<p>Shape-Based matching (SBM) is a known method for 2D object recognition that is rather robust against illumination variations, noise, clutter and partial occlusion.</p><p>The objects to be recognized can be translated, rotated and scaled.</p><p>The translation of an object is determined by evaluating a similarity measure for all possible positions (similar to cross correlation).</p><p>The similarity measure is based on dot products between normalized gradient directions in edges.</p><p>Rotation and scale is determined by evaluating all possible combinations, spanning a huge search space.</p><p>A resolution pyramid is used to form a heuristic for the search that then gains real-time performance.</p><p>For SBM, a model consisting of normalized edge gradient directions, are constructed for all possible combinations of rotation and scale.</p><p>We have avoided this by using (bilinear) interpolation in the search gradient map, which greatly reduces the amount of storage required.</p><p>SBM is highly parallelizable by nature and with our suggested improvements it becomes much suited for running on a GPU.</p><p>This have been implemented and tested, and the results clearly outperform those of our reference CPU implementation (with magnitudes of hundreds).</p><p>It is also very scalable and easily benefits from future devices without effort.</p><p>An extensive evaluation material and tools for evaluating object recognition algorithms have been developed and the implementation is evaluated and compared to two commercial 2D object recognition solutions.</p><p>The results show that the method is very powerful when dealing with the distortions listed above and competes well with its opponents.</p>

Utilizing a case study approach, this study explored the perspectives of preservice teachers as they relate to working with students with disabilities in inclusive classroom settings. Preservice teachers' perceptions about the extent, if any, their learning experiences during teacher preparation contributed to their perspectives was examined through a sequential exploratory design that employed both quantitative and qualitative data. The findings of this case study of six (6) elementary and secondary preservice teachers indicated that the experiences they had during their final student teaching (internship) were the most meaningful triggers of their perspective transformations. The findings further indicated that four (4) of the six (6) preservice teachers who identified they had a positive perspective toward including students with disabilities in their classrooms experienced a change in the directionality of that perspective to a less positive perspective following their final student teaching experience (internship). The use of the case study method, with its reliance on theoretical propositions and multiple sources of evidence, offered an effective way to better understand the perceived change in perspectives of these preservice teachers. The use of the Learning Activities Survey (LAS) to first ascertain whether or not preservice teachers perceived they had a perspective transformation offered a strong starting point to begin this investigation. When combined with additional qualitative data in the form of semi-structured interviews and document analysis, the structure of Yin's case study approach provided strong evidence supporting the nature and extent of preservice teachers' perspective transformations toward including students with disabilities. Implications of this study include recommendations for designing meaningful learning experiences for preservice teachers, a call for action research within teacher education, and purposeful provision of support and relationship building that goes beyond the acquisition of knowledge and skills and facilitates transformative learning.

Nowadays, fulfillment of the tactical operations in secrecy has great importance for especially subsurface and surface warfare platforms as a result of improvements in weapon technologies. Spreading out of the tactical operations to the larger areas has made discrimination of targets unavoidable. Due to enlargement of the weapon ranges and increasing subtle hostile threats as a result of improving technology, &ldquo / visual&rdquo / target detection methods left the stage to the computerized acoustic signature detection and evaluation methods. Despite this, the research projects have not sufficiently addressed in the field of acoustic signature evaluation. This thesis work mainly investigates classification and recognition techniques with TRN / LOFAR signals, which are emitted from surface and subsurface platforms and proposes possible adaptations of existing methods that may give better results if they are used with these signals. Also a detailed comparison has been made about the experimental results with underwater acoustic signals.

Casamento de padrões de pontos em Espaços Euclidianos é um dos problemas fundamentais em reconhecimento de padrões, tendo aplicações que vão desde Visão Computacional até Química Computacional. Sempre que dois padrões complexos estão codi- ficados em termos de dois conjuntos de pontos que identificam suas características fundamentais, sua comparação pode ser vista como um problema de casamento de padrões de pontos. Este trabalho propõe uma abordagem unificada para os problemas de casamento exato e inexato de padrões de pontos em Espaços Euclidianos de dimensão arbitrária. No caso de casamento exato, é garantida a obtenção de uma solução ótima. Para casamento inexato (quando ruído está presente), resultados experimentais confirmam a validade da abordagem. Inicialmente, considera-se o problema de casamento de padrões de pontos como um problema de casamento de grafos ponderados. O problema de casamento de grafos ponderados é então formulado como um problema de inferência Bayesiana em um modelo gráfico probabilístico. Ao explorar certos vínculos fundamentais existentes em padrões de pontos imersos em Espaços Euclidianos, provamos que, para o casamento exato de padrões de pontos, um modelo gráfico simples é equivalente ao modelo completo. É possível mostrar que inferência probabilística exata neste modelo simples tem complexidade polinomial para qualquer dimensionalidade do Espaço Euclidiano em consideração. Experimentos computacionais comparando esta técnica com a bem conhecida baseada em relaxamento probabilístico evidenciam uma melhora significativa de desempenho para casamento inexato de padrões de pontos. A abordagem proposta é signi- ficativamente mais robusta diante do aumento do tamanho dos padrões envolvidos. Na ausência de ruído, os resultados são sempre perfeitos. / Point pattern matching in Euclidean Spaces is one of the fundamental problems in Pattern Recognition, having applications ranging from Computer Vision to Computational Chemistry. Whenever two complex patterns are encoded by two sets of points identifying their key features, their comparison can be seen as a point pattern matching problem. This work proposes a single approach to both exact and inexact point set matching in Euclidean Spaces of arbitrary dimension. In the case of exact matching, it is assured to find an optimal solution. For inexact matching (when noise is involved), experimental results confirm the validity of the approach. We start by regarding point pattern matching as a weighted graph matching problem. We then formulate the weighted graph matching problem as one of Bayesian inference in a probabilistic graphical model. By exploiting the existence of fundamental constraints in patterns embedded in Euclidean Spaces, we prove that for exact point set matching a simple graphical model is equivalent to the full model. It is possible to show that exact probabilistic inference in this simple model has polynomial time complexity with respect to the number of elements in the patterns to be matched. This gives rise to a technique that for exact matching provably finds a global optimum in polynomial time for any dimensionality of the underlying Euclidean Space. Computational experiments comparing this technique with well-known probabilistic relaxation labeling show significant performance improvement for inexact matching. The proposed approach is significantly more robust under augmentation of the sizes of the involved patterns. In the absence of noise, the results are always perfect.

Casamento de padrões de pontos em Espaços Euclidianos é um dos problemas fundamentais em reconhecimento de padrões, tendo aplicações que vão desde Visão Computacional até Química Computacional. Sempre que dois padrões complexos estão codi- ficados em termos de dois conjuntos de pontos que identificam suas características fundamentais, sua comparação pode ser vista como um problema de casamento de padrões de pontos. Este trabalho propõe uma abordagem unificada para os problemas de casamento exato e inexato de padrões de pontos em Espaços Euclidianos de dimensão arbitrária. No caso de casamento exato, é garantida a obtenção de uma solução ótima. Para casamento inexato (quando ruído está presente), resultados experimentais confirmam a validade da abordagem. Inicialmente, considera-se o problema de casamento de padrões de pontos como um problema de casamento de grafos ponderados. O problema de casamento de grafos ponderados é então formulado como um problema de inferência Bayesiana em um modelo gráfico probabilístico. Ao explorar certos vínculos fundamentais existentes em padrões de pontos imersos em Espaços Euclidianos, provamos que, para o casamento exato de padrões de pontos, um modelo gráfico simples é equivalente ao modelo completo. É possível mostrar que inferência probabilística exata neste modelo simples tem complexidade polinomial para qualquer dimensionalidade do Espaço Euclidiano em consideração. Experimentos computacionais comparando esta técnica com a bem conhecida baseada em relaxamento probabilístico evidenciam uma melhora significativa de desempenho para casamento inexato de padrões de pontos. A abordagem proposta é signi- ficativamente mais robusta diante do aumento do tamanho dos padrões envolvidos. Na ausência de ruído, os resultados são sempre perfeitos. / Point pattern matching in Euclidean Spaces is one of the fundamental problems in Pattern Recognition, having applications ranging from Computer Vision to Computational Chemistry. Whenever two complex patterns are encoded by two sets of points identifying their key features, their comparison can be seen as a point pattern matching problem. This work proposes a single approach to both exact and inexact point set matching in Euclidean Spaces of arbitrary dimension. In the case of exact matching, it is assured to find an optimal solution. For inexact matching (when noise is involved), experimental results confirm the validity of the approach. We start by regarding point pattern matching as a weighted graph matching problem. We then formulate the weighted graph matching problem as one of Bayesian inference in a probabilistic graphical model. By exploiting the existence of fundamental constraints in patterns embedded in Euclidean Spaces, we prove that for exact point set matching a simple graphical model is equivalent to the full model. It is possible to show that exact probabilistic inference in this simple model has polynomial time complexity with respect to the number of elements in the patterns to be matched. This gives rise to a technique that for exact matching provably finds a global optimum in polynomial time for any dimensionality of the underlying Euclidean Space. Computational experiments comparing this technique with well-known probabilistic relaxation labeling show significant performance improvement for inexact matching. The proposed approach is significantly more robust under augmentation of the sizes of the involved patterns. In the absence of noise, the results are always perfect.

Casamento de padrões de pontos em Espaços Euclidianos é um dos problemas fundamentais em reconhecimento de padrões, tendo aplicações que vão desde Visão Computacional até Química Computacional. Sempre que dois padrões complexos estão codi- ficados em termos de dois conjuntos de pontos que identificam suas características fundamentais, sua comparação pode ser vista como um problema de casamento de padrões de pontos. Este trabalho propõe uma abordagem unificada para os problemas de casamento exato e inexato de padrões de pontos em Espaços Euclidianos de dimensão arbitrária. No caso de casamento exato, é garantida a obtenção de uma solução ótima. Para casamento inexato (quando ruído está presente), resultados experimentais confirmam a validade da abordagem. Inicialmente, considera-se o problema de casamento de padrões de pontos como um problema de casamento de grafos ponderados. O problema de casamento de grafos ponderados é então formulado como um problema de inferência Bayesiana em um modelo gráfico probabilístico. Ao explorar certos vínculos fundamentais existentes em padrões de pontos imersos em Espaços Euclidianos, provamos que, para o casamento exato de padrões de pontos, um modelo gráfico simples é equivalente ao modelo completo. É possível mostrar que inferência probabilística exata neste modelo simples tem complexidade polinomial para qualquer dimensionalidade do Espaço Euclidiano em consideração. Experimentos computacionais comparando esta técnica com a bem conhecida baseada em relaxamento probabilístico evidenciam uma melhora significativa de desempenho para casamento inexato de padrões de pontos. A abordagem proposta é signi- ficativamente mais robusta diante do aumento do tamanho dos padrões envolvidos. Na ausência de ruído, os resultados são sempre perfeitos. / Point pattern matching in Euclidean Spaces is one of the fundamental problems in Pattern Recognition, having applications ranging from Computer Vision to Computational Chemistry. Whenever two complex patterns are encoded by two sets of points identifying their key features, their comparison can be seen as a point pattern matching problem. This work proposes a single approach to both exact and inexact point set matching in Euclidean Spaces of arbitrary dimension. In the case of exact matching, it is assured to find an optimal solution. For inexact matching (when noise is involved), experimental results confirm the validity of the approach. We start by regarding point pattern matching as a weighted graph matching problem. We then formulate the weighted graph matching problem as one of Bayesian inference in a probabilistic graphical model. By exploiting the existence of fundamental constraints in patterns embedded in Euclidean Spaces, we prove that for exact point set matching a simple graphical model is equivalent to the full model. It is possible to show that exact probabilistic inference in this simple model has polynomial time complexity with respect to the number of elements in the patterns to be matched. This gives rise to a technique that for exact matching provably finds a global optimum in polynomial time for any dimensionality of the underlying Euclidean Space. Computational experiments comparing this technique with well-known probabilistic relaxation labeling show significant performance improvement for inexact matching. The proposed approach is significantly more robust under augmentation of the sizes of the involved patterns. In the absence of noise, the results are always perfect.

Cette thèse en bioinformatique étudie l'intérêt de rechercher des motifs dans des séquences génomiques à l'aide de grammaires. Depuis les années 80, à l'initiative notamment de David Searls, des travaux ont montré qu'en théorie, des grammaires de haut niveau offrent suffisamment d'expressivité pour permettre la description de motifs biologiques complexes, notamment par le biais d'une nouvelle classe de grammaire dédiée à la biologie : les grammaires à variables de chaîne (SVG, String Variable Grammar). Ce formalisme a donné lieu à Logol, qui est un langage grammatical et un outil d'analyse développé dans l'équipe Dyliss où a lieu cette thèse. Logol est un langage conçu pour être suffisamment flexible pour se plier à une large gamme de motifs qu'il est possible de rencontrer en biologie. Le fait que les grammaires restent inutilisée pour la reconnaissance de motifs pose question. Le formalisme grammatical est-il vraiment pertinent pour modéliser des motifs biologiques ? Cette thèse tente de répondre à cette question à travers une démarche exploratoire. Ainsi, nous étudions la pertinence d'utiliser les modèles grammaticaux, via Logol, sur six applications différentes de reconnaissance de motifs sur des génomes. Au travers de la résolution concrète de problématiques biologiques, nous avons mis en évidence certaines caractéristiques des modèles grammaticaux. Une de leurs limites est que leur utilisation présente un coût en termes de performance. Un de leurs atouts est que leur expressivité couvre un large spectre des motifs biologiques, contrairement aux méthodes alternatives, et d'ailleurs certains motifs modélisés par les grammaires n'ont pas d'autres alternatives existantes. Il s'avère en particulier que pour certains motifs complexes, tels que ceux alliant séquence et structure, l'approche grammaticale est la plus adaptée. Pour finir, l'une des conclusions de cette thèse est qu'il n'y a pas réellement de compétition entre les différentes approches, mais plutôt qu'il y a tout à gagner d'une coopération fructueuse. / This thesis studies the interest to look for patterns in genomic sequences using grammars. Since the 80s, work has shown that, in theory, high level grammars offer enough expressivity to allow the description of complex biological patterns. In particular David Searls has proposed a new grammar dedicated to biology: string variable grammar (SVG). This formalism has resulted in Logol, a grammatical language and an analysis tool developed by Dyliss team where this thesis is taking place. Logol is a language designed to be flexible enough to express a wide range of biological patterns. The fact that the grammars remain unknown to model biological patterns raises questions. Is the grammatical formalism really relevant to the recognition of biological patterns? This thesis attempts to answer this question through an exploratory approach. We study the relevance of using the grammatical patterns, by using Logol on six different applications of genomic pattern matching. Through the practical resolution of biological problems, we have highlighted some features of grammatical patterns. First, the use of grammatical models presents a cost in terms of performance. Second the expressiveness of grammatical models covers a broad spectrum of biological patterns, unlike the others alternatives, and some patterns modeled by grammars have no other alternative solutions. It also turns out that for some complex patterns, such as those combining sequence and structure, the grammatical approach is the most suitable. Finally, a thesis conclusion is that there was no real competition between different approaches, but rather everything to gain from successful cooperation.

This masters thesis continues in the work of two previous theses dealing with machine understanding of maps and modelling terrain. The final program also has to be able to interpret position data from dataloggers and integrate it with the loaded map. The goal for the program is to serve during training of Czech orienteering runners. Position measurement and storage is researched first. Also researched are map markers used to define the terrain. Afterwards, past approaches are evaluated, including identification of most severe issues hindering the usage in real world applications. Many improvements are proposed, for example methods to remove noise in the input data, or to improve processing speed. Lastly, a set of possible improvements to the original applications are made, i.e. methods for denoising the input data or for speedup of the image processing. Proposed improvements are then implemented, the most impactful being processing speed and contour segmentation improvements.

The aim of this work is to realize a system in the Matlab-Simulink environment, which will be able to detect and recognize the human face from the input image. The created model will actually simulate the biometric security systems working on the principle of face recognition. The work is divided into two parts. In the first part, several methods for face detection from image are described. We focused on the symptomatic oriented and color segmentation methods. The pattern matching method is also described and implemented; the advantage ofthe pattern matching that it can be used either for face detection or face recognition. The second part of this work contains a description of the face recognition. Where PCA (Principal Component Analysis) are used for this task, this part of the work also includes experimental results of tests performed on our methods.

This thesis deals with the pattern matching methods based on finite automata and describes their optimizations. It presents a methodology for the measurement of reliability of pattern matching methods, by comparing their results to the results of the PCRE library. Experiments were conducted for a finite automaton with perfect hashing and faulty transition table. Finally, the resulting reliability evaluation of the algorithm is shown and possible solutions of the identified problems are proposed.