Les Graphes sont des structures mathématiques puissantes constituant un outil de modélisation universel utilisé dans différents domaines de l'informatique, notamment dans le domaine de la reconnaissance de formes. L'appariement de graphes est l'opération principale dans le processus de la reconnaissance de formes à base de graphes. Dans ce contexte, trouver des solutions d'appariement de graphes, garantissant l'optimalité en termes de précision et de temps de calcul est un problème de recherche difficile et d'actualité. Dans cette thèse, nous nous intéressons à la résolution de ce problème dans deux domaines : la reconnaissance de formes 2D et 3D. Premièrement, nous considérons le problème d'appariement de graphes géométriques et ses applications sur la reconnaissance de formes 2D. Dance cette première partie, la reconnaissance des Kites (structures archéologiques) est l'application principale considérée. Nous proposons un "framework" complet basé sur les graphes pour la reconnaissance des Kites dans des images satellites. Dans ce contexte, nous proposons deux contributions. La première est la proposition d'un processus automatique d'extraction et de transformation de Kites a partir d'images réelles en graphes et un processus de génération aléatoire de graphes de Kites synthétiques. En utilisant ces deux processus, nous avons généré un benchmark de graphes de Kites (réels et synthétiques) structuré en 3 niveaux de bruit. La deuxième contribution de cette première partie, est la proposition d'un nouvel algorithme d'appariement pour les graphes géométriques et par conséquent pour les Kites. L'approche proposée combine les invariants de graphes au calcul de l'édition de distance géométrique. Deuxièmement, nous considérons le problème de reconnaissance des formes 3D ou nous nous intéressons à la reconnaissance d'objets déformables représentés par des graphes c.à.d. des tessellations de triangles. Nous proposons une décomposition des tessellations de triangles en un ensemble de sous structures que nous appelons triangle-étoiles. En se basant sur cette décomposition, nous proposons un nouvel algorithme d'appariement de graphes pour mesurer la distance entre les tessellations de triangles. L'algorithme proposé assure un nombre minimum de structures disjointes, offre une meilleure mesure de similarité en couvrant un voisinage plus large et utilise un ensemble de descripteurs qui sont invariants ou au moins tolérants aux déformations les plus courantes. Finalement, nous proposons une approche plus générale de l'appariement de graphes. Cette approche est fondée sur une nouvelle formalisation basée sur le problème de mariage stable. L'approche proposée est optimale en terme de temps d'exécution, c.à.d. la complexité est quadratique O(n2), et flexible en terme d'applicabilité (2D et 3D). Cette approche se base sur une décomposition en sous structures suivie par un appariement de ces structures en utilisant l'algorithme de mariage stable. L'analyse de la complexité des algorithmes proposés et l'ensemble des expérimentations menées sur les bases de graphes des Kites (réelle et synthétique) et d'autres bases de données standards (2D et 3D) attestent l'efficacité, la haute performance et la précision des approches proposées et montrent qu'elles sont extensibles et générales / Graphs are powerful mathematical modeling tools used in various fields of computer science, in particular, in Pattern Recognition. Graph matching is the main operation in Pattern Recognition using graph-based approach. Finding solutions to the problem of graph matching that ensure optimality in terms of accuracy and time complexity is a difficult research challenge and a topical issue. In this thesis, we investigate the resolution of this problem in two fields: 2D and 3D Pattern Recognition. Firstly, we address the problem of geometric graphs matching and its applications on 2D Pattern Recognition. Kite (archaeological structures) recognition in satellite images is the main application considered in this first part. We present a complete graph based framework for Kite recognition on satellite images. We propose mainly two contributions. The first one is an automatic process transforming Kites from real images into graphs and a process of generating randomly synthetic Kite graphs. This allowing to construct a benchmark of Kite graphs (real and synthetic) structured in different level of deformations. The second contribution in this part, is the proposition of a new graph similarity measure adapted to geometric graphs and consequently for Kite graphs. The proposed approach combines graph invariants with a geometric graph edit distance computation. Secondly, we address the problem of deformable 3D objects recognition, represented by graphs, i.e., triangular tessellations. We propose a new decomposition of triangular tessellations into a set of substructures that we call triangle-stars. Based on this new decomposition, we propose a new algorithm of graph matching to measure the distance between triangular tessellations. The proposed algorithm offers a better measure by assuring a minimum number of triangle-stars covering a larger neighbourhood, and uses a set of descriptors which are invariant or at least oblivious under most common deformations. Finally, we propose a more general graph matching approach founded on a new formalization based on the stable marriage problem. The proposed approach is optimal in term of execution time, i.e. the time complexity is quadratic O(n2) and flexible in term of applicability (2D and 3D). The analyze of the time complexity of the proposed algorithms and the extensive experiments conducted on Kite graph data sets (real and synthetic) and standard data sets (2D and 3D) attest the effectiveness, the high performance and accuracy of the proposed approaches and show that the proposed approaches are extensible and quite general

The human vision system is generally recognized as being superior to all known artificial vision systems. Visual attention, among many processes that are related to human vision, is responsible for identifying relevant regions in a scene for further processing. In most cases, analyzing an entire scene is unnecessary and inevitably time consuming. Hence considering visual attention might be advantageous. A subfield of computer vision where this particular functionality is computationally emulated has been shown to retain high potential in solving real world vision problems effectively. In this monograph, elements of visual attention are explored and algorithms are proposed that exploit such elements in order to enhance image understanding capabilities. Satellite images are given special attention due to their practical relevance, inherent complexity in terms of image contents, and their resolution. Processing such large-size images using visual attention can be very helpful since one can first identify relevant regions and deploy further detailed analysis in those regions only. Bottom-up features, which are directly derived from the scene contents, are at the core of visual attention and help identify salient image regions. In the literature, the use of intensity, orientation and color as dominant features to compute bottom-up attention is ubiquitous. The effects of incorporating an entropy feature on top of the above mentioned ones are also studied. This investigation demonstrates that such integration makes visual attention more sensitive to fine details and hence retains the potential to be exploited in a suitable context. One interesting application of bottom-up attention, which is also examined in this work, is that of image segmentation. Since low salient regions generally correspond to homogenously textured regions in the input image; a model can therefore be learned from a homogenous region and used to group similar textures existing in other image regions. Experimentation demonstrates that the proposed method produces realistic segmentation on satellite images. Top-down attention, on the other hand, is influenced by the observer’s current states such as knowledge, goal, and expectation. It can be exploited to locate target objects depending on various features, and increases search or recognition efficiency by concentrating on the relevant image regions only. This technique is very helpful in processing large images such as satellite images. A novel algorithm for computing top-down attention is proposed which is able to learn and quantify important bottom-up features from a set of training images and enhances such features in a test image in order to localize objects having similar features. An object recognition technique is then deployed that extracts potential target objects from the computed top-down attention map and attempts to recognize them. An object descriptor is formed based on physical appearance and uses both texture and shape information. This combination is shown to be especially useful in the object recognition phase. The proposed texture descriptor is based on Legendre moments computed on local binary patterns, while shape is described using Hu moment invariants. Several tools and techniques such as different types of moments of functions, and combinations of different measures have been applied for the purpose of experimentations. The developed algorithms are generalized, efficient and effective, and have the potential to be deployed for real world problems. A dedicated software testing platform has been designed to facilitate the manipulation of satellite images and support a modular and flexible implementation of computational methods, including various components of visual attention models.

Trois hypothèses principales existent quant aux indices locaux du contour étant les plus informatifs pour le processus de structuration de la forme, et permettant l’identification visuelle des objets : les angles et les indices de tridimensionnalité (Biederman, 1987 ; Boucart et al, 1995), les éléments mi-segments (Kennedy & Domander, 1985, Singh & Fulvio, 2005), et l’interaction entre le type de fragmentation et le degré de spécificité de la forme globale (Panis & Wagemans, 2009). L’objectif de ce travail consiste donc à confronter ces trois hypothèses, en tentant de déterminer par ailleurs le niveau (conscient ou non conscient) auquel s’opèrent la détection et le traitement de ces indices. Les paradigmes d’amorçage supra et infraliminaire sont employés. Des dessins d’objets fragmentés selon deux modes (angles et indices de tridimensionnalité versus éléments mi-segments) sont insérés en tant qu’amorce, précédant une image cible du même objet, elle-même fragmentée et présentant des zones de contours strictement identiques ou complémentaires à l’amorce. Aucune des quatre expériences proposées ne met en évidence un effet « qualitatif » du type de fragmentation. En revanche, certaines conditions temporelles permettent un effet d’amorçage de type lié à la quantité de contour présenté. Nos résultats confirment l’ambiguïté émergeant de la littérature relative aux zones de contours les plus informatives, et semblent conforter la nécessité d’un haut degré d’automaticité des processus impliqués dans la perspective de mettre en évidence des effets d’amorçage perceptif / Three main hypotheses exist concerning the most informative local features of contour for binding processes, allowing visual object identification: vertices and 3D features (Biederman, 1987 ; Boucart et al, 1995), midsegments elements (Kennedy R& Domander, 1985, Singh & Fulvio, 2005), and the interaction betweenfragmentation type and complexity of the global form (Panis & Wagemans, 2009). The aim of this work is to confront these hypotheses, while trying to determine the level (conscious or unconscious) at which the detection and the processing of these features occur. Conscious and unconscious priming paradigms are employed. Drawings of fragmented objects contain either vertices and 3D features or midsegment elements. They are used as primes, preceding a fragmented target image of the same object containing identical or complementary contour features. None of these four experiments highlight a qualitative effect of fragmentation types. However, a quantitative priming effect can be observed under certain timing conditions. Our results confirm the ambiguity emerging from literature concerning the most informative contour features and the necessity of a high degree of automatism of the processes involved in order to highlight perceptual priming effects

Reconhecimento de padrões em imagens é um problema clássico da área de visão computacional e consiste em detectar um padrão ou objeto de referência (template) em uma imagem digital. A maioria dos métodos para esta finalidade propostos na literatura simplifica as imagens por meio de operações como binarização, segmentação e detecção de bordas ou pontos de contorno, para em seguida extrair um conjunto de atributos descritores. O problema é que esta simplificação pode descartar informações importantes para descrição dos padrões, fazendo diminuir a robustez do processo de detecção. Um método eficiente deve ter a habilidade de identificar um padrão sujeito a algumas transformações geométricas como rotação, escalonamento, translação, cisalhamento e, no caso de métodos para imagens coloridas, deve ainda tratar do problema da constância da cor. Além disso, o conjunto de atributos que descrevem um padrão deve ser pequeno o suficiente para viabilizar o desenvolvimento de aplicações práticas como um sistema de visão robótica ou um sistema de vigilância. Estes são alguns dos motivos que justificam os esforços empreendidos nos inúmeros trabalhos desta natureza encontrados na literatura. Neste trabalho é proposto um método de casamento de padrões em imagens digitais, denominado Ciratefi (Circular, Radial and Template-Matching Filter), livre de segmentação e invariante sob transformações de similaridade, brilho e contraste. O Ciratefi consiste de três etapas de filtragem que sucessivamente descartam pontos na imagem analisada que não correspondem ao padrão procurado. Também foram propostas duas extensões do Ciratefi, uma que utiliza operadores morfológicos na extração dos atributos descritores, denominada Ciratefi Morfológico e outra para imagens coloridas chamada de color Ciratefi. Foram realizados vários experimentos com o intuito de comparar o desempenho do método proposto com dois dos principais métodos encontrados na literatura. Os resultados experimentais mostram que o desempenho do Ciratefi é superior ao desempenho dos métodos empregados na análise comparativa. / Pattern recognition in images is a classical problem in computer vision. It consists in detecting some reference pattern or template in a digital image. Most of the existing pattern recognition techniques usually apply simplifications like binarization, segmentation, interest points or edges detection before extracting features from images. Unfortunately, these simplification operations can discard rich grayscale information used to describe the patterns, decreasing the robustness of the detection process. An efficient method should be able to identify a pattern subject to some geometric transformations such as translation, scale, rotation, shearing and, in the case of color images, should deal with the color constancy problem. In addition, the set of features that describe a pattern should be sufficiently small to make feasible practical applications such as robot vision or surveillance system. These are some of the reasons that justify the effort for development of many works of this nature found in the literature. In this work we propose a segmentation-free template matching method named Ciratefi (Circular, Radial and Template-Matching Filter) that is invariant to rotation, scale, translation, brightness and contrast. Ciratefi consists of three cascaded filters that successively exclude pixels that have no chance of matching the template from further processing. Also we propose two extensions of Ciratefi, one using the mathematical morphology approach to extract the descriptors named Morphological Ciratefi and another to deal with color images named Color Ciratefi. We conducted various experiments aiming to compare the performance of the proposed method with two other methods found in the literature. The experimental results show that Ciratefi outperforms the methods used in the comparison analysis.

Apresentamos neste trabalho o desenvolvimento de um método para o reconhecimento do Formato de Objetos Tri-dimensionais. Os sistemas tradicionais de Visão Computacional empregam imagens bi-dimensionais obtidos através de câmeras de TV, ricas em detalhes necessários a visão humana. Estes detalhes em grande parte das aplicações industriais de Robôs são supérfluos. Os algoritmos tradicionais de classificação consomem portanto muito tempo no processamento deste excesso de informação. Para este trabalho, desenvolvemos um sistema dedicado para reconhecimento que utiliza um feixe de Laser defletido sobre um objeto e a digitalização da Luminância em cada ponto de sua superfície. A intensidade luminosa refletida e proporcional a distância do ponto ao observador. É, portanto, possível determinar parâmetros que classifiquem cada objeto. A inclinação de cada face de um poliedro, o comportamento de suas fronteiras e também a existência de arestas internas, são as características adotadas. Estas características são então rotuladas, permitindo que o programa de classificação busque em um \"banco de conhecimento\" previamente estabelecido, a descrição dos objetos. Uma mesa giratória permite a rotação do modele fornecendo novas vistas ao observador, determinando sua classificação. Todo o sistema é controlado por um microcomputador cujo programa reconhece em tempo real o objeto em observação. Para o protótipo construído, utilizamos um Laser de HeNe sendo a recepção do raio refletido realizada por um fototransistor. Os objetos reconhecíveis pelo programa são poliedros regulares simples, compondo o seguinte conjunto: 1 prisma de base triangular, 1 cubo, 1 pirâmide de base triangular, 1 pirâmide de base retangular. O tratamento matemático empregado visa a comprovação da tecnologia proposta, podendo, na continuação de trabalhos futuros, ser efetivamente estendido a diversos outros objetos como, por exemplo, os de superfícies curvas. / We present in this work a new method for three dimensional Shape Recognition. Traditional Computer Vision systems use bi-dimensional TV camera images. In most of the industrial Robotic applications, the excess of detail obtained by the TV camera is needless. Traditional classification algorithms spend a lot of time to process the excess of information. For the present work we developed a dedicated recognition system, which deflects a Laser beam over an object and digitizes the Reflected beam point by point over the surface. The intensity of the reflected beam is proportional to the observer distance. Using this technique it was possible to establish features to classify various objects. These features are the slope of the polyhedral surfaces, the boundary type and the inner edges. For each object the features are labeled and the classification algorithm searches in a \"knowledge data base\" for the object description. The recognition system used a He-Ne Laser and the reflected signal was captured by a photo-transistor. The object to be recognized is placed over a rotating table which can be rotated, supplying a new view for the classification. A microcomputer controls the system operation and the object is recognized in real time. The recognized objects were simple regular polyhedral, just as: 1 triangular base prism, 1 cube, 1 triangular base pyramid, 1 rectangular base pyramid. To check that the proposed technology was correct, we used a dedicated mathematical approach, which can be extended to other surfaces, such as curves, in future works.

Reconhecimento de padrões em imagens é um problema clássico da área de visão computacional e consiste em detectar um padrão ou objeto de referência (template) em uma imagem digital. A maioria dos métodos para esta finalidade propostos na literatura simplifica as imagens por meio de operações como binarização, segmentação e detecção de bordas ou pontos de contorno, para em seguida extrair um conjunto de atributos descritores. O problema é que esta simplificação pode descartar informações importantes para descrição dos padrões, fazendo diminuir a robustez do processo de detecção. Um método eficiente deve ter a habilidade de identificar um padrão sujeito a algumas transformações geométricas como rotação, escalonamento, translação, cisalhamento e, no caso de métodos para imagens coloridas, deve ainda tratar do problema da constância da cor. Além disso, o conjunto de atributos que descrevem um padrão deve ser pequeno o suficiente para viabilizar o desenvolvimento de aplicações práticas como um sistema de visão robótica ou um sistema de vigilância. Estes são alguns dos motivos que justificam os esforços empreendidos nos inúmeros trabalhos desta natureza encontrados na literatura. Neste trabalho é proposto um método de casamento de padrões em imagens digitais, denominado Ciratefi (Circular, Radial and Template-Matching Filter), livre de segmentação e invariante sob transformações de similaridade, brilho e contraste. O Ciratefi consiste de três etapas de filtragem que sucessivamente descartam pontos na imagem analisada que não correspondem ao padrão procurado. Também foram propostas duas extensões do Ciratefi, uma que utiliza operadores morfológicos na extração dos atributos descritores, denominada Ciratefi Morfológico e outra para imagens coloridas chamada de color Ciratefi. Foram realizados vários experimentos com o intuito de comparar o desempenho do método proposto com dois dos principais métodos encontrados na literatura. Os resultados experimentais mostram que o desempenho do Ciratefi é superior ao desempenho dos métodos empregados na análise comparativa. / Pattern recognition in images is a classical problem in computer vision. It consists in detecting some reference pattern or template in a digital image. Most of the existing pattern recognition techniques usually apply simplifications like binarization, segmentation, interest points or edges detection before extracting features from images. Unfortunately, these simplification operations can discard rich grayscale information used to describe the patterns, decreasing the robustness of the detection process. An efficient method should be able to identify a pattern subject to some geometric transformations such as translation, scale, rotation, shearing and, in the case of color images, should deal with the color constancy problem. In addition, the set of features that describe a pattern should be sufficiently small to make feasible practical applications such as robot vision or surveillance system. These are some of the reasons that justify the effort for development of many works of this nature found in the literature. In this work we propose a segmentation-free template matching method named Ciratefi (Circular, Radial and Template-Matching Filter) that is invariant to rotation, scale, translation, brightness and contrast. Ciratefi consists of three cascaded filters that successively exclude pixels that have no chance of matching the template from further processing. Also we propose two extensions of Ciratefi, one using the mathematical morphology approach to extract the descriptors named Morphological Ciratefi and another to deal with color images named Color Ciratefi. We conducted various experiments aiming to compare the performance of the proposed method with two other methods found in the literature. The experimental results show that Ciratefi outperforms the methods used in the comparison analysis.

Recognizing generic objects by single or multi view range images is a contemporary popular problem in 3D object recognition area with developing technology of scanning devices such as laser range scanners. This problem is vital to current and future vision systems performing shape based matching and classification of the objects in an arbitrary scene. Despite improvements on scanners, there are still imperfections on range scans such as holes or unconnected parts on images. This studyobjects at proposing and comparing algorithms that match a range image to complete 3D models in a target database.The study started with a baseline algorithm which usesstatistical representation of 3D shapesbased on 4D geometricfeatures, namely SURFLET-Pair relations.The feature describes the geometrical relationof a surface-point pair and reflects local and the global characteristics of the object. With the desire of generating solution to the problem,another algorithmthat interpretsSURFLET-Pairslike in the baseline algorithm, in which histograms of the features are used,isconsidered. Moreover, two other methods are proposed by applying 2D space filing curves on range images and applying 4D space filling curves on histograms of SURFLET-Pairs. Wavelet transforms are used for filtering purposes in these algorithms. These methods are tried to be compact, robust, independent on a global coordinate frame and descriptive enough to be distinguish queries&rsquo / categories.Baseline and proposed algorithms are implemented on a database in which range scans of real objects with imperfections are queries while generic 3D objects from various different categories are target dataset.

The human vision system is generally recognized as being superior to all known artificial vision systems. Visual attention, among many processes that are related to human vision, is responsible for identifying relevant regions in a scene for further processing. In most cases, analyzing an entire scene is unnecessary and inevitably time consuming. Hence considering visual attention might be advantageous. A subfield of computer vision where this particular functionality is computationally emulated has been shown to retain high potential in solving real world vision problems effectively. In this monograph, elements of visual attention are explored and algorithms are proposed that exploit such elements in order to enhance image understanding capabilities. Satellite images are given special attention due to their practical relevance, inherent complexity in terms of image contents, and their resolution. Processing such large-size images using visual attention can be very helpful since one can first identify relevant regions and deploy further detailed analysis in those regions only. Bottom-up features, which are directly derived from the scene contents, are at the core of visual attention and help identify salient image regions. In the literature, the use of intensity, orientation and color as dominant features to compute bottom-up attention is ubiquitous. The effects of incorporating an entropy feature on top of the above mentioned ones are also studied. This investigation demonstrates that such integration makes visual attention more sensitive to fine details and hence retains the potential to be exploited in a suitable context. One interesting application of bottom-up attention, which is also examined in this work, is that of image segmentation. Since low salient regions generally correspond to homogenously textured regions in the input image; a model can therefore be learned from a homogenous region and used to group similar textures existing in other image regions. Experimentation demonstrates that the proposed method produces realistic segmentation on satellite images. Top-down attention, on the other hand, is influenced by the observer’s current states such as knowledge, goal, and expectation. It can be exploited to locate target objects depending on various features, and increases search or recognition efficiency by concentrating on the relevant image regions only. This technique is very helpful in processing large images such as satellite images. A novel algorithm for computing top-down attention is proposed which is able to learn and quantify important bottom-up features from a set of training images and enhances such features in a test image in order to localize objects having similar features. An object recognition technique is then deployed that extracts potential target objects from the computed top-down attention map and attempts to recognize them. An object descriptor is formed based on physical appearance and uses both texture and shape information. This combination is shown to be especially useful in the object recognition phase. The proposed texture descriptor is based on Legendre moments computed on local binary patterns, while shape is described using Hu moment invariants. Several tools and techniques such as different types of moments of functions, and combinations of different measures have been applied for the purpose of experimentations. The developed algorithms are generalized, efficient and effective, and have the potential to be deployed for real world problems. A dedicated software testing platform has been designed to facilitate the manipulation of satellite images and support a modular and flexible implementation of computational methods, including various components of visual attention models.

Accurate and frequent construction progress tracking provides critical input data for project systems such as cost and schedule control as well as billing. Unfortunately, conventional progress tracking is labor intensive, sometimes subject to negotiation, and often driven by arcane rules. Attempts to improve progress tracking have recently focused mainly on automation, using technologies such as 3D imaging, Global Positioning System (GPS), Ultra Wide Band (UWB) indoor locating, hand-held computers, voice recognition, wireless networks, and other technologies in various combinations. Three dimensional (3D) imaging technologies, such as 3D laser scanners (LADARs) and photogrammetry have shown great potential for saving time and cost for recording project 3D status and thus to support some categories of progress tracking. Although laser scanners in particular and 3D imaging in general are being investigated and used in multiple applications in the construction industry, their full potential has not yet been achieved. The reason may be that commercial software packages are still too complicated and time consuming for processing scanned data. Methods have however been developed for the automated, efficient and effective recognition of project 3D BIM objects in site laser scans. This thesis presents a novel system that combines 3D object recognition technology with schedule information into a combined 4D object based construction progress tracking system. The performance of the system is investigated on a comprehensive field database acquired during the construction of a steel reinforced concrete structure, Engineering V Building at the University of Waterloo. It demonstrates a degree of accuracy that meets or exceeds typical manual performance. However, the earned value tracking is the most commonly used method in the industry. That is why the object based automated progress tracking system is further explored, and combined with earned value theory into an earned value based automated progress tracking system. Nevertheless, both of these systems are focused on permanent structure objects only, not secondary or temporary. In the last part of the thesis, several approaches are proposed for concrete construction secondary and temporary object tracking. It is concluded that accurate tracking of structural building project progress is possible by combining a-priori 4D project models with 3D object recognition using the algorithms developed and presented in this thesis.

<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>