Orientador: João Antonio Pereira / Resumo: Visão de máquina é um campo multidisciplinar que vem crescendo na indústria, que está cada vez mais preocupada em reduzir custos, automatizar processos, e atender requisitos de qualidade do produto para atender seus clientes. Processos de montagem realizados de forma manual com inspeção e controle visual são tipicamente processos susceptíveis a erros, à utilização de peças não conformes na montagem do produto final. Este trabalho apresenta uma proposta de desenvolvimento de um sistema de visão de máquina com base no processamento e análise de imagens digitais para a inspeção das características e especificações das peças e componentes utilizados na montagem de capotas marítimas, objetivando verificar e garantir a conformidade do produto final. A inspeção e avaliação da conformidade do produto são feitas por etapas com a utilização de duas câmeras, uma captura a imagem do código de identificação alfanumérico do produto e a outra inspeciona o conjunto de elementos de fixação. As imagens passam por um processo de tratamento que envolve a filtragem espacial utilizando máscara de médias para suavização, alargamento de contraste para expandir a faixa de intensidades e segmentação para formação dos objetos de interesse. Uma função de OCR é utilizada para a extração de caracteres e reconhecimento do código do produto e a extração de características específicas do conjunto de componentes de fixação é feita por descritores de forma representados pelos invariantes de momento. As caracte... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Machine vision is a growing multidisciplinary field in the industry that is increasingly concerned with reducing costs, automating processes, and meeting product quality requirements to serve its customers. Manual assembly processes with inspection and visual control are typically error-prone processes using non-conforming parts in the final product assembly. This work presents a proposal for the development of a machine vision system based on digital image processing and analysis for the inspection of the characteristics and specifications of the parts and components used in the assembly of marine bonnets, aiming to verify and ensure the conformity of the final product. Inspection and conformity assessment of the product are done in stages using two cameras, one capturing the image of the alphanumeric identification code of the product and the other inspecting the set of fasteners. The images undergo a treatment process that involves spatial filtering using averaging masks for smoothing, contrast widening to expand the range of intensities, and segmentation to form the objects of interest. An OCR function is used for character extraction and product code recognition, and the extraction of specific features of the fastener assembly is done by shape descriptors represented by the moment invariants. The specific characteristics of the fasteners are used to assess the conformity of the product with its respective code. The presentation of data and results of the implemented prop... (Complete abstract click electronic access below) / Mestre

This document deals with experimental verifying to use machine learning algorithms AdaBoost or WaldBoost to make classifier, that is able to find point in the second picture that matches original point in the first picture. This work also depicts finding points of interest in image as a first step of finding correspondence. Next there are described some descriptors of points of interest. Corresponding points could be useful for 3D modeling of shooted scene.

Recognition of complex events in consumer uploaded Internet videos, captured under realworld settings, has emerged as a challenging area of research across both computer vision and multimedia community. In this dissertation, we present a systematic decomposition of complex events into hierarchical components and make an in-depth analysis of how existing research are being used to cater to various levels of this hierarchy and identify three key stages where we make novel contributions, keeping complex events in focus. These are listed as follows: (a) Extraction of novel semi-global features – firstly, we introduce a Lie-algebra based representation of dominant camera motion present while capturing videos and show how this can be used as a complementary feature for video analysis. Secondly, we propose compact clip level descriptors of a video based on covariance of appearance and motion features which we further use in a sparse coding framework to recognize realistic actions and gestures. (b) Construction of intermediate representations – We propose an efficient probabilistic representation from low-level features computed from videos, based on Maximum Likelihood Estimates which demonstrates state of the art performance in large scale visual concept detection, and finally, (c) Modeling temporal interactions between intermediate concepts – Using block Hankel matrices and harmonic analysis of slowly evolving Linear Dynamical Systems, we propose two new discriminative feature spaces for complex event recognition and demonstrate significantly improved recognition rates over previously proposed approaches.

The National Wetlands Inventory (NWI) is the definitive source for wetland resources in the United States. The NWI production unit in Hadley, MA has begun to upgrade their digital map database, integrating descriptors for assessment of wetland functions. Updating is conducted manually and some automation is needed to increase production and efficiency. This study assigned landscape position descriptor codes to NWI wetland polygons and correlated polygon environmental properties with public domain terrain, soils, hydrology, and vegetation data within the Coastal Plain of Virginia. Environmental properties were applied to a non-metric multidimensional scaling technique to identify similarities within individual landscape positions based on wetland plant indicators, primary and secondary hydrology indicators, and field indicators of hydric soils. Individual NWI landscape position classes were linked to field-validated environmental properties. Measures provided by this analysis indicated that wetland plant occurrence and wetland plant status obtained a stress value of 0.136 (Kruskal's stress measure = poor), which is a poor indicator when determining correlation among wetland environmental properties. This is due principally to the highly-variable plant distribution and wetland plant status found among the field-validated sites. Primary and secondary hydrology indicators obtained a stress rating of 0.097 (Kruskal's stress measure = good) for correlation. The hydrology indicators measured in this analysis had a high level of correlation with all NWI landscape position classes due the common occurrence of at least one primary hydrology indicator in all field validated wetlands. The secondary indicators had an increased accuracy in landscape position discrimination over the primary indicators because they were less ubiquitous. Hydric soil characteristics listed in the 1987 Manual and NTCHS field indicators of hydric soils proved to be a relatively poor indicator, based on Kruskal's stress measure of 0.117, for contrasting landscape position classes because the same values occurred across all classes. The six NWI field–validated landscape position classes used in this study were then further applied in a public domain digital data analysis. Mean pixel attribute values extracted from the 180 field-validated wetlands were analyzed using cluster analysis. The percent hydric soil component displayed the greatest variance when compared to elevation and slope curvature, streamflow and waterbody, Cowardin classification, and wetland vegetation type. Limitations of the soil survey data included: variable date of acquisition, small scale compared to wetland size, and variable quality. Flow had limitations related to its linear attributes, therefore is often found insignificant when evaluating pixel values that are mean of selected pixels across of wetland landscape position polygons. NLCD data limitations included poor quality resolution (large pixel size) and variable classification of cover types. The three sources of information that would improve wetland mapping and modeling the subtle changes in elevation and slope curvature that characterize wetland landscapes are: recent high resolution leaf-off aerial photography, high-quality soil survey data, and high-resolution elevation data. Due to the data limitations and the choice of variables used in this study, development of models and rules that clearly separate the six different landscape positions was not possible, and thus automation of coding could not be attempted. / Master of Science

This research was executed as three separate studies. Study 1 focused on the perception of pain and the semantic aspects of pain. Study 2 focused on the measurement of acute pain and mood states. Study 3 focused on the psychological treatment of cancer pain. In Study 1 a group of 66 Setswana-speaking adults were required to describe what they saw, what happened, and what would be the outcome with respect to three visually presented pain scenes using The Pain Apperception Test (PAT) A qualitative analysis of their responses shows that pain is experienced as an all encompassing experience affecting all aspects of their lives, such as the physical, emotional, social, and economic. This was found to be true, irrespective of gender and age with the exception of economic issues. A qualitative analysis of their responses to the Pain Eliciting Incidents Questionnaire (PEIQ) reveals that the Setswana pain descriptors are classifiable according to the three dimensions of pain namely, the sensory-discriminative, affective-motivational, and cognitive-evaluative. Sludy 2 applied the Profile of Mood States (POMS) preoperatively to a group of 58 female laparotomy (gynaecological) patients. These patients were also tested post-operatively with the Visual Analogue Scale (VAS) and the Wisconsin Brief Pain Questionnaire (WBPQ) as pain measures. The pain measures were taken at no medication and at the peak of medication. Factor analysis could not confirm the validity of the six POMS scales. These scales also did not show correlations with post-operative pain. Correlations between the pain measures showed acceptable reliability and validity of the VAS and the WBPQ. In Study 3 three groups of 15 cancer patients each, suffering from chronic pain, were treated over a period of two weeks with either cognitive behavioural therapy plus medication, reassurance therapy plus medication, or medication only. Comparison of before and after treatment pain measures showed that both cognitive behavioural therapy and reassurance therapy had a beneficial effect. Follow-up results three months later showed that the beneficial effect of reassurance therapy did not persist. Patients treated with cognitive behavioral therapy still showed the beneficial effects thereof. / Psychology / D. Litt. et Phil. (Psychology)

In recent years, the potential benefits of high-throughput virtual screening to the drug discovery community have been recognized, bringing an increase in the number of tools developed for this purpose. These programs have to process large quantities of data, searching for an optimal solution in a vast combinatorial range. This is particularly the case for protein-ligand docking, since proteins are sophisticated structures with complicated interactions for which either molecule might reshape itself. Even the very limited flexibility model to be considered here, using ligand conformation ensembles, requires six dimensions of exploration - three translations and three rotations - per rigid conformation. The functions for evaluating pose suitability can also be complex to calculate. Consequently, the programs being written for these biochemical simulations are extremely resource-intensive. This work introduces a pure computer science approach to the field, developing techniques to improve the effectiveness of such tools. Their architecture is generalized to an abstract pattern of nested layers for discussion, covering scoring functions, search methods, and screening overall. Based on this, new stratagems for molecular docking software design are described, including lazy or partial evaluation, geometric analysis, and parallel processing implementation. In addition, a range of novel algorithms are presented for applications such as active site detection with linear complexity (PIES) and small molecule shape description (PASTRY) for pre-alignment of ligands. The various stratagems are assessed individually and in combination, using several modified versions of an existing docking program, to demonstrate their benefit to virtual screening in practical contexts. In particular, the importance of appropriate precision in calculations is highlighted.

La lecture automatique de plaques d’immatriculation de véhicule est considérée comme une approche de surveillance de masse. Elle permet, grâce à la détection /localisation ainsi que la reconnaissance optique, d’identifier un véhicule dans les images ou les séquences d’images. De nombreuses applications comme le suivi du trafic, la détection de véhicules volés, le télépéage ou la gestion d’entrée / sortie des parkings utilise ce procédé. Or malgré d’important progrès enregistré depuis l’apparition des premiers prototypes en 1979 accompagné d’un taux de reconnaissance parfois impressionnant, notamment grâce aux avancés en recherche scientifique et en technologie des capteurs, les contraintes imposés pour le bon fonctionnement de tels systèmes en limitent les portées. En effet, l’utilisation optimale des techniques de localisation et de reconnaissance de plaque d’immatriculation dans les scénarii opérationnels nécessite des conditions d’éclairage contrôlées ainsi qu’une limitation dans de la pose, de vitesse ou tout simplement de type de plaque. La lecture automatique de plaques d’immatriculation reste alors un problème de recherche ouvert. La contribution majeure de cette thèse est triple. D’abord une nouvelle approche robuste de localisation de plaque d’immatriculation dans des images ou des séquences d’images est proposée. Puis, l’amélioration de la qualité des plaques localisées est traitée par une adaptation de technique de super-résolution. Finalement, un modèle unifié de localisation et de super-résolution est proposé permettant de diminuer la complexité temporelle des deux approches combinées. / Automatic reading of vehicle license plates is considered an approach to mass surveillance. It allows, through the detection / localization and optical recognition to identify a vehicle in the images or video sequences. Many applications such as traffic monitoring, detection of stolen vehicles, the toll or the management of entrance/ exit parking uses this method. Yet in spite of important progress made since the appearance of the first prototype sin 1979, with a recognition rate sometimes impressive thanks to advanced science and sensor technology, the constraints imposed for the operation of such systems limit laid. Indeed, the optimal use of techniques for localizing and recognizing license plates in operational scenarios requiring controlled lighting conditions and a limitation of the pose, velocity, or simply type plate. Automatic reading of vehicle license plates then remains an open research problem. The major contribution of this thesis is threefold. First, a new approach to robust license plate localization in images or image sequences is proposed. Then, improving the quality of the plates is treated with a localized adaptation of super-resolution technique. Finally, a unified model of location and super-resolution is proposed to reduce the time complexity of both approaches combined.

This research was executed as three separate studies. Study 1 focused on the perception of pain and the semantic aspects of pain. Study 2 focused on the measurement of acute pain and mood states. Study 3 focused on the psychological treatment of cancer pain. In Study 1 a group of 66 Setswana-speaking adults were required to describe what they saw, what happened, and what would be the outcome with respect to three visually presented pain scenes using The Pain Apperception Test (PAT) A qualitative analysis of their responses shows that pain is experienced as an all encompassing experience affecting all aspects of their lives, such as the physical, emotional, social, and economic. This was found to be true, irrespective of gender and age with the exception of economic issues. A qualitative analysis of their responses to the Pain Eliciting Incidents Questionnaire (PEIQ) reveals that the Setswana pain descriptors are classifiable according to the three dimensions of pain namely, the sensory-discriminative, affective-motivational, and cognitive-evaluative. Sludy 2 applied the Profile of Mood States (POMS) preoperatively to a group of 58 female laparotomy (gynaecological) patients. These patients were also tested post-operatively with the Visual Analogue Scale (VAS) and the Wisconsin Brief Pain Questionnaire (WBPQ) as pain measures. The pain measures were taken at no medication and at the peak of medication. Factor analysis could not confirm the validity of the six POMS scales. These scales also did not show correlations with post-operative pain. Correlations between the pain measures showed acceptable reliability and validity of the VAS and the WBPQ. In Study 3 three groups of 15 cancer patients each, suffering from chronic pain, were treated over a period of two weeks with either cognitive behavioural therapy plus medication, reassurance therapy plus medication, or medication only. Comparison of before and after treatment pain measures showed that both cognitive behavioural therapy and reassurance therapy had a beneficial effect. Follow-up results three months later showed that the beneficial effect of reassurance therapy did not persist. Patients treated with cognitive behavioral therapy still showed the beneficial effects thereof. / Psychology / D. Litt. et Phil. (Psychology)

L’objectif de ce travail est d’étudier les couplages entre les propriétés hygroélastiques des papierset leur microstructure. L’exploitation d’images de papiers modèles acquises par microtomographieà rayons X a permis de caractériser de manière inédite l’évolution des propriétésmicrostructurales de ces matériaux en fonction de leurs conditions d’élaboration ainsique lors d’essais où ils ont été placés sous atmosphère à humidité relative contrôlée.Ces résultats constituent un apport nouveau pour la connaissance de la nature statistique desdescripteurs des propriétés des fibres (dimensions et orientation) et de leurs contacts (surface,degré de liaison), de l’architecture des réseaux fibreux que forment les papiers (nombrede contacts entre fibre) et pour la taille des volumes élémentaires représentatifs des propriétésmicrostructurales et élastiques de ces milieux. Sur la base de ces informations, différentsmodèles, plus oumoins raffinés, ont été élaborés dans le cadre de la théorie de l’homogénéisationdes structures périodiques discrètes, pour décrire les propriétésmécaniques des papiers.Cette approche apporte un éclairage nouveau sur le rôle des liaisons entre fibres sur leur comportement mécanique. / The objective of this work is to study the coupling between the hygroelastic properties ofpapers and their microstructure. The use of images of models acquired by X-ray microtomographypapers allowed the characterization in an unprecedentedmanner of the evolutionofmicrostructural properties of thesematerials according to their production conditions andduring tests where they were placed in atmosphere at controlled relative humidity. These resultsprovide a new contribution to the knowledge of the statistical nature of the descriptorsof fibre properties (size and orientation) and their contacts (surface, bonding degree ratio), ofthe architecture of fibrous networks that papers constitute (number of fibre-to-fibre bonds)as well as of the size of the representative elementary volumes of microstructural and elasticproperties. Based on this information, various models, more or less sophisticated, were developedin the framework of the theory of homogenisation of discrete periodic structures todescribe the mechanical properties of paper. This approach sheds new light on the role offibre-to-fibre bonds on themechanical behaviour of thesematerials.

La tâche la plus délicate d'un système de reconnaissance faciale est la phase d'extraction de caractéristiques significatives et discriminantes. Dans le cadre de cette thèse, nous nous sommes focalisés sur cette tâche avec comme objectif l'élaboration d'une représentation de visage robuste aux variations majeures suivantes: variations d'éclairage, de pose, de temps, images de qualité différentes (vidéosurveillance). Par ailleurs, nous avons travaillé également dans une optique de traitement temps réel. Tout d'abord, en tenant compte des caractéristiques d'orientation des traits principaux du visages (yeux, bouche), une nouvelle variante nommée ELBP de célèbre descripteur LBP a été proposée. Elle s'appuie sur les informations de micro-texture contenues dans une ellipse horizontale. Ensuite, le descripteur EPOEM est construit afin de tenir compte des informations d'orientation des contours. Puis un descripteur nommée PLPQMC qui intégre des informations obtenues par filtrage monogénique dans le descripteur LPQ est proposé. Enfin le descripteur LPOG intégrant des informations de gradient est présenté. Chacun des descripteurs proposés est testé sur les 3 bases d'images AR, FERET et SCface. Il en résulte que les descripteurs PLPQMC et LPOG sont les plus performants et conduisent à des taux de reconnaissance comparables voire supérieur à ceux des meilleurs méthodes de l'état de l'art. / Centered around feature extraction, the core task of any Face recognition system, our objective is devising a robust facial representation against major challenges, such as variations of illumination, pose and time-lapse and low resolution probe images, to name a few. Besides, fast processing speed is another crucial criterion. Towards these ends, several methods have been proposed through out this thesis. Firstly, based on the orientation characteristics of the facial information and important features, like the eyes and mouth, a novel variant of LBP, referred as ELBP, is designed for encoding micro patterns with the usage of an horizontal ellipse sample. Secondly, ELBP is exploited to extract local features from oriented edge magnitudes images. By this, the Elliptical Patterns of Oriented Edge Magnitudes (EPOEM) description is built. Thirdly, we propose a novel feature extraction method so called Patch based Local Phase Quantization of Monogenic components (PLPQMC). Lastly, a robust facial representation namely Local Patterns of Gradients (LPOG) is developed to capture meaningful features directly from gradient images. Chiefs among these methods are PLPQMC and LPOG as they are per se illumination invariant and blur tolerant. Impressively, our methods, while offering comparable or almost higher results than that of existing systems, have low computational cost and are thus feasible to deploy in real life applications.