Distance field text rendering has many advantages compared to most other text renderingsolutions. Two of the advantages are the possibility  to scale the glyphs without losing the crisp edge and less memory consumption. A drawback with distance field text renderingcan be high distance field generation time. The solution for fast distance field text renderingin this thesis generates the distance fields by drawing distance gradients locally over the outlines of the glyphs. This method is much faster than the old exact methods for generating distance fields that often includes multiple passes over the whole image. Using the solution for text rendering proposed in this thesis results in good looking text that is generated on the fly. The distance fields are generated on a mobile device in less than 10 ms for most of the glyphs in good quality which is less than the time between two frames.

Knowing the shapes, sizes and positional relations between features in an image can be useful for different types of image processing.Using a Distance Transform can give us these properties as a Distance Map.There are many different variations of distance transforms that can increase accuracy or add functionality, two such transforms are the Anti-Aliased Euclidean Distance Transform and the Signed Euclidean Distance Transform.To get the benefits of both of these it is of interest to see if they can be combined and if so, how does it perform?Investigating the possibility of such a transform is the main object of this thesis. To create this combined transform a copy of the image was created and then inverted, both images are transformed and the resulting distance maps are combined into one.Signed distance maps are created for three transforms using this method. The transforms in question are, EDT, AAEDT and VAAEDT.All transforms are then evaluated using a series of images containing two randomly placed circles, the circles are created using simple Signed Distance Functions. The signed transforms work and the AAEDT performs well compared to the Signed Euclidean Distance Transform.These results were expected as a similar gap in results can be seen between the regular EDT and AAEDT.But, this transform is not perfect and there is room for improvements in the accuracy, a good start for future work. / Att känna till formen, storleken samt olika objekts position relativt till varandra i en bild kan vara användbart för olika former av bildanalys.En Distance Transform kan ge oss alla dessa egenskaper i form av en ny bild, en så kallad avståndskarta.Det finns flera olika transformer som producerar avståndskartor med olika egenskaper och precision, två exempel är Anti-Aliased Euclidean Distance Transform och Signed Euclidean Distance Transform.För att få den ökade precisionen av Anti-Aliased Euclidean Distance Transform och funktionaliteten från en dubbelriktad så är det relevant att undersöka om de går att kombinera och om det går, hur presterar den nya transformen?Att undersöka om detta är möjligt är huvudmålet med detta arbete. För att skapa denna kombinerade transform så kopieras och inverteras bilden som ska transformeras, både kopian och orginalet transformeras sedan och de resulterande avståndskartorna kombineras till ett resultat.Dubbelriktade avståndskartor skapas för tre transformer, Euclidean Distance Transform, Anti-Aliased Euclidean Distance Transform och Vector Anti-Aliased Euclidean Distance Transform.Alla tre transformer utvärderas sedan genom en serie testbilder innehållandes två slumpmässigt placerade cirklar, skapade med hjälp av vektormatematik. De dubbelriktade transformerna fungerar och resultaten är i linje med motsvarande resultat för enkelriktade transformer.Detta betyder dock inte att resultaten är perfekta, utan det finns utrymme för prestandavinster i precisionen, detta är därför en bra startriktning för framtida förbättringsarbete.

No description available.

<p>This thesis shows the result from investigations of methods that use distance vectors when matching pictures. The distance vectors are available in a distance map made by the Euclidean Distance Transform. The investigated methods use the two characteristic features of the distance vector when matching pictures, length and direction. The length of the vector is used to calculate a value of how good a match is and the direction of the vector is used to predict a transformation to get a better match. The results shows that the number of calculation steps that are used during a search can be reduced compared to matching methods that only uses the distance during the matching.</p>

This thesis shows the result from investigations of methods that use distance vectors when matching pictures. The distance vectors are available in a distance map made by the Euclidean Distance Transform. The investigated methods use the two characteristic features of the distance vector when matching pictures, length and direction. The length of the vector is used to calculate a value of how good a match is and the direction of the vector is used to predict a transformation to get a better match. The results shows that the number of calculation steps that are used during a search can be reduced compared to matching methods that only uses the distance during the matching.

[pt] Este trabalho apresenta um método para extração de malhas poligonais adaptativas em multi-resolução, a partir de objetos volumétricos. As principais aplicações da extração de malhas estão ligadas à área médica, dinâmica de fluidos, geociências, meteorologia, dentre outras. Nestas áreas os dados podem ser representados como objetos volumétricos. Nos dados volumétricos as informações estão representadas implicitamente, o que dificulta o processamento direto dos objetos que se encontram representados dentro do volume. A extração da malha visa obter uma representação explícita dos objetos, de modo a viabilizar o processamento dos mesmos. O método apresentado na tese procura extrair a malha a partir de processos de Simplicação e Refinamento. Durante a simplificação é extraída uma representação super amostrada do objeto (na mesma resolução do volume inicial), a qual é simplificada de modo a se obter uma malha base ou malha grossa, em baixa resolução, porém contendo a topologia correta do objeto. A etapa de refinamento utiliza a transformada de distâ ncia para obter uma representação da malha em multi-resolução, ou seja, a cada instante é obtida uma malha de maior resolução que vai se adaptando progressivamente à geometria do objeto. A malha final apresenta uma série de propriedades importantes, como boa razão de aspecto dos triângulos, converge para a superfície do objeto, pode ser aplicada tanto a objetos com borda quanto a objetos sem borda, pode ser aplicada tanto a superfície conexas quanto a não conexas, dentre outras. / [en] This work presents a method for extracting multiresolution adaptive polygonal meshes, from volumetric objects. Main aplications of this work are related to medical area, fluid dynamics, geosciences, metheorology and others. In these areas data may be represented as volumetric objects. Volumetric datasets are implicit representations of objects, so it s very dificult to apply directly any process to these objects. Mesh extraction obtains an explicit representation of the objetc, such that it s easier to process directly the objects. The presented method extracts the mesh from two main processes: Simplification and Refinement. The simplification step extracts a supersampled representation of the object (in the same volume resolution), and simplifies it in such a way to obtain a base mesh (or coarse mesh), in a low resolution, but containing the correct topology of the object. Refinement step uses the distance transform to obtain a multiresolution representation of the mesh, it means that at each instant it s obtained an adaptive higher resolution mesh. The final mesh presents a set of important properties, like good triangle aspect ratio, convergency to the object surface, may be applied as to objects with boundary and as to objects with multiple connected components, among others properties.

Les travaux présentés dans ce manuscrit s’inscrivent dans le contexte de l’inspection automatisée d’assemblages mécaniques aéronautiques par vision artificielle. Il s’agit de décider si l’assemblage mécanique a été correctement réalisé (assemblage conforme). Les travaux ont été menés dans le cadre de deux projets industriels. Le projet CAAMVis d’une part, dans lequel le capteur d’inspection est constitué d’une double tête stéréoscopique portée par un robot, le projet Lynx© d’autre part, dans lequel le capteur d’inspection est une caméra Pan/Tilt/Zoom (vision monoculaire). Ces deux projets ont pour point commun la volonté d’exploiter au mieux le modèle CAO de l’assemblage (qui fournit l’état de référence souhaité) dans la tâche d’inspection qui est basée sur l’analyse de l’image ou des images 2D fournies par le capteur. La méthode développée consiste à comparer une image 2D acquise par le capteur (désignée par « image réelle ») avec une image 2D synthétique, générée à partir du modèle CAO. Les images réelles et synthétiques sont segmentées puis décomposées en un ensemble de primitives 2D. Ces primitives sont ensuite appariées, en exploitant des concepts de la théorie de graphes, notamment l’utilisation d’un graphe biparti pour s’assurer du respect de la contrainte d’unicité dans le processus d’appariement. Le résultat de l’appariement permet de statuer sur la conformité ou la non-conformité de l’assemblage. L’approche proposée a été validée à la fois sur des données de simulation et sur des données réelles acquises dans le cadre des projets sus-cités. / The work presented in this manuscript deals with automated inspection of aeronautical mechanical parts using computer vision. The goal is to decide whether a mechanical assembly has been assembled correctly i.e. if it is compliant with the specifications. This work was conducted within two industrial projects. On one hand the CAAMVis project, in which the inspection sensor consists of a dual stereoscopic head (stereovision) carried by a robot, on the other hand the Lynx© project, in which the inspection sensor is a single Pan/Tilt/Zoom camera (monocular vision). These two projects share the common objective of exploiting as much as possible the CAD model of the assembly (which provides the desired reference state) in the inspection task which is based on the analysis of the 2D images provided by the sensor. The proposed method consists in comparing a 2D image acquired by the sensor (referred to as "real image") with a synthetic 2D image generated from the CAD model. The real and synthetic images are segmented and then decomposed into a set of 2D primitives. These primitives are then matched by exploiting concepts from the graph theory, namely the use of a bipartite graph to guarantee the respect of the uniqueness constraint required in such a matching process. The matching result allows to decide whether the assembly has been assembled correctly or not. The proposed approach was validated on both simulation data and real data acquired within the above-mentioned projects.

A textura de uma imagem apresenta informações importantes sobre as características de um objeto. Usar essa informação para reconhecimento de padrões vem sendo uma tarefa bastante pesquisada na área de processamento de imagens e aplicado em atividades como indústria têxtil, biologia, análise de imagens médicas, imagens de satélite, análise de peças industriais, entre outros. Muitos pesquisadores focam em criar mecanismos que convertam a imagem em um vetor de características a fim de utilizar um classificador sobre esse vetores. No entanto, as imagens podem ser transformadas para que que características peculiares sejam evidenciadas fazendo com que extratores de características já existentes explorem melhor as imagens. Esse trabalho tem como objetivo estudar a influência da aplicação de métodos de pré-processamento em imagens de textura para a posterior análise das imagens. Os métodos escolhidos são seis: difusão isotrópica, difusão anisotrópica clássica, dois métodos de regularização da difusão anisotrópica, um método de difusão morfológica e a transformada de distância. Além disso, os métodos foram aliados a sete descritores já conhecidos da literatura para que as características das imagens tranformadas sejam extraídas. Resultados mostram um aumento significativo no desempenho dos classificadores KNN e Naive Bayes quando utilizados nas imagens transformadas de quatro bases de textura: Brodatz, Outex, Usptex e Vistex. / The texture of an image plays an important source of information of the image content. The use of this information to pattern recognition became very popular in image processing area and has applications such in textile industry, biology, medical image analysis, satelite images analysis, industrial equipaments analysis, among others. Many researchers focus on creating different methods to convert the input image to a feature vector to the able to classify the image based on these vectors. However, images can be modified in different ways such that important features are enhanced. Therefore, descriptors are able to extract features easily to perform a better representation of the image. This project aims to apply six different preprocessing methods to analyze their power of enhancement on the texture extraction. The methods are: isotropic diffusion, the classic anisotropic diffusion, two regularizations of the anisotropic diffusion, a morphologic diffusion and the distance transform. To extract the features of these modified images, seven texture analysis algorithms are used along KNN and Naive Bayes to classify the textures. Results show a significant increase when datasets Brodatz, Vistex, Usptex and Outex are transformed prior to texture analysis and classification.

A textura de uma imagem apresenta informações importantes sobre as características de um objeto. Usar essa informação para reconhecimento de padrões vem sendo uma tarefa bastante pesquisada na área de processamento de imagens e aplicado em atividades como indústria têxtil, biologia, análise de imagens médicas, imagens de satélite, análise de peças industriais, entre outros. Muitos pesquisadores focam em criar mecanismos que convertam a imagem em um vetor de características a fim de utilizar um classificador sobre esse vetores. No entanto, as imagens podem ser transformadas para que que características peculiares sejam evidenciadas fazendo com que extratores de características já existentes explorem melhor as imagens. Esse trabalho tem como objetivo estudar a influência da aplicação de métodos de pré-processamento em imagens de textura para a posterior análise das imagens. Os métodos escolhidos são seis: difusão isotrópica, difusão anisotrópica clássica, dois métodos de regularização da difusão anisotrópica, um método de difusão morfológica e a transformada de distância. Além disso, os métodos foram aliados a sete descritores já conhecidos da literatura para que as características das imagens tranformadas sejam extraídas. Resultados mostram um aumento significativo no desempenho dos classificadores KNN e Naive Bayes quando utilizados nas imagens transformadas de quatro bases de textura: Brodatz, Outex, Usptex e Vistex. / The texture of an image plays an important source of information of the image content. The use of this information to pattern recognition became very popular in image processing area and has applications such in textile industry, biology, medical image analysis, satelite images analysis, industrial equipaments analysis, among others. Many researchers focus on creating different methods to convert the input image to a feature vector to the able to classify the image based on these vectors. However, images can be modified in different ways such that important features are enhanced. Therefore, descriptors are able to extract features easily to perform a better representation of the image. This project aims to apply six different preprocessing methods to analyze their power of enhancement on the texture extraction. The methods are: isotropic diffusion, the classic anisotropic diffusion, two regularizations of the anisotropic diffusion, a morphologic diffusion and the distance transform. To extract the features of these modified images, seven texture analysis algorithms are used along KNN and Naive Bayes to classify the textures. Results show a significant increase when datasets Brodatz, Vistex, Usptex and Outex are transformed prior to texture analysis and classification.