images by point to point correspondence is a hard optimization problem. It
can be solved using t-Extremal Optimization or with a modification of this method called
Fitness threshold accepting. In this work these two methods are tested and compared to
see whether one of the methods should be preferred for image alignment. Since real image
data is almost always noisy the performance of the methods under conditions like noisy and
outlying data is analyzed too.
13
Authesserre, Jean-baptiste. "Alignement paramétrique d’images : proposition d’un formalisme unifié et prise en compte du bruit pour le suivi d’objets." Thesis, Bordeaux 1, 2010. http://www.theses.fr/2010BOR14136/document.
Full textAbstract:
L’alignement d’images paramétrique a de nombreuses applications pour la réalité augmentée, la compression vidéo ou encore le suivi d’objets. Dans cette thèse, nous nous intéressons notamment aux techniques de recalage d’images (template matching) reposant sur l’optimisation locale d’une fonctionnelle d’erreur. Ces approches ont conduit ces dernières années à de nombreux algorithmes efficaces pour le suivi d’objets. Cependant, les performances de ces algorithmes ont été peu étudiées lorsque les images sont dégradées par un bruit important comme c’est le cas, par exemple, pour des captures réalisées dans des conditions de faible luminosité. Dans cette thèse, nous proposons un nouveau formalisme, appelé formalisme bidirectionnel, qui unifie plusieurs approches de l’état de l’art. Ce formalisme est utilisé dans un premier temps pour porter un éclairage nouveau sur un grand nombre d’approches de la littérature et en particulier sur l’algorithme ESM (Efficient Second-order Minimization). Nous proposons ensuite une étude théorique approfondie de l’influence du bruit sur le processus d’alignement. Cette étude conduit à la définition de deux nouvelles familles d’algorithmes, les approches ACL (Asymmetric Composition on Lie Groups) et BCL (Bidirectional Composition on Lie Groups) qui permettent d’améliorer les performances en présence de niveaux de bruit asymétriques (Rapport Signal sur Bruit différent dans les images). L’ensemble des approches introduites sont validées sur des données synthétiques et sur des données réelles capturées dans des conditions de faible luminositéParametric image alignment is a fundamental task of many vision applications such as object tracking, image mosaicking, video compression and augmented reality. To recover the motion parameters, direct image alignment works by optimizing a pixel-based difference measure between a moving image and a fixed-image called template. In the last decade, many efficient algorithms have been proposed for parametric object tracking. However, those approaches have not been evaluated for aligning images of low SNR (Signal to Noise ratio) such as images captured in low-light conditions. In this thesis, we propose a new formulation of image alignment called Bidirectional Framework for unifying existing state of the art algorithms. First, this framework allows us to produce new insights on existing approaches and in particular on the ESM (Efficient Second-order Minimization) algorithm. Subsequently, we provide a theoretical analysis of image noise on the alignment process. This yields the definition of two new approaches : the ACL (Asymmetric Composition on Lie Groups) algorithm and the BCL (Bidirectional Composition on Lie Groups) algorithm, which outperform existing approaches in presence of images of different SNR. Finally, experiments on synthetic and real images captured under low-light conditions allow to evaluate the new and existing approaches under various noise conditions
14
Carroll, Hyrum D. "Biologically Relevant Multiple Sequence Alignment." Diss., CLICK HERE for online access, 2008. http://contentdm.lib.byu.edu/ETD/image/etd2623.pdf.
Full text
15
Studholme, Colin. "Measures of 3D medical image alignment." Thesis, King's College London (University of London), 1997. https://kclpure.kcl.ac.uk/portal/en/theses/measures-of-3d-medical-image-alignment(7e3dd0a9-6dc2-4ff0-8b9f-8fd513728ffb).html.
Full text
16
Duchenne, Olivier. "Non-rigid image alignment for object recognition." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2012. http://tel.archives-ouvertes.fr/tel-00906074.
Full textAbstract:
La vision permet aux animaux de recueillir une information riche et détaillée sur leur environnent proche ou lointain. Les machines ont aussi accès à cette information riche via leurs caméras. Mais, elles n'ont pas encore le logiciel adéquat leur permettant de la traiter pour transformer les valeurs brutes des pixels de l'image en information plus utile telle que la nature, la position, et la fonction des objets environnants. Voilà une des raisons pour laquelle il leur est difficile de se mouvoir dans un environnement inconnu, et d'interagir avec les humains ou du matériel dans des scénarios non-planifiés. Cependant, la conception de ce logiciel comporte de multiples défis. Parmi ceux-ci, il est difficile de comparer deux images entre elles, par exemple, afin que la machine puisse reconnaître que ce qu'elle voit est similaire à une image qu'elle a déjà vue et identifiée. Une des raisons de cette difficulté est que la machine ne sait pas, a priori, quelles parties des deux images se correspondent, et ne sait donc pas quoi comparer avec quoi. Cette thèse s'attaque à ce problème et propose une série d'algorithmes permettant de trouver les parties correspondantes entre plusieurs images, ou en d'autre terme d'aligner les images. La première méthode proposée permet d'apparier ces parties de manière cohérente en prenant en compte les interactions entre plus de deux d'entre elles. Le deuxième algorithme proposé applique avec succès une méthode d'alignement pour déterminer la catégorie d'un objet centré dans une image. Le troisième est optimisé pour la vitesse et tente de détecter un objet d'une catégorie donné où qu'il soit dans l'image.
17
Fiorani, Fulvia M. "Active mirror alignment for free electron lasers." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2002. http://library.nps.navy.mil/uhtbin/hyperion-image/02Dec%5FFiorani.pdf.
Full textAbstract:
Thesis (M.S. in Applied Physics)--Naval Postgraduate School, December 2002.Thesis advisor(s): Bruce C. Denardo, Thomas J. Hofler. Includes bibliographical references (p. 61). Also available online.
18
Magnvall, Andreas, and Alexander Henne. "Real-time Aerial Photograph Alignment using Feature Matching." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176658.
Full textAbstract:
With increased mobile hardware capabilities, improved UAVs and modern algorithms, accurate maps can be created in real-time by capturing overlapping photographs of the ground. A method for mapping that can be used is to position photos by relying purely on the GPS position and altitude. However, GPS inaccuracies will be visible in the created map. In this paper, we will instead present a method for aligning the photos correctly with the help of feature matching. Feature matching is a well-known method which analyses two photos to find similar parts. If an overlap exists, feature matching can be used to find and localise those parts, which can be used for positioning one image over the other at the overlap. When repeating the process, a whole map can be created. For this purpose, we have also evaluated a selection of feature detection and matching algorithms. The algorithm found to be the best was SIFT with FLANN, which was then used in a prototype for creating a complete map of a forest. Feature matching is in many cases superior to GPS positioning, although it cannot be fully depended on as failed or incorrect matching is a common occurrence.
19
Xin, Huijun. "DNA-Templated Surface Alignment and Characterization of Carbon Nanotubes." Diss., CLICK HERE for online access, 2006. http://contentdm.lib.byu.edu/ETD/image/etd1394.pdf.
Full text
20
Höhl, Michael. "Is multiple sequence alignment required for accurate inference of phylogeny? /." [St. Lucia, Qld.], 2006. http://www.library.uq.edu.au/pdfserve.php?image=thesisabs/absthe19790.pdf.
Full text
21
Yang, Christopher Minzer. "Spectral control of viscous alignment for deformation invariant image matching." Thesis, Massachusetts Institute of Technology, 2009. http://hdl.handle.net/1721.1/53158.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.Includes bibliographical references (p. 55-57).
We present a new approach to deformation invariant image matching. Our approach retains the broad range of linear and nonlinear deformations that viscous alignment methods can model, but introduces a selectivity that is necessary for recognition. Our method models viscous kernels with an over-complete filter basis. The basis is parameterized with a single scalar parameter, the spectral radius r, which selects deformations ranging in complexity from tranlations to "turbulence." The spectral radius is used for cascaded alignment starting from low deformation frequencies and finishing with high deformation frequencies. Cascaded alignment makes deformation invariant matching for recognition feasible and efficient. Because spectral radii map directly to deformation complexity, their contributions are selectively weighed to calculate the template-target similarity. In this way, our model can distinguish deformations by their relevance to recognition, without losing the flexibility of viscous alignment for handling nonlinear deformations. Our approach is applied to recognize flexible bodies of animals, and results indicate that the method is very promising.
by Christopher Minzer Yang.
M.Eng.
22
Gonzalez, Manuel Guillen. "Spherical mosaic construction using physical analogy for consistent image alignment." Thesis, University of Central Lancashire, 1999. http://clok.uclan.ac.uk/20297/.
Full textAbstract:
The research contained in this thesis is an investigation into mosaic construction. Mosaic techniques are used to obtain images with a large field of view by assembling a sequence of smaller individual overlapping images. In existing methods of mosaic construction only successive images are aligned. Accumulation of small alignment errors occur, and in the case of the image path returning to a previous position in the mosaic, a significant mismatch between nonconsecutive images will result (looping path problem). A new method for consistently aligning all the images in a mosaic is proposed in this thesis. This is achieved by distribution of the small alignment errors. Each image is allowed to modify its position relative to its neighbour images in the mosaic by a small amount with respect to the computed registration. Two images recorded by a rotating ideal camera are related by the same transformation that relates the camera's sensor plane at the time the images were captured. When two images overlap, the intensity values in both images coincide through the intersection line of the sensor planes. This intersection line has the property that the images can be seamlessly joined through that line. An analogy between the images and the physical world is proposed to solve the looping path problem. The images correspond to rigid objects, and these are linked with forces which pull them towards the right positions with respect to their neighbours. That is, every pair of overlapping images are "hinged" through their corresponding intersection line. Aided by another constraint named the spherical constraint, this network of selforganising images has the ability of distributing itself on the surface of a sphere. As a direct result of the new concepts developed in this research work, spherical mosaics (i.e. mosaics with unlimited horizontal and vertical field of view) can be created.
23
Ogden, Samuel R. "Automatic Content-Based Temporal Alignment of Image Sequences with Varying Spatio-Temporal Resolution." BYU ScholarsArchive, 2012. https://scholarsarchive.byu.edu/etd/3303.
Full textAbstract:
Many applications use multiple cameras to simultaneously capture imagery of a scene from different vantage points on a rigid, moving camera system over time. Multiple cameras often provide unique viewing angles but also additional levels of detail of a scene at different spatio-temporal resolutions. However, in order to benefit from this added information the sources must be temporally aligned. As a result of cost and physical limitations it is often impractical to synchronize these sources via an external clock device. Most methods attempt synchronization through the recovery of a constant scale factor and offset with respect to time. This limits the generality of such alignment solutions. We present an unsupervised method that utilizes a content-based clustering mechanism in order to temporally align multiple non-synchronized image sequences of different and varying spatio-temporal resolutions. We show that the use of temporal constraints and dynamic programming adds robustness to changes in capture rates, field of view, and resolution.
24
Schwartz, Bonnie Jo. "An Evolutionary Programming Algorithm for Automatic Chromatogram Alignment." Wright State University / OhioLINK, 2007. http://rave.ohiolink.edu/etdc/view?acc_num=wright1175715183.
Full text
25
Partington, Mike. "AUTOMATIC IMAGE TO MODEL ALIGNMENT FOR PHOTO-REALISTIC URBAN MODEL RECONSTRUCTION." UKnowledge, 2001. http://uknowledge.uky.edu/gradschool_theses/218.
Full textAbstract:
We introduce a hybrid approach in which images of an urban scene are automatically alignedwith a base geometry of the scene to determine model-relative external camera parameters. Thealgorithm takes as input a model of the scene and images with approximate external cameraparameters and aligns the images to the model by extracting the facades from the images andaligning the facades with the model by minimizing over a multivariate objective function. Theresulting image-pose pairs can be used to render photo-realistic views of the model via texturemapping.Several natural extensions to the base hybrid reconstruction technique are also introduced. Theseextensions, which include vanishing point based calibration refinement and video stream basedreconstruction, increase the accuracy of the base algorithm, reduce the amount of data that mustbe provided by the user as input to the algorithm, and provide a mechanism for automaticallycalibrating a large set of images for post processing steps such as automatic model enhancementand fly-through model visualization.Traditionally, photo-realistic urban reconstruction has been approached from purely image-basedor model-based approaches. Recently, research has been conducted on hybrid approaches, whichcombine the use of images and models. Such approaches typically require user assistance forcamera calibration. Our approach is an improvement over these methods because it does notrequire user assistance for camera calibration.
26
Bjerwe, Ida. "Automatic Alignment Detection and Correction in Infrared and Visual Image Pairs." Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-165887.
Full textAbstract:
Previously well aligned image sensors, mounted on the same camera, might become misaligned depending on external vibrations. It is of interest to be able to automatically detect and correct for this misalignment, and to separate the deviation into pointing- and/or parallax errors. Two methods were evaluated for this purpose, an area based image registration method and a feature based image registration method. In the area based method normalized cross-correlation was used to estimate translation parameters. In the feature based method, SIFT or LIOP descriptors were used to extract features that were matched between the two image modalities to estimate transformation parameters. In both methods only image points that were in focus were extracted to avoid detection of false alignment deviations. The results indicate that the area based image registration method has potential to automatically detect and correct for an alignment deviation. Moreover, the area based method showed potential to separate the deviation into pointing errors and parallax errors. The feature based method was limited to specific scenes but could be used as a complement to the area based method in order to additionally correct for rotation and/or scaling.
27
Jia, Zhen. "Image Registration and Image Completion: Similarity and Estimation Error Optimization." University of Cincinnati / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1406821875.
Full text
28
Burgos, Herrera Diego A. "Towards an image-term co-occurence model for multilingual terminology alignment and cross-language image indexing." Doctoral thesis, Universitat Pompeu Fabra, 2014. http://hdl.handle.net/10803/145644.
Full textAbstract:
This thesis addresses the potential that the relation between terms and images in multilingual specialized documentation has for glossary compilation, terminology alignment, and image indexing. It takes advantage of the recurrent use of these two modes of communication (i.e., text and images) in digital documents to build a bimodal co-occurrence model which aims at dynamically compiling glossaries of a wider coverage. The model relies on the developments of content-based image retrieval (CBIR) and text processing techniques. CBIR is used to make two images from different origin match, and text processing supports term recognition, artifact noun classification, and image-term association. The model aligns one image with its denominating term from collateral text, and then aligns this image with another image of the same artifact from a different document, which also enables the alignment of the two equivalent denominating terms. The ultimate goal of the model is to tackle the limitations and drawbacks of current static terminological repositories by generating bimodal, bilingual glossaries that reflect real usage, even when terms and images may originate from noisy corpora.Esta tesis enfoca la relación entre términos e imágenes en documentación especializada y su potencial para compilación de glosarios, alineación de terminología e indexación de imágenes. Asimismo, esta investigación se vale del frecuente uso de estos dos modos de comunicación (i.e., texto e imágenes) en documentos digitales para construir un modelo de concurrencia bimodal que guíe la compilación de glosarios de más cobertura. El modelo se basa en los desarrollos de técnicas de recuperación de imágenes por contenido (CBIR) y de procesamiento de texto. Las técnicas de CBIR se usan aquí para conectar dos imágenes de distinto origen, mientras que el procesamiento de texto sustenta las tareas de reconocimiento de términos, clasificación de nombres de artefacto y asociación término-imagen. El modelo asocia una imagen con el término del texto circundante que la denomina y luego alinea esta imagen con otra imagen del mismo artefacto pero que se origina en otro documento, lo cual permite también la alineación de los dos términos equivalentes que denominan los artefactos de las imágenes. El objetivo principal del modelo es contribuir a compensar el estatismo, las limitaciones y las desventajas de los repositorios terminológicos actuales mediante la generación de glosarios bimodales bilingües que reflejen el uso real de los términos, incluso cuando éstos y sus imágenes se originen en corpus problemáticos.
29
Su, QingLang. "Automatic image alignment for clinical evaluation of patient setup errors in radiotherapy." Thesis, University of Central Lancashire, 2004. http://clok.uclan.ac.uk/20692/.
Full textAbstract:
In radiotherapy, the treatment is typically pursued by irradiating the patient with high energy x-ray beams conformed to the shape of the tumour from multiple directions. Rather than administering the total dose in one session, the dose is often delivered in twenty to thirty sessions. For each session several settings must be reproduced precisely (treatment setup). These settings include machine setup, such as energy, direction, size and shape of the radiation beams as well as patient setup, such as position and orientation of the patient relative to the beams. An inaccurate setup may result in not only recurrence of the tumour but also medical complications. The aim of the project is to develop a novel image processing system to enable fast and accurate evaluation of patient setup errors in radiotherapy by automatic detection and alignment of anatomical features in images acquired during treatment simulation and treatment delivery. By combining various image processing and mathematical techniques, the thesis presents the successful development of an effective approach which includes detection and separation of collimation features for establishment of image correspondence, region based image alignment based on local mutual information, and application of the least-squares method for exhaustive validation to reject outliers and for estimation of global optimum alignment. A complete software tool was developed and clinical validation was performed using both phantom and real radiotherapy images. For the former, the alignment accuracy is shown to be within 0.06 cm for translation and 1.14 degrees for rotation. More significantly, the translation is within the ±0.1 cm machine setup tolerance and the setup rotation can vary between ±1 degree. For the latter, the alignment was consistently found to be similar or better than those based on manual methods. Therefore, a good basis is formed for consistent, fast and reliable evaluation of patient setup errors in radiotherapy.
30
Nishitani, André Toshio Nogueira. "Localização baseada em odometria visual." Universidade de São Paulo, 2015. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-17082016-095838/.
Full textAbstract:
O problema da localização consiste em estimar a posição de um robô com relação a algum referencial externo e é parte essencial de sistemas de navegação de robôs e veículos autônomos. A localização baseada em odometria visual destaca-se em relação a odometria de encoders na obtenção da rotação e direção do movimento do robô. Esse tipo de abordagem é também uma escolha atrativa para sistemas de controle de veículos autônomos em ambientes urbanos, onde a informação visual é necessária para a extração de informações semânticas de placas, semáforos e outras sinalizações. Neste contexto este trabalho propõe o desenvolvimento de um sistema de odometria visual utilizando informação visual de uma câmera monocular baseado em reconstrução 3D para estimar o posicionamento do veículo. O problema da escala absoluta, inerente ao uso de câmeras monoculares, é resolvido utilizando um conhecimento prévio da relação métrica entre os pontos da imagem e pontos do mundo em um mesmo plano.The localization problem consists of estimating the position of the robot with regards to some external reference and it is an essential part of robots and autonomous vehicles navigation systems. Localization based on visual odometry, compared to encoder based odometry, stands out at the estimation of rotation and direction of the movement. This kind of approach is an interesting choice for vehicle control systems in urban environment, where the visual information is mandatory for the extraction of semantic information contained in the street signs and marks. In this context this project propose the development of a visual odometry system based on structure from motion using visual information acquired from a monocular camera to estimate the vehicle pose. The absolute scale problem, inherent with the use of monocular cameras, is achieved using som previous known information regarding the metric relation between image points and points lying on a same world plane.
31
Kozlovski, Nikolai. "TEXT-IMAGE RESTORATION AND TEXT ALIGNMENT FOR MULTI-ENGINE OPTICAL CHARACTER RECOGNITION SYSTEMS." Master's thesis, University of Central Florida, 2006. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/3607.
Full textAbstract:
Previous research showed that combining three different optical character recognition (OCR) engines (ExperVision® OCR, Scansoft OCR, and Abbyy® OCR) results using voting algorithms will get higher accuracy rate than each of the engines individually. While a voting algorithm has been realized, several aspects to automate and improve the accuracy rate needed further research. This thesis will focus on morphological image preprocessing and morphological text restoration that goes to OCR engines. This method is similar to the one used in restoration partial finger prints. Series of morphological dilating and eroding filters of various mask shapes and sizes were applied to text of different font sizes and types with various noises added. These images were then processed by the OCR engines, and based on these results successful combinations of text, noise, and filters were chosen. The thesis will also deal with the problem of text alignment. Each OCR engine has its own way of dealing with noise and corrupted characters; as a result, the output texts of OCR engines have different lengths and number of words. This in turn, makes it impossible to use spaces a delimiter as a method to separate the words for processing by the voting part of the system. Text aligning determines, using various techniques, what is an extra word, what is supposed to be two or more words instead of one, which words are missing in one document compared to the other, etc. Alignment algorithm is made up of a series of shifts in the two texts to determine which parts are similar and which are not. Since errors made by OCR engines are due to visual misrecognition, in addition to simple character comparison (equal or not), a technique was developed that allows comparison of characters based on how they look.M.S.E.E.
Department of Electrical and Computer Engineering
Engineering and Computer Science
Electrical Engineering
32
Areskog, John, and Oden Qvarnström. "Alternative mechanical interfaces for alignment of image sensor and lens in surveillance cameras." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20286.
Full textAbstract:
To manufacture better cameras at lower costs is of great interest to the surveillance industry. Inthe process of manufacturing cameras, the mounting of the optics and the digital image sensor, isa crucial part of producing a high quality image. For high resolution cameras, mechanical passivealignment of the optics and image sensor is insufficient for producing a picture of adequate quality.This is caused by inherit problems from manufacturing, resulting in performance issues for theparts. For the lens, these performance issues causes the light path to deviate and the focal pointto be off center. In the same way, manufacturing of the image sensor causes similar problems.These problems results in an image of subpar quality, if the interface solely relies on mechanicalpassive alignment. To compensate for these problems a computer aided machine is used to alignthe lens and the image sensor. The lens and the sensor, are placed in the machine, aligned forbest possible image quality and fixated in its place. This fixation is done with UV light curedadhesive. The process is drawn with some issues, the curing of the adhesive causes unpredictableshrinkage that affects the image quality. In addition, contaminations such as dust or dirt on theparts, are impossible to remove once the fixation is complete, causing blemishes on the images.These faults results in scrapping of expensive parts, which is costly for the manufacturer. Thisthesis aims to find alternative mounting solutions to the parts, that result in less scrapping ofexpensive components, without sacrificing image quality. The result is two concepts that can beused as inspiration for future improvement of surveillance camera manufacturing. A new adhesiveinterface, that can reduce, manufacturing cost and the unreliable shrinkage of the adhesive, as wellas a new mechanical coupling that allows reassembly after cleaning, is presented.iii
33
Chen, Xin. "Automatic pre-treatment validation in radiotherapy by computer aided 3D-2D image alignment." Thesis, University of Central Lancashire, 2008. http://clok.uclan.ac.uk/21602/.
Full textAbstract:
Most cancer patients may need external beam radiotherapy at certain times. Sufficient exposure of malignant cells and better avoidance of surrounding healthy tissues are necessary in order to minimise damage to non-cancerous regions. Therefore, accurate patient positioning and proper radiation directions as well as dose distributions are crucial. A vital part of external beam radiotherapy is the geometric verification of treatment delivery. This thesis extensively studied three-dimensional (31)) to two-dimensional (2D) image registration methods. The author has proposed two novel methods to register computerised tomography (CT) based volume image data acquired for treatment planning with orthogonal planar images acquired at treatment simulation, which are able to recover the transformation errors in full six degrees of freedom (three translations and three rotations). The first proposed method is a novel feature-based method. It is based on automatic or semi-automatic extraction of object contours from the orthogonal X-ray images, matching with the 3D contours automatically extracted from the planning CT data. The registration is based on the Z-bnffer projection algorithm and the iterative closest point (ICP) algorithm. The novelty of the method proposed by the author is that: with the depth information of the projected features from the 3D model retained by the Z-bnffer method and the correspondence points found by ICP method, the 2D correspondence points are back projected to 3D space. Then the 3D-2D registration can be solved as a 3D-3D registration problem which enables the cost function to be easily built and optimised. The proposed method has been evaluated using simulated data as well as phantom data. For the simulated data, the root-mean-square (RMS) registration errors were 0.70 mm + 0.21 mm for translations and 0.49° + 0.46° for rotations with the capture range up to 18 mm (measured by mean target registration error (mTRE)). For the phantom data, the alignment errors were found to vary from 0.04 mm to 3.3 mm with an average of 1.27 mm for translation, and to vary from 0.02° to 1.64° with an average of 0.82° for rotation. The accuracy compares favourably against some of the other feature-based registration methods, and the computational cost is significantly lower than intensity-based registration methods. Another significant contribution of this research work is the proposed hybrid 3D-2D image registration framework. The novel framework is distinct from other methods by combining the advantages from both feature-based methods and intensity based methods. It can be performed fully automatically which consists of two stages. The first stage is a coarse registration procedure, which is based on the idea of region based segmentation. It enables a fast and rough alignment that can successfully reduce the searching range for the subsequent fine registration. In the fine registration stage, an accelerated digitally reconstructed radiograph (DRR) generation method based on iso-region leaping method is proposed. Based on the generation of a series of region of interest (ROl) bone structure DRRS along the projected anatomical features, the proposed method is computationally effIcient, with registration error less than 0.5 mm measured by rnTRE. The capture range was up to 50 mm for the tested simulated data. For the evaluated phantom data sets from different parts of body, the proposed method was also able to achieve an acceptable registration accuracy with 2.15 mm + 0.82 mm (measured by mTRE). By providing a comparable registration accuracy, the proposed method was shown to be computationally more efficient than other software based methods (i.e. conventional ray casting method and accelerated ray casting based on pre-computations). In addition, an easy-to-use graphic user interface (GUI) was developed which enables the proposed framework to be further evaluated and compared with current clinical software.
34
Yu, Lap Fai. "3D reconstruction and synthesis of facial expressions using a manifold alignment framework /." View abstract or full-text, 2009. http://library.ust.hk/cgi/db/thesis.pl?CSED%202009%20YU.
Full text
35
Crusoe, Henry L. "An analysis of the effect the Enlisted Grade Structure Review has upon First Term Alignment Plan retention requirements." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2003. http://library.nps.navy.mil/uhtbin/hyperion-image/03Mar%5FCrusoe.pdf.
Full textAbstract:
Thesis (M.S. in Management)--Naval Postgraduate School, March 2003.Thesis advisor(s): Robert M. McNab, Susan G. Dooley, William D. Hatch II. Includes bibliographical references (p. 77-80). Also available online.
36
Hanselmann, Harald Verfasser], Hermann [Akademischer Betreuer] [Ney, and Gerhard [Akademischer Betreuer] Rigoll. "Alignment and localization in fine-grained image recognition / Harald Hanselmann ; Hermann Ney, Gerhard Rigoll." Aachen : Universitätsbibliothek der RWTH Aachen, 2020. http://d-nb.info/1230661611/34.
Full text
37
Neumann, Markus. "Automatic multimodal real-time tracking for image plane alignment in interventional Magnetic Resonance Imaging." Phd thesis, Université de Strasbourg, 2014. http://tel.archives-ouvertes.fr/tel-01038023.
Full textAbstract:
Interventional magnetic resonance imaging (MRI) aims at performing minimally invasive percutaneous interventions, such as tumor ablations and biopsies, under MRI guidance. During such interventions, the acquired MR image planes are typically aligned to the surgical instrument (needle) axis and to surrounding anatomical structures of interest in order to efficiently monitor the advancement in real-time of the instrument inside the patient's body. Object tracking inside the MRI is expected to facilitate and accelerate MR-guided interventions by allowing to automatically align the image planes to the surgical instrument. In this PhD thesis, an image-based workflow is proposed and refined for automatic image plane alignment. An automatic tracking workflow was developed, performing detection and tracking of a passive marker directly in clinical real-time images. This tracking workflow is designed for fully automated image plane alignment, with minimization of tracking-dedicated time. Its main drawback is its inherent dependence on the slow clinical MRI update rate. First, the addition of motion estimation and prediction with a Kalman filter was investigated and improved the workflow tracking performance. Second, a complementary optical sensor was used for multi-sensor tracking in order to decouple the tracking update rate from the MR image acquisition rate. Performance of the workflow was evaluated with both computer simulations and experiments using an MR compatible testbed. Results show a high robustness of the multi-sensor tracking approach for dynamic image plane alignment, due to the combination of the individual strengths of each sensor.
38
Vimond, Myriam. "Inférence statistique par des transformées de Fourier pour des modèles de régression semi-paramétriques." Phd thesis, Université Paul Sabatier - Toulouse III, 2007. http://tel.archives-ouvertes.fr/tel-00185102.
Full textAbstract:
Dans cette thèse, nous étudions des modèles semi-paramétriques dits de forme invariante. Ces modèles consistent en l'observation d'un nombre fixés de fonctions de régression identiques à un opérateur de déformation paramétriques près. Ce type de modèles trouve des applications dans les problèmes d'alignement de signaux continus (images 2D, rythmes biologiques, ...) ou discrets (electroencéphalogramme, ...). Pour différents groupes de déformations, nous proposons des M-estimateurs pour les paramètres caractérisant les opérateurs associés aux fonctions de régression. Ces estimateurs minimisent ou maximisent des fonctions de contraste, construites à partir de la moyenne synchronisée des transformées de Fourier des données. De plus, pour l'un des modèles étudiés, nous prouvons l'efficacité semi-paramétrique de cet estimateur ainsi défini, et nous proposons un test d'adéquation du modèle de forme invariante construit à partir d'une des fonctions de contraste.
39
Schreiber, Michael Stuart. "ADVANCES IN THE OPTO-MECHANICAL DESIGN AND ALIGNMENT OF THE HEHSI IMAGING SPECTROMETER BASED ON A SAGNAC INTERFEROMETER." Master's thesis, University of Central Florida, 2005. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/2463.
Full textAbstract:
The High Efficiency HyperSpectral Imager (HEHSI) is a Fourier Transform hyperspectral imager based on a Sagnac interferometer. This thesis research concentrates on the design upgrade and calibration of HEHSI from a proof of concept instrument to a prototype field instrument. Stability is enhanced by removing degrees of freedom and alignment is enhanced by providing for in-situ adjustments. The use of off the shelf components allows for reduced development time and cost constraints. HEHSI is capable of multiple configurations to accommodate sensors and optics with specialized capabilities for multiple wavelength ranges and viewing conditions. With a spectral response of 400 to 1000 nanometers in the visible and very near IR as well as 900 to 1700nm in the Near IR. Creation and use of a real time feedback alignment utility allow quantifiable signal comparison and image alignment. Advances allow for HEHSI to remain aligned during data collection sessions and confirmation of alignment through quantitative measures.M.S.M.E.
Department of Mechanical, Materials and Aerospace Engineering;
Engineering and Computer Science
Mechanical Engineering
40
Veltroni, Wellington Cristiano. "Alinhamento texto-imagem em sites de notícias." Universidade Federal de São Carlos, 2018. https://repositorio.ufscar.br/handle/ufscar/10130.
Full textAbstract:
Submitted by Wellington Veltroni (wellingtonveltroni@gmail.com) on 2018-04-10T20:01:58Z
No. of bitstreams: 4
Disserta__o___Wellington_C__Veltroni-versao_final.pdf: 15387621 bytes, checksum: 73df0490e376ced1e7ca7ae3eb77db60 (MD5)
FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5)
rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5)
tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5)Rejected by Eunice Nunes (eunicenunes6@gmail.com), reason: Bom dia Wellington, Informamos que faltou enviar a Carta comprovante assinada pelo orientador. Solicite o modelo em sua Secretaria de Pós-graduação, preencha e colete a assinatura com o orientador e acesse novamente o sistema para fazer o Upload. Fico no aguardo para finalizarmos o processo. Abraços Ronildo on 2018-04-17T14:16:27Z (GMT)
Submitted by Wellington Veltroni (wellingtonveltroni@gmail.com) on 2018-04-18T12:15:38Z No. of bitstreams: 5 Disserta__o___Wellington_C__Veltroni-versao_final.pdf: 15387621 bytes, checksum: 73df0490e376ced1e7ca7ae3eb77db60 (MD5) FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5) rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5) tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5) Carta_orientadora.pdf: 386667 bytes, checksum: 7343ef875a0334174a4a5abe3fd73b3e (MD5)
Approved for entry into archive by Eunice Nunes (eunicenunes6@gmail.com) on 2018-04-26T12:03:07Z (GMT) No. of bitstreams: 5 Disserta__o___Wellington_C__Veltroni-versao_final.pdf: 15387621 bytes, checksum: 73df0490e376ced1e7ca7ae3eb77db60 (MD5) FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5) rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5) tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5) Carta_orientadora.pdf: 386667 bytes, checksum: 7343ef875a0334174a4a5abe3fd73b3e (MD5)
Rejected by Eunice Nunes (eunicenunes6@gmail.com), reason: Bom dia Wellington, Verificamos que a folha de aprovação não está inserida em sua dissertação Tentei colocá-la aqui mas desconfigura todo o trabalho Poderia por favor enviar um novo arquivo com a folha de aprovação já inserida em sua dissertação Aguardo o retorno para finalizarmos o processo Qualquer dúvida estou à disposição Abraços Eunice on 2018-05-17T13:43:35Z (GMT)
Submitted by Wellington Veltroni (wellingtonveltroni@gmail.com) on 2018-05-28T14:50:36Z No. of bitstreams: 5 FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5) rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5) tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5) Carta_orientadora.pdf: 386667 bytes, checksum: 7343ef875a0334174a4a5abe3fd73b3e (MD5) Disserta__o___Wellington_C__Veltroni_c_folha_aprovacao.pdf: 15849017 bytes, checksum: 2884d766f705fbe38907a8f56724796e (MD5)
Approved for entry into archive by Ronildo Prado (ri.bco@ufscar.br) on 2018-06-06T13:12:16Z (GMT) No. of bitstreams: 5 FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5) rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5) tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5) Carta_orientadora.pdf: 386667 bytes, checksum: 7343ef875a0334174a4a5abe3fd73b3e (MD5) Disserta__o___Wellington_C__Veltroni_c_folha_aprovacao.pdf: 15849017 bytes, checksum: 2884d766f705fbe38907a8f56724796e (MD5)
Approved for entry into archive by Ronildo Prado (ri.bco@ufscar.br) on 2018-06-06T13:12:26Z (GMT) No. of bitstreams: 5 FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5) rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5) tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5) Carta_orientadora.pdf: 386667 bytes, checksum: 7343ef875a0334174a4a5abe3fd73b3e (MD5) Disserta__o___Wellington_C__Veltroni_c_folha_aprovacao.pdf: 15849017 bytes, checksum: 2884d766f705fbe38907a8f56724796e (MD5)
Made available in DSpace on 2018-06-06T13:16:03Z (GMT). No. of bitstreams: 5 FA_vELTRONI.jpg: 460462 bytes, checksum: 790b1993aa2dca9f252dac391edb16d3 (MD5) rd_vELTRONI.jpg: 817039 bytes, checksum: 9dca57906ec66fb968b138749edaf787 (MD5) tc_vELTRONI.jpg: 581847 bytes, checksum: bcc9d308881a36fbccfb47fe2349b222 (MD5) Carta_orientadora.pdf: 386667 bytes, checksum: 7343ef875a0334174a4a5abe3fd73b3e (MD5) Disserta__o___Wellington_C__Veltroni_c_folha_aprovacao.pdf: 15849017 bytes, checksum: 2884d766f705fbe38907a8f56724796e (MD5) Previous issue date: 2018-03-02
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Text-image alignment is the task of aligning elements in a text with elements in the image accompanying it. In this work the text-image alignment was applied in news sites. A lot of news do not make clear the correspondence between elements of a text and elements within the associated image. In this scenario, text-image alignment arises with the intention of guiding the reader, bringing clarity to the news and associated image since it explicitly explains the direct correspondence between regions of the image and words (or named entities) in the text. The goal of this work is to combine Natural Language Processing (NLP) and Computer Vision (CV) techniques to generate a text-image alignment for news: the LinkPICS aligner. LinkPICS uses the YOLO convolutional network (CNN) to detect people and objects in the image associated with the news text. Due to the limitation of the number of objects detected by YOLO (only 80 classes), we decided to use three other CNNs to generate new labels for detected objects. In this work, the text-image alignment was divided into two distinct processes: (1) people alignment and (2) objects alignment. In people alignment, the named entities identified in the text are aligned with images of people. In the evaluation performed with the Folha de São Paulo International news corpus, in English, LinkPICS obtained an accuracy of 98% precision. For the objects alignment, the physical words are aligned with objects (or animals, fruits, etc.) present in the image associated with the news. In the evaluation performed with the news corpus of BBC NEWS, also in English, LinkPICS achieved 72% precision. The main contributions of this work are the LinkPICS aligner and the proposed strategy for its implementation, which represent innovations for the NLP and CV areas. In addition to these, another contribution of this work is the possibility of generating a visual dictionary (words associated with images) containing people and objects aligned, which can be used in other researches and applications such as helping to learn a second language.
O alinhamento texto-imagem é a tarefa de alinhar elementos presentes em um texto com elementos presentes na imagem que o acompanha. Neste trabalho, o alinhamento texto-imagem foi aplicado em sites de notícias. Muitas notícias não deixam clara para o leitor a correspondência entre elementos do texto e elementos contidos na imagem associada. Nesse cenário, o alinhamento texto-imagem surge com a intenção de orientar o leitor, trazendo clareza para a notícia e a imagem associada uma vez que explicita a correspondência direta entre regiões da imagem e palavras (ou entidades) no texto. O objetivo deste trabalho é combinar técnicas de Processamento de Linguagem Natural (PLN) e Visão Computacional (VC) para gerar um alinhador texto-imagem para notícias: o alinhador LinkPICS. O LinkPICS utiliza a rede convolucional (CNN) YOLO para detectar pessoas e objetos na imagem associada ao texto da notícia. Devido à limitação do número de objetos detectados pela YOLO (80 classes de objetos), optou-se também pela utilização de outras três CNNs para a geração de novos rótulos para objetos. Neste trabalho, o alinhamento texto-imagem foi dividido em dois processos distintos: (1) o alinhamento de pessoas e (2) o alinhamento de objetos. No alinhamento de pessoas, as entidades nomeadas são alinhadas com imagens de pessoas e na avaliação realizada no córpus de notícias da Folha de São Paulo Internacional, em inglês, obteve-se uma precisão de 98%. No alinhamento de objetos, as palavras físicas são alinhadas com objetos (ou animais, frutas, etc.) contidos na imagem associada à notícia e na avaliação realizada no córpus de notícias da BBC NEWS, também em inglês, obteve-se uma precisão de 72%. As principais contribuições deste trabalho são o alinhador LinkPICS e a estratégia proposta para sua implementação, que representam inovações para as áreas de PLN e VC. Além destas, outra contribuição deste trabalho é a possibilidade de geração de um dicionário visual (palavras associadas a imagens) contendo pessoas e objetos alinhados, que poderá ser utilizado em outras pesquisas e aplicações como, por exemplo, no auxílio ao aprendizado de outro idioma.
CNPQ: 133679/2015-2
41
Wang, Yizhi. "Automated Analysis of Astrocyte Activities from Large-scale Time-lapse Microscopic Imaging Data." Diss., Virginia Tech, 2019. http://hdl.handle.net/10919/95988.
Full textAbstract:
The advent of multi-photon microscopes and highly sensitive protein sensors enables the recording of astrocyte activities on a large population of cells over a long-time period in vivo. Existing tools cannot fully characterize these activities, both within single cells and at the population-level, because of the insufficiency of current region-of-interest-based approaches to describe the activity that is often spatially unfixed, size-varying, and propagative. Here, we present Astrocyte Quantitative Analysis (AQuA), an analytical framework that releases astrocyte biologists from the ROI-based paradigm. The framework takes an event-based perspective to model and accurately quantify the complex activity in astrocyte imaging datasets, with an event defined jointly by its spatial occupancy and temporal dynamics. To model the signal propagation in astrocyte, we developed graphical time warping (GTW) to align curves with graph-structured constraints and integrated it into AQuA. To make AQuA easy to use, we designed a comprehensive software package. The software implements the detection pipeline in an intuitive step by step GUI with visual feedback. The software also supports proof-reading and the incorporation of morphology information. With synthetic data, we showed AQuA performed much better in accuracy compared with existing methods developed for astrocytic data and neuronal data. We applied AQuA to a range of ex vivo and in vivo imaging datasets. Since AQuA is data-driven and based on machine learning principles, it can be applied across model organisms, fluorescent indicators, experimental modes, and imaging resolutions and speeds, enabling researchers to elucidate fundamental astrocyte physiology.Doctor of Philosophy
Astrocyte is an important type of glial cell in the brain. Unlike neurons, astrocyte cannot be electrically excited. However, the concentrations of many different molecules inside and near astrocytes change over space and time and show complex patterns. Recording, analyzing, and deciphering these activity patterns enables the understanding of various roles astrocyte may play in the nervous system. Many of these important roles, such as sensory-motor integration and brain state modulation, were traditionally considered the territory of neurons, but recently found to be related to astrocytes. These activities can be monitored in the intracellular and extracellular spaces in either brain slices and living animals, thanks to the advancement of microscopes and genetically encoded fluorescent sensors. However, sophisticated analytical tools lag far behind the impressive capability of generating the data. The major reason is that existing tools are all based on the region-of-interest-based (ROI) approach. This approach assumes the field of view can be segmented to many regions, and all pixels in the region should be active together. In neuronal activity analysis, all pixels in an ROI (region of interest) correspond to a neuron and are assumed to share a common activity pattern (curve). This is not true for astrocyte activity data because astrocyte activities are spatially unfixed, size-varying, and propagative. In this dissertation, we developed a framework called AQuA to detect the activities directly. We designed an accurate and flexible detection pipeline that works with different types of astrocyte activity data sets. We designed a machine learning model to characterize the signal propagation for the pipeline. We also implemented a compressive and user-friendly software package. The advantage of AQuA is confirmed in both simulation studies and three different types of real data sets.
42
Chen, Carl Gang 1972. "Beam alignment and image metrology for scanning beam interference lithography : fabricating gratings with nanometer phase accuracy." Thesis, Massachusetts Institute of Technology, 2003. http://hdl.handle.net/1721.1/16950.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2003.Includes bibliographical references (p. 279-285).
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
We are developing a scanning beam interference lithography (SBIL) system. SBIL is capable of producing large-area linear diffraction gratings that are phase-accurate to the nanometer level. Such gratings may enable new paradigms in fields such as semiconductor pattern placement metrology and grating-based displacement measuring interferometry. With our prototype tool nicknamed "Nanoruler", I have successfully patterned, for the first time, a 400 nm period grating over a 300 mm-diam. wafer, the largest that the tool can currently accommodate. By interfering two small diameter Gaussian laser beams to produce a low-distortion grating image, SBIL produces large gratings by step-and-scanning the photoresist-covered substrate underneath the image. To implement SBIL, two main questions need to be answered: First, how does one lock the interference image to a fast-moving substrate with nanometer accuracy? Secondly, how does one produce an interference image with minimum phase nonlinearities while setting and holding its period to the part-per-million (ppm) level? My thesis work solves the latter problem, which can be further categorized into two parts: period control and wavefront metrology. Period control concerns SBIL's ability to set, stabilize and measure the image grating period. Our goal is to achieve control at the ppm level in order to reduce any related phase nonlinearity in the exposed grating to subnanometers. A grating beamsplitter is used to stabilize the period. I demonstrate experimental results where the period stabilization is at the 1 ppm level. An automated beam alignment system is built. The system can overlap the beam centroids to around 10 [mu]m and equalize the mean beam angles to better than 2 [mu]rad (0.4 arcsec), which translates into a period adjustability of 4 ppm at 400 nm.
(cont.) Image period is measured in-situ via an interferometric technique. The measurement repeatability is demonstrated at 2.8 ppm, three-sigma. Modeling shows that such small period measurement error does not accumulate as growing phase nonlinearities in the patterned resist grating; rather, the resist grating has an averaged period that equals the measured period. Any phase nonlinearity is periodic and subnanometer in magnitude. SBIL wavefront metrology refers to the process of mapping the phase of the grating image and adjusting the collimating optics so that minimum image phase nonlinearity can be achieved. The current SBIL wavefront metrology system employs phase shifting interferometry and determines the image nonlinearity through a moire technique. The system has an established measurement repeatability of 3.2 nm, three-sigma. I am able to minimize the nonlinearity to 12 nm across a 2 mm-diam. image. Modeling shows that despite an image phase nonlinearity at the dozen nanometer level, printed phase error in the resist can be reduced to subnanometers by overlapping scans appropriately. From the point of view of period control and wavefront metrology, I conclude that SBIL is capable of producing gratings with subnanometer phase nonlinearities.
by Carl Gang Chen.
Ph.D.
43
Rahtu, E. (Esa). "A multiscale framework for affine invariant pattern recognition and registration." Doctoral thesis, University of Oulu, 2007. http://urn.fi/urn:isbn:9789514286018.
Full textAbstract:
Abstract
This thesis presents a multiscale framework for the construction of affine invariant pattern recognition and registration methods. The idea in the introduced approach is to extend the given pattern to a set of affine covariant versions, each carrying slightly different information, and then to apply known affine invariants to each of them separately. The key part of the framework is the construction of the affine covariant set, and this is done by combining several scaled representations of the original pattern. The advantages compared to previous approaches include the possibility of many variations and the inclusion of spatial information on the patterns in the features.
The application of the multiscale framework is demonstrated by constructing several new affine invariant methods using different preprocessing techniques, combination schemes, and final recognition and registration approaches. The techniques introduced are briefly described from the perspective of the multiscale framework, and further treatment and properties are presented in the corresponding original publications. The theoretical discussion is supported by several experiments where the new methods are compared to existing approaches.
In this thesis the patterns are assumed to be gray scale images, since this is the main application where affine relations arise. Nevertheless, multiscale methods can also be applied to other kinds of patterns where an affine relation is present.
An additional application of one multiscale based technique in convexity measurements is introduced. The method, called multiscale autoconvolution, can be used to build a convexity measure which is a descriptor of object shape. The proposed measure has two special features compared to existing approaches. It can be applied directly to gray scale images approximating binary objects, and it can be easily modified to produce a number of measures. The new measure is shown to be straightforward to evaluate for a given shape, and it performs well in the applications, as demonstrated by the experiments in the original paper.
44
Moore, Thomas Brendan. "Learning Geometry-Free Face Re-lighting." Master's thesis, University of Central Florida, 2007. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/3353.
Full textAbstract:
The accurate modeling of the variability of illumination in a class of images is a fundamental problem that occurs in many areas of computer vision and graphics. For instance, in computer vision there is the problem of facial recognition. Simply, one would hope to be able to identify a known face under any illumination. On the other hand, in graphics one could imagine a system that, given an image, the illumination model could be identified and then used to create new images. In this thesis we describe a method for learning the illumination model for a class of images. Once the model is learnt it is then used to render new images of the same class under the new illumination. Results are shown for both synthetic and real images. The key contribution of this work is that images of known objects can be re-illuminated using small patches of image data and relatively simple kernel regression models. Additionally, our approach does not require any knowledge of the geometry of the class of objects under consideration making it relatively straightforward to implement. As part of this work we will examine existing geometric and image-based re-lighting techniques; give a detailed description of our geometry-free face re-lighting process; present non-linear regression and basis selection with respect to image synthesis; discuss system limitations; and look at possible extensions and future work.M.S.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Computer Science MS
45
Zavan, Flávio Henrique de Bittencourt. "Nose pose estimation in the wild and its applications on nose tracking and 3d face alignment." reponame:Repositório Institucional da UFPR, 2016. http://hdl.handle.net/1884/44969.
Full textAbstract:
Orientador : Prof. Dr. Olga R.P. BellonDissertação (mestrado) - Universidade Federal do Paraná, Setor de Ciências Exatas, Programa de Pós-Graduação em Informática. Defesa: Curitiba, 31/08/2016
Inclui referências : f. 53-57
Resumo: Neste trabalho, estimamos a pose da cabe¸ca em imagens 2D, tanto em ambientes controlados como n˜ao controlados, baseado apenas na regi˜ao do nariz. Para este fim, propomos e comparamos uma metodologia livre de landmarks, baseado em Support Vector Machi- nes (SVM-NosePose). O uso de apenas a regi˜ao do nariz apresenta vantagens sobre o uso da face inteira; n˜ao apenas 'e menos prov'avel a oclus˜ao do nariz, mas ele tamb'em 'e vis'?vel e provado ser altamente discriminante em todas as poses de perfil a frontal. O SVM j'a foi utilizado para este tipo de tarefa em uma base pequena e controlada. Nosso SVM-NosePose adiciona novas id'eias e experimentos 'a etapa da gera¸c˜ao do vetor de caracter '?sticas, tanto na extra¸c˜ao destas, como na agrega¸c˜ao dos dados. 'E comparado favoravelmente ao estado-da-arte, atrav'es de experimentos abrangentes cuidadosamente elaborados, utilizando seis bases de dados publicamente dispon'?veis, Pointing'04, Multi-PIE, McGillFaces, SFEW, AFW e PaSC, abrangendo diversos cen'arios poss'?veis na estimativa da pose da cabe¸ca. A fim de realizar uma avali¸c˜ao completa e detalhada, apresentamos resultados tanto com as regi˜oes anotadas do nariz quanto com a sa'?da de um detector de narizes estado-da-arte. Adicionalmente, investigamos duas diferentes aplica¸c˜oes para nossa estimativa: a inclus˜ao original de uma pontua¸c˜ao da pose da cabe¸ca na estimativa da qualidade da face para a inicializa¸c˜ao de um rastreador de narizes, alcan¸cando maior precis˜ao de rastreamento; e a execu¸c˜ao de alinhamento 3D livre de landmarks em ambientes n˜ao controlados utilizando apenas a informa¸c˜ao da regi˜ao do nariz, permitindo que estimativas sejam geradas mesmo em cen'arios desafiadores. Palavras-chave: pose da cabe¸ca; rastreamento facial; alinhamento facial
Abstract: We perform head pose estimation solely based on the nose region as input, extracted from 2D images in both constrained and unconstrained environments. To this end, we propose a landmark free methodology, based on Support Vector Machines (SVM-NosePose) and compare it against the state-of-the-art. Using the nose region has advantages over using the whole face; not only it is less likely to be occluded, it is also visible and proved to be highly discriminant in all poses from profile to frontal. SVM has been previously used for this task on a small, controlled dataset. Our SVM-NosePose adds new ideas and experiments on the feature vector generation stage, both in feature extraction and data aggregation. Our SVM-NosePose estimation favorably compares, through thoughtful and comprehensive experiments, against state-of-the-art approaches, using six publicly available datasets, Pointing'04, Multi-PIE, McGillFaces, SFEW, AFW and PaSC. To achieve a complete and detailed evaluation, we present results using both the nose region ground-truth and the output of a state-of-the-art nose detector. Additionally, two different applications for our approach are also investigated: the original inclusion of a head pose score for face quality estimation, for initializing a nose tracker, leading to higher tracking precision; and performing landmark-free 3D face alignment in the wild using only the information of the nose region, enabling coherent estimates to be generated even in challenging scenarios. Keywords: head pose; face tracking; face alignment
46
Ojansivu, V. (Ville). "Blur invariant pattern recognition and registration in the Fourier domain." Doctoral thesis, University of Oulu, 2009. http://urn.fi/urn:isbn:9789514292552.
Full textAbstract:
Abstract
Pattern recognition and registration are integral elements of computer vision, which considers image patterns. This thesis presents novel blur, and combined blur and geometric invariant features for pattern recognition and registration related to images. These global or local features are based on the Fourier transform phase, and are invariant or insensitive to image blurring with a centrally symmetric point spread function which can result, for example, from linear motion or out of focus.
The global features are based on the even powers of the phase-only discrete Fourier spectrum or bispectrum of an image and are invariant to centrally symmetric blur. These global features are used for object recognition and image registration. The features are extended for geometrical invariances up to similarity transformation: shift invariance is obtained using bispectrum, and rotation-scale invariance using log-polar mapping of bispectrum slices. Affine invariance can be achieved as well using rotated sets of the log-log mapped bispectrum slices. The novel invariants are shown to be more robust to additive noise than the earlier blur, and combined blur and geometric invariants based on image moments.
The local features are computed using the short term Fourier transform in local windows around the points of interest. Only the lowest horizontal, vertical, and diagonal frequency coefficients are used, the phase of which is insensitive to centrally symmetric blur. The phases of these four frequency coefficients are quantized and used to form a descriptor code for the local region. When these local descriptors are used for texture classification, they are computed for every pixel, and added up to a histogram which describes the local pattern. There are no earlier textures features which have been claimed to be invariant to blur. The proposed descriptors were superior in the classification of blurred textures compared to a few non-blur invariant state of the art texture classification methods.
47
LEE, Wen-Chia, and 李文加. "Subpixel BGA Images Alignment Based on Moment Methods." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/10127890008406942535.
Full textAbstract:
碩士國立成功大學
電腦與通信工程研究所
93
BGA (Ball Grid Array), a technology of packaging, is widely used in the integrated circuits. The model name and function of each IC chip through laser marking are to be identified by recognizing the etched mark on package surface. For instance, chip group, CPU, Flash, some communication IC etc. In order to achieve accurate alignment for the location of the etched mark, the central position and orientation angle of an IC package are examined through the image inspection system. This thesis proposed a subpixel alignment method for BGA images. In the method, firstly, region projection is applied to recognize the contour of the object within the inspected area and delimit the regions of interest. Then the edge elements of the object can be found by using DOB (Difference of Boxes). Moreover, the edge elements resulting from cracks or flaws on object’s boundaries are filtered out by edge following method. Next, the edge elements are modified by ZOM (Zernike Orthogonal Moment) to achieve subpixel accuracy. Finally, the central position and orientation angle are obtained by the LSE line fitting algorithm followed by geometric computation. Our proposed method is evaluated in terms of the stability and accuracy under noise degradation for synthetic images. The experimental results show that the error of the central position and the orientation is within ±0.1 pixel and within ±0.01 degree respectively without noise; the error standard deviation of the central position and the orientation are all less than 1.6% under various levels of Gaussian noise corruption. On running performance, it takes approximate 109 ms to complete the entire process for an inspected area of 360×300 pixels while running on a PC equipped with a processor of Pentium 4 3.0GHz.
48
Haung, Zhong-Yi, and 黃鐘儀. "Alignment and Texture Color Calibration of 3D Images." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/57790526156007170584.
Full textAbstract:
碩士國立交通大學
應用數學系數學建模與科學計算碩士班
104
In computer vision, presenting a complete model and high quality texture is an important issue. In this thesis, we focus on 3D image registration and color calibration of the texture. In the image registration part, we use Iterative Closest Point, the most classical and efficient rigid registration algorithm, to combine data coming from different sensors into a complete model. We also apply this algorithm to solve the data size mismatch problem caused by specification differences between the sensors. In the texture color calibration part, we calibrate colors based on the overlapping region between two images to reduce the difference of their colors. This step reduces sudden change of color at the boundary between images and makes the model more realistic and perfect.
49
Huang, BO-XI, and 黃博熙. "Improve Alignment of RGB and Depth Images for KINECT V2." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/xmzj9h.
Full textAbstract:
碩士逢甲大學
資訊工程學系
106
Due to the vigorous development of computer vision, the use of 3D reconstruction has become more and more extensive in recent years, such as industrial design, archaeological research, entertainment industry, etc. Therefore, it is urgent to get more accurate reconstruction information. Instruments that used to perform 3D reconstruction have been quite expensive. However, in recent years, the introduction of Microsoft KINECT V2 not only has a cheaper price, but also provides depth and color information. Because the KINECT V2 color and depth camera are not in the same horizontal position, the images captured by the two cameras cannot be directly aligned, so the depth image coordinates can be converted to be aligned with the color image. The main purpose of this thesis is to use KINECT V2 to align the color and depth images by coordinate transformation method, and compare it with the alignment method using affine transformation. Furthermore, since the images captured by the KINECT V2 color camera and the depth camera may be distorted before alignment, the camera needs to be calibrated to facilitate higher accuracy after alignment. This thesis is divided into three parts. The first part is camera calibration, which is divided into internal correction, external correction and distortion correction. Mainly with reference to the methods of D. C. Herrera [1] and Zhengyou Zhang [2] to improve. The second part is to use the coordinate conversion method to align the color and depth image; The third part is the comparison of our proposed coordinate transformation method and the affine transformation method based on the root mean square error of the aligned images.
50
Morais, Fábio André da Rocha. "3D reconstruction in underwater environment using CAD model alignment with images." Dissertação, 2021. https://hdl.handle.net/10216/135373.
Full textAbstract:
Subsea assets need to be regularly inspected, maintained and repaired. These operations are typically performed using a Remotely Operated Vehicle (ROV) controlled by a pilot that sits in a ship. In order to make operations safer and cheaper, it would be interesting to control the ROVs from land, avoiding the need to hire a ship and crew.
As part of these operations, ROVs need to perform high precision actions such as turning valves, which may be hard to perform in this remote setting due to latency. A semi-autonomous vehicle capable of performing high precision tasks could potentiate the transition to fully remote operations, where people stay on land. In order to develop such a system, we need a robust perception model capable of segmenting the assets of interest.
Additionally, it is important to fuse that information with 3D models of those same assets in order to have a spatial perception of the environment. This fusion may be useful to, in the future, plan the necessary actions to interact with the given asset.
The main goal of this work is to implement a model that: 1) segments different subsea assets of interest, such as valves; and 2) fuse the segmentation information with 3D models of those same assets.