Génération et édition de textures géométriques représentées par des ensembles de points

Thèse numérisée par la Division de la gestion de documents et des archives de l'Université de Montréal

Evaluation of texture and geometry for dimensional facial expression recognition

Facial expression recognition (FER) algorithms mainly focus on classification into a small discrete set of emotions or representation of emotions using facial action units (AUs). Dimensional representation of emotions as continuous values in an arousal-valence space is relatively less investigated. It is not fully known whether fusion of geometric and texture features will result in better dimensional representation of spontaneous emotions. Moreover, the performance of many previously proposed approaches to dimensional representation has not been evaluated thoroughly on publicly available databases. To address these limitations, this paper presents an evaluation framework for dimensional representation of spontaneous facial expressions using texture and geometric features. SIFT, Gabor and LBP features are extracted around facial fiducial points and fused with FAP distance features. The CFS algorithm is adopted for discriminative texture feature selection. Experimental results evaluated on the publicly accessible NVIE database demonstrate that fusion of texture and geometry does not lead to a much better performance than using texture alone, but does result in a significant performance improvement over geometry alone. LBP features perform the best when fused with geometric features. Distributions of arousal and valence for different emotions obtained via the feature extraction process are compared with those obtained from subjective ground truth values assigned by viewers. Predicted valence is found to have a more similar distribution to ground truth than arousal in terms of covariance or Bhattacharya distance, but it shows a greater distance between the means.

Automatically Recovering Geometry and Texture from Large Sets of Calibrated Images

Three-dimensional models which contain both geometry and texture have numerous applications such as urban planning, physical simulation, and virtual environments. A major focus of computer vision (and recently graphics) research is the automatic recovery of three-dimensional models from two-dimensional images. After many years of research this goal is yet to be achieved. Most practical modeling systems require substantial human input and unlike automatic systems are not scalable. This thesis presents a novel method for automatically recovering dense surface patches using large sets (1000's) of calibrated images taken from arbitrary positions within the scene. Physical instruments, such as Global Positioning System (GPS), inertial sensors, and inclinometers, are used to estimate the position and orientation of each image. Essentially, the problem is to find corresponding points in each of the images. Once a correspondence has been established, calculating its three-dimensional position is simply a matter of geometry. Long baseline images improve the accuracy. Short baseline images and the large number of images greatly simplifies the correspondence problem. The initial stage of the algorithm is completely local and scales linearly with the number of images. Subsequent stages are global in nature, exploit geometric constraints, and scale quadratically with the complexity of the underlying scene. We describe techniques for: 1) detecting and localizing surface patches; 2) refining camera calibration estimates and rejecting false positive surfels; and 3) grouping surface patches into surfaces and growing the surface along a two-dimensional manifold. We also discuss a method for producing high quality, textured three-dimensional models from these surfaces. Some of the most important characteristics of this approach are that it: 1) uses and refines noisy calibration estimates; 2) compensates for large variations in illumination; 3) tolerates significant soft occlusion (e.g. tree branches); and 4) associates, at a fundamental level, an estimated normal (i.e. no frontal-planar assumption) and texture with each surface patch.

Maximum Spreading of Liquid Drops Impacting on Groove-Textured Surfaces: Effect of Surface Texture

Maximum, spreading of liquid drops impacting on solid surfaces textured with unidirectional parallel grooves is studied for drop Weber number in the range 1-100 focusing on the role of texture geometry and wettability. The maximum spread factor of impacting drops measured perpendicular to grooves; beta(m,perpendicular to) is seen to be less than, that:measured parallel to grooves, beta(m,perpendicular to).The difference between beta(m,perpendicular to), and beta(m,parallel to) increases with drop impact velocity. This deviation of beta(m,perpendicular to) from beta(m,parallel to) is analyzed by considering the possible mechanisms, correspond, ing to experimental observations (1) impregnation of drop into the grooves, (2) convex shape of liquid vapor interface near contact line at maximum spreading, and (3) contact line pinning of spreading drop at the pillar edges by incorporating them into an energy conservation-based model. The analysis reveals that contact line pinning offers a physically meaningful justification of the observed: deviation of beta(m,perpendicular to) from beta(m,parallel to) compared to other possible candidates. A unified model, incorporating all the above-mentioned mechanisms, is formulated, which predicts beta(m,perpendicular to) on several groove-textured surfaces made of intrinsically hydrophilic and hydrophobic materials with an average error of 8.3%. The effect of groove-texture geometrical parameters,on maximum drop spreading is explained using this unified model. A special case of the unified model, with contact line pinning, absent, predicts beta(m,parallel to) with an average error of 6.3%.

The Representation of Image Texture

This thesis explores how to represent image texture in order to obtain information about the geometry and structure of surfaces, with particular emphasis on locating surface discontinuities. Theoretical and psychophysical results lead to the following conclusions for the representation of image texture: (1) A texture edge primitive is needed to identify texture change contours, which are formed by an abrupt change in the 2-D organization of similar items in an image. The texture edge can be used for locating discontinuities in surface structure and surface geometry and for establishing motion correspondence. (2) Abrupt changes in attributes that vary with changing surface geometry ??ientation, density, length, and width ??ould be used to identify discontinuities in surface geometry and surface structure. (3) Texture tokens are needed to separate the effects of different physical processes operating on a surface. They represent the local structure of the image texture. Their spatial variation can be used in the detection of texture discontinuities and texture gradients, and their temporal variation may be used for establishing motion correspondence. What precisely constitutes the texture tokens is unknown; it appears, however, that the intensity changes alone will not suffice, but local groupings of them may. (4) The above primitives need to be assigned rapidly over a large range in an image.

Object segregation and local gist vision using low-level geometry

Multi-scale representations of lines, edges and keypoints on the basis of simple, complex and end-stopped cells can be used for object categorisation and recognition (Rodrigues and du Buf, 2009 BioSystems 95 206-226). These representations are complemented by saliency maps of colour, texture, disparity and motion information, which also serve to model extremely fast gist vision in parallel with object segregation. We present a low-level geometry model based on a single type of self-adjusting grouping cell, with a circular array of dendrites connected to edge cells located at several angles.

Simulation des fonctions de texture bidirectionnelles

Le réalisme des objets en infographie exige de simuler adéquatement leur apparence sous divers éclairages et à différentes échelles. Une solution communément adoptée par les chercheurs consiste à mesurer avec l’aide d’appareils calibrés la réflectance d’un échantillon de surface réelle, pour ensuite l’encoder sous forme d’un modèle de réflectance (BRDF) ou d’une texture de réflectances (BTF). Malgré des avancées importantes, les données ainsi mises à la portée des artistes restent encore très peu utilisées. Cette réticence pourrait s’expliquer par deux raisons principales : (1) la quantité et la qualité de mesures disponibles et (2) la taille des données. Ce travail propose de s’attaquer à ces deux problèmes sous l’angle de la simulation. Nous conjecturons que le niveau de réalisme du rendu en infographie produit déjà des résultats satisfaisants avec les techniques actuelles. Ainsi, nous proposons de précalculer et encoder dans une BTF augmentée les effets d’éclairage sur une géométrie, qui sera par la suite appliquée sur les surfaces. Ce précalcul de rendu et textures étant déjà bien adopté par les artistes, il pourra mieux s’insérer dans leurs réalisations. Pour nous assurer que ce modèle répond aussi aux exigences des représentations multi-échelles, nous proposons aussi une adaptation des BTFs à un encodage de type MIP map.

Texture recognition under varying imaging geometries

La visió és probablement el nostre sentit més dominant a partir del qual derivem la majoria d'informació del món que ens envolta. A través de la visió podem percebre com són les coses, on són i com es mouen. En les imatges que percebem amb el nostre sistema de visió podem extreure'n característiques com el color, la textura i la forma, i gràcies a aquesta informació som capaços de reconèixer objectes fins i tot quan s'observen sota unes condicions totalment diferents. Per exemple, som capaços de distingir un mateix objecte si l'observem des de diferents punts de vista, distància, condicions d'il·luminació, etc. La Visió per Computador intenta emular el sistema de visió humà mitjançant un sistema de captura d'imatges, un ordinador, i un conjunt de programes. L'objectiu desitjat no és altre que desenvolupar un sistema que pugui entendre una imatge d'una manera similar com ho realitzaria una persona. Aquesta tesi es centra en l'anàlisi de la textura per tal de realitzar el reconeixement de superfícies. La motivació principal és resoldre el problema de la classificació de superfícies texturades quan han estat capturades sota diferents condicions, com ara distància de la càmera o direcció de la il·luminació. D'aquesta forma s'aconsegueix reduir els errors de classificació provocats per aquests canvis en les condicions de captura. En aquest treball es presenta detalladament un sistema de reconeixement de textures que ens permet classificar imatges de diferents superfícies capturades en diferents condicions. El sistema proposat es basa en un model 3D de la superfície (que inclou informació de color i forma) obtingut mitjançant la tècnica coneguda com a 4-Source Colour Photometric Stereo (CPS). Aquesta informació és utilitzada posteriorment per un mètode de predicció de textures amb l'objectiu de generar noves imatges 2D de les textures sota unes noves condicions. Aquestes imatges virtuals que es generen seran la base del nostre sistema de reconeixement, ja que seran utilitzades com a models de referència per al nostre classificador de textures. El sistema de reconeixement proposat combina les Matrius de Co-ocurrència per a l'extracció de característiques de textura, amb la utilització del Classificador del veí més proper. Aquest classificador ens permet al mateix temps aproximar la direcció d'il·luminació present en les imatges que s'utilitzen per testejar el sistema de reconeixement. És a dir, serem capaços de predir l'angle d'il·luminació sota el qual han estat capturades les imatges de test. Els resultats obtinguts en els diferents experiments que s'han realitzat demostren la viabilitat del sistema de predicció de textures, així com del sistema de reconeixement.

Influence of surface texture on the galling characteristics of lean duplex and austenitic stainless steels

Two simulative test methods were used to study galling in sheet forming of two types of stainlesssteel sheet: austenitic (EN 1.4301) and lean duplex LDX 2101 (EN 1.4162) in different surface conditions. Thepin-on-disc test was used to analyse the galling resistance of different combinations of sheet materials and lubricants. The strip reduction test, a severe sheet forming tribology test was used to simulate the conditionsduring ironing. This investigation shows that the risk of galling is highly dependent on the surface texture of theduplex steel. Trials were also performed in an industrial tool used for high volume production of pumpcomponents, to compare forming of LDX 2101 and austenitic stainless steel with equal thickness. The forming forces, the geometry and the strains in the sheet material were compared for the same component.It was found that LDX steels can be formed to high strain levels in tools normally applied for forming ofaustenitic steels, but tool adaptations are needed to comply with the higher strength and springback of thematerial.

Color texture analysis based on fractal descriptors

Color texture classification is an important step in image segmentation and recognition. The color information is especially important in textures of natural scenes, such as leaves surfaces, terrains models, etc. In this paper, we propose a novel approach based on the fractal dimension for color texture analysis. The proposed approach investigates the complexity in R, G and B color channels to characterize a texture sample. We also propose to study all channels in combination, taking into consideration the correlations between them. Both these approaches use the volumetric version of the Bouligand-Minkowski Fractal Dimension method. The results show a advantage of the proposed method over other color texture analysis methods. (C) 2011 Elsevier Ltd. All rights reserved.

The making of the architecture of the plant cell wall: How cells exploit geometry

Cell wall deposition is a key process in the formation, growth, and differentiation of plant cells. The most important structural components of the wall are long cellulose microfibrils, which are synthesized by synthases embedded in the plasma membrane. A fundamental question is how the microfibrils become oriented during deposition at the plasma membrane. The current textbook explanation for the orientation mechanism is a guidance system mediated by cortical microtubules. However, too many contraindications are known in secondary cell walls for this to be a universal mechanism, particularly in the case of helicoidal arrangements, which occur in many situations. An additional construction mechanism involves liquid crystalline self-assembly [A. C. Neville (1993) Biology of Fibrous Composites: Development Beyond the Cell Membrane (Cambridge Univ. Press, Cambridge, U.K.)], but the required amount of bulk material that is able to equilibrate thermally is not normally present at any stage of the wall deposition process. Therefore, we have asked whether the complex ordered texture of helicoidal cell walls can be formed in the absence of direct cellular guidance mechanisms. We propose that they can be formed by a mechanism that is based on geometrical considerations. It explains the genesis of the complicated helicoidal texture and shows that the cell has intrinsic, versatile tools for creating a variety of textures. A compelling feature of the model is that local rules generate global order, a typical phenomenon of life.

Texture for Script identification

The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.