No description available.

No description available.

No description available.

El principal objectiu d'aquest treball de tesi és tractar el problema de la representació de la textura en color des del punt de vista de la visió per computador. L'extensió dels mètodes classics de processament de textura per imatges en nivells de grisos als canals d'una imatge color no assegura resultats semblants als de la percepció humana en aquesta tasca. Els mecanismes d'inducció cromàtica del sistema visual humà, estudiats en psicofísica, són fonamentals en la dependència que crea l'entorn en la percepció del color. La inducció cromàtica inclou dos efectes complementaris: l'assimilació i el contrast cromàtic. Mentre el primer ja ha estat mesurat des de la psicofísica i extés a la visió per computador, molts aspectes del segon encara queden per fer. La contribució principal d'aquesta tesi és la definició d'un operador computacional que simula el fenòmen del contrast cromàtic i que té un comportament coherent amb el del sistema visual humà en diferents problemes de la percepcció de la textura en color, ja que permet enfatitzar les diferències de color en distribucions que són quasibé unimodals i així millorar la segmentació de les regions de color. El problema que encara queda obert és la realització de mesures psicofísiques pels paràmetres de l'operador, tal com es va fer amb l's-cielab per al procés d'assimilació.La definició de representacions computacionals de textura i color perceptuals és un objectiu de gran importància en els problemes d'inspecció automàtica de superfícies en els que els dispositius de la colorimetria clàssica no permeten donar bones mesures d'aparença de color. La segona contribució de la tesi defineix una representació computacional basada en mesures globals de color incloent-hi l'assimilació de color i mesures locals de les propietats de les regions segmentades considerant el contrast cromàtic. Aquesta representació és aplicada a la classificació de gres porcelànic.Tenint en compte que s'han de realitzar mesures molt acurades de petites diferències, s'ha dedicat una part d'aquest treball a l'adquisició d'imatges en color, i en concret a aconseguir bones propietats de constància de color. En aquest sentit, la darrera contribució de la tesi és la definició d'un algorisme de contància de color en línea per a una càmera lineal d'alta precisió de color. Aquest mètode s'ha basat en el model lineal diagonal de constància de color prèviament garantit amb una transformació que canvia les propietats de la sensibilitat de la càmera. / The main goal of this thesis is to deal with the colour texture representation problem from a computer vision point of view. It is easy to demonstrate that the extension of classical grey level methods for texture processing to the three channels of the corresponding colour texture does not succeed in having a human-like behaviour on this visual task. Chromatic induction mechanisms of the human visual system, which have been widely studied in psychophysics, play an important role on the dependency of the colour perception from its surround. Chromatic induction includes two complementary effects: chromatic assimilation and chromatic contrast. While the former has been psychophysically measured and lately extended to computer vision, some aspects on the last one still remain to be measured. The main contribution of this thesis is a computational operator that simulates the contrast induction phenomena that has demonstrated a coherent behaviour on different texture colour perception problems, since it allows to emphasise colour differences on almost-unimodal colour distributions and consequently improving the segmentation of colour regions. An open problem that will remain open from this work is the psychophysical measurement of the operator parameters, in the same sense as it was done with the s-cielab for the assimilation process.A perceptually consistent colour texture computational representation is a goal of extreme importance in automatic colour-textured surface inspection problems, where the classic colorimetric tools does not succeed in given good colour appearance measurements. In this scope, a second contribution is a colour-texture representation based on global colour features considering colour assimilation and local features based on properties of colour blobs considering colour contrast. This representation is applied to an automatic tile classification problem.Since an important accuracy is needed to measure such small differences, we have devoted a great part of this work to the colour acquisition issue, and to the problem of achieving good colour constancy properties on the acquired images. In this sense, a last contribution of this work has been to define an on-line colour constancy algorithm for a high colour precision scan line camera based on a diagonal linear colour constancy model previously guaranteed by linear transform changing the camera sensitivity properties.

Many smooth, highly specular coatings such as automotive paints are subjected to considerable performance demands as the customer expectations for appearance of coatings are continually increasing. Therefore it is vital to develop robust methods to monitor surface quality online. An automated visual assessment of specular coated surface that would not only provide a cost effective and reliable solution to the industries but also facilitate the implementation of a real-time feedback loop. The scope of this thesis is a subset of the inspection technology that facilitates real-time close loop control of the surface quality and concentrates on one common surface defect the seed defect. This machine vision system design utilizes surface reflectance models as a rational basis. Using a single high-contrast image the height of the seed defect is computed; the result is obtained rapidly and is reasonably accurate approximation of the actual height.

Um atuador planar de indução é um dispositivo baseado no mesmo princípio de funcionamento de um motor linear de indução, onde a interação de um campo magnético viajante produzido pelo primário do dispositivo com uma superfície de boa condutividade elétrica induz correntes parasitas que levam à produção de uma força de propulsão. O movimento planar sobre essa superfície é produzido através da movimentação linear em dois eixos ortogonais. Uma aplicação deste movimento é na propulsão de uma plataforma equipada com câmeras e sensores para a realização da inspeção em uma superfície metálica, que se beneficiaria da força normal que o motor planar de indução produz quando acionado sobre uma superfície ferromagnética para anexar a plataforma à superfície. Um modelo analítico que fornece equações para o campo elétrico e magnético é apresentado, e simulações numéricas baseadas no método dos elementos finitos são realizadas para avaliar o comportamento do dispositivo utilizando três tipos diferentes de superfícies como secundário: um secundário com duas camadas formadas por uma chapa de alumínio com outra de aço por baixo; apenas a chapa de alumínio; e apenas a chapa de aço. As distribuições de campo magnético calculadas por estes dois modelos teóricos mostram boa concordância entre si, e são utilizadas para calcular as forças de propulsão e normal produzidas pelo atuador. Medidas experimentais são realizadas em um protótipo de atuador planar de indução, e seus resultados são comparados com os resultados obtidos nos modelos teóricos, mostrando uma boa concordância e potencial para a aplicação do atuador planar de indução na inspeção de superfícies horizontais. / An induction planar actuator is a device that, based on the operating principle of a linear induction motor, in which the interaction between a travelling magnetic field produced by the primary of the device and a conducting surface generates eddy currents in the surface and leads to the generation of a thrust force. The device produces planar motion over this surface through movement on two orthogonal axis. An application of this movement is in a platform for the inspection of metallic surfaces, which is driven by the planar induction motor and equipped with cameras and sensors to inspect the surface. This application benefits from the normal force produced by the induction planar actuator operating over a ferromagnetic surface to attach the driving platform to it. An analytical model with equations for the electric and magnetic fields is presented, and numerical simulations based on the finite element method are carried out to assess the behaviour of the device using three different surfaces as secondary: a double-layered secondary formed by an aluminum plate over a steel plate; a aluminum only plate; and a single steel plate. The distributions for the magnetic field computed through these theoretical models show good agreement, and are employed to evaluate the thrust and normal forces produced by the planar induction actuator. Experimental measurements are made on a prototype of the device, and the results are compared to the results of the theoretical models, showing good agreement and potential in the application of the induction planar motor for the inspection of horizontal metallic surfaces.

Um atuador planar de indução é um dispositivo baseado no mesmo princípio de funcionamento de um motor linear de indução, onde a interação de um campo magnético viajante produzido pelo primário do dispositivo com uma superfície de boa condutividade elétrica induz correntes parasitas que levam à produção de uma força de propulsão. O movimento planar sobre essa superfície é produzido através da movimentação linear em dois eixos ortogonais. Uma aplicação deste movimento é na propulsão de uma plataforma equipada com câmeras e sensores para a realização da inspeção em uma superfície metálica, que se beneficiaria da força normal que o motor planar de indução produz quando acionado sobre uma superfície ferromagnética para anexar a plataforma à superfície. Um modelo analítico que fornece equações para o campo elétrico e magnético é apresentado, e simulações numéricas baseadas no método dos elementos finitos são realizadas para avaliar o comportamento do dispositivo utilizando três tipos diferentes de superfícies como secundário: um secundário com duas camadas formadas por uma chapa de alumínio com outra de aço por baixo; apenas a chapa de alumínio; e apenas a chapa de aço. As distribuições de campo magnético calculadas por estes dois modelos teóricos mostram boa concordância entre si, e são utilizadas para calcular as forças de propulsão e normal produzidas pelo atuador. Medidas experimentais são realizadas em um protótipo de atuador planar de indução, e seus resultados são comparados com os resultados obtidos nos modelos teóricos, mostrando uma boa concordância e potencial para a aplicação do atuador planar de indução na inspeção de superfícies horizontais. / An induction planar actuator is a device that, based on the operating principle of a linear induction motor, in which the interaction between a travelling magnetic field produced by the primary of the device and a conducting surface generates eddy currents in the surface and leads to the generation of a thrust force. The device produces planar motion over this surface through movement on two orthogonal axis. An application of this movement is in a platform for the inspection of metallic surfaces, which is driven by the planar induction motor and equipped with cameras and sensors to inspect the surface. This application benefits from the normal force produced by the induction planar actuator operating over a ferromagnetic surface to attach the driving platform to it. An analytical model with equations for the electric and magnetic fields is presented, and numerical simulations based on the finite element method are carried out to assess the behaviour of the device using three different surfaces as secondary: a double-layered secondary formed by an aluminum plate over a steel plate; a aluminum only plate; and a single steel plate. The distributions for the magnetic field computed through these theoretical models show good agreement, and are employed to evaluate the thrust and normal forces produced by the planar induction actuator. Experimental measurements are made on a prototype of the device, and the results are compared to the results of the theoretical models, showing good agreement and potential in the application of the induction planar motor for the inspection of horizontal metallic surfaces.

Um atuador planar de indução é um dispositivo baseado no mesmo princípio de funcionamento de um motor linear de indução, onde a interação de um campo magnético viajante produzido pelo primário do dispositivo com uma superfície de boa condutividade elétrica induz correntes parasitas que levam à produção de uma força de propulsão. O movimento planar sobre essa superfície é produzido através da movimentação linear em dois eixos ortogonais. Uma aplicação deste movimento é na propulsão de uma plataforma equipada com câmeras e sensores para a realização da inspeção em uma superfície metálica, que se beneficiaria da força normal que o motor planar de indução produz quando acionado sobre uma superfície ferromagnética para anexar a plataforma à superfície. Um modelo analítico que fornece equações para o campo elétrico e magnético é apresentado, e simulações numéricas baseadas no método dos elementos finitos são realizadas para avaliar o comportamento do dispositivo utilizando três tipos diferentes de superfícies como secundário: um secundário com duas camadas formadas por uma chapa de alumínio com outra de aço por baixo; apenas a chapa de alumínio; e apenas a chapa de aço. As distribuições de campo magnético calculadas por estes dois modelos teóricos mostram boa concordância entre si, e são utilizadas para calcular as forças de propulsão e normal produzidas pelo atuador. Medidas experimentais são realizadas em um protótipo de atuador planar de indução, e seus resultados são comparados com os resultados obtidos nos modelos teóricos, mostrando uma boa concordância e potencial para a aplicação do atuador planar de indução na inspeção de superfícies horizontais. / An induction planar actuator is a device that, based on the operating principle of a linear induction motor, in which the interaction between a travelling magnetic field produced by the primary of the device and a conducting surface generates eddy currents in the surface and leads to the generation of a thrust force. The device produces planar motion over this surface through movement on two orthogonal axis. An application of this movement is in a platform for the inspection of metallic surfaces, which is driven by the planar induction motor and equipped with cameras and sensors to inspect the surface. This application benefits from the normal force produced by the induction planar actuator operating over a ferromagnetic surface to attach the driving platform to it. An analytical model with equations for the electric and magnetic fields is presented, and numerical simulations based on the finite element method are carried out to assess the behaviour of the device using three different surfaces as secondary: a double-layered secondary formed by an aluminum plate over a steel plate; a aluminum only plate; and a single steel plate. The distributions for the magnetic field computed through these theoretical models show good agreement, and are employed to evaluate the thrust and normal forces produced by the planar induction actuator. Experimental measurements are made on a prototype of the device, and the results are compared to the results of the theoretical models, showing good agreement and potential in the application of the induction planar motor for the inspection of horizontal metallic surfaces.

Le travail présenté dans cette thèse porte sur l'inspection de surfaces métalliques industrielles. Nous proposons de généraliser des méthodes de l'imagerie hyperspectrale à des données multimodales comme des images optiques multi-canales, et des images thermographiques multi-temporelles. Dans la première application, les cubes de données sont construits à partir d'images multi-composantes pour détecter des défauts de surface. Les meilleures performances sont obtenues avec les éclairages multi-longueurs d'ondes dans le visible et le proche IR, et la détection du défaut en utilisant l'angle spectral, avec le spectre moyen comme référence. La deuxième application concerne l'utilisation de l'imagerie thermique pour l'inspection de pièces métalliques nucléaires afin de détecter des défauts de surface et sub-surface. Une approche 1D est proposée, basée sur l'utilisation du kurtosis pour sélectionner la composante principale parmi les premières obtenues après réduction des données avec l’ACP. La méthode proposée donne de bonnes performances avec des données non-bruitées et homogènes, cependant la SVD avec les algorithmes de détection d'anomalies est très robuste aux perturbations. Finalement, une approche, basée sur les techniques d'analyse de franges et la lumière structurée est présentée, dans le but d'inspecter des surfaces métalliques à forme libre. Après avoir déterminé les paramètres décrivant les modèles de franges sinusoïdaux, l'approche proposée consiste à projeter une liste de motifs déphasés et à calculer l'image de phase des motifs enregistrés. La localisation des défauts est basée sur la détection et l'analyse des franges dans les images de phase. / The work presented in this thesis deals with the quality control and inspection of industrial metallic surfaces. The purpose is the generalization and application of hyperspectral imagery methods for multimodal data such as multi-channel optical images and multi-temporal thermographic images. In the first application, data cubes are built from multi-component images to detect surface defects within flat metallic parts. The best performances are obtained with multi-wavelength illuminations in the visible and near infrared ranges, and detection using spectral angle mapper with mean spectrum as a reference. The second application turns on the use of thermography imaging for the inspection of nuclear metal components to detect surface and subsurface defects. A 1D approach is proposed based on using the kurtosis to select 1 principal component (PC) from the first PCs obtained after reducing the original data cube with the principal component analysis (PCA) algorithm. The proposed PCA-1PC method gives good performances with non-noisy and homogeneous data, and SVD with anomaly detection algorithms gives the most consistent results and is quite robust to perturbations such as inhomogeneous background. Finally, an approach based on fringe analysis and structured light techniques in case of deflectometric recordings is presented for the inspection of free-form metal surfaces. After determining the parameters describing the sinusoidal stripe patterns, the proposed approach consists in projecting a list of phase-shifted patterns and calculating the corresponding phase-images. Defect location is based on detecting and analyzing the stripes within the phase-images.

[...]L’inspection des surfaces considérées est basée sur la technique d’Inspection par Particules Magnétiques (Magnetic Particle Inspection (MPI)) qui révèle les défauts de surfaces après les traitements suivants : la surface est enduite d’une solution contenant les particules, puis magnétisées et soumise à un éclairage Ultra-Violet. La technique de contrôle non destructif MPI est une méthode bien connue qui permet de révéler la présence de fissures en surface d’un matériau métallique. Cependant, une fois le défaut révélé par le procédé, ladétection automatique sans intervention de l’opérateur en toujours problématique et à ce jour l'inspection basée sur le procédé MPI des matériaux tubulaires sur les sites de production deVallourec est toujours effectuée sur le jugement d’un opérateur humain. Dans cette thèse, nous proposons une approche par vision artificielle pour détecter automatiquement les défauts à partir des images de la surface de tubes après traitement MPI. Nous avons développé étape par étape une méthodologie de vision artificielle de l'acquisition d'images à la classification.[...] La première étape est la mise au point d’un prototype d'acquisition d’images de la surface des tubes. Une série d’images a tout d’abord été stockée afin de produire une base de données. La version actuelle du logiciel permet soit d’enrichir la base de donnée soit d’effectuer le traitement direct d’une nouvelle image : segmentation et saisie de la géométrie (caractéristiques de courbure) des défauts. Mis à part les caractéristiques géométriques et d’intensité, une analyse multi résolution a été réalisée sur les images pour extraire des caractéristiques texturales. Enfin la classification est effectuée selon deux classes : défauts et de non-défauts. Celle ci est réalisée avec le classificateur des forêts aléatoires (Random Forest) dont les résultats sontcomparés avec les méthodes Support Vector Machine et les arbres de décision.La principale contribution de cette thèse est l'optimisation des paramètres utilisées dans les étapes de segmentations dont ceux des filtres de morphologie mathématique, du filtrage linéaire utilisé et de la classification avec la méthode robuste des plans d’expériences (Taguchi), très utilisée dans le secteur de la fabrication. Cette étape d’optimisation a été complétée par les algorithmes génétiques. Cette méthodologie d’optimisation des paramètres des algorithmes a permis un gain de temps et d’efficacité significatif. La seconde contribution concerne la méthode d’extraction et de sélection des caractéristiques des défauts. Au cours de cette thèse, nous avons travaillé sur deux bases de données d’images correspondant à deux types de tubes : « Tool Joints » et « Tubes Coupling ». Dans chaque cas un tiers des images est utilisé pour l’apprentissage. Nous concluons que le classifieur du type« Random Forest » combiné avec les caractéristiques géométriques et les caractéristiques detexture extraites à partir d’une décomposition en ondelettes donne le meilleur taux declassification pour les défauts sur des pièces de « Tool Joints »(95,5%) (Figure 1). Dans le cas des « coupling tubes », le meilleur taux de classification a été obtenu par les SVM avec l’analyse multirésolution (89.2%) (figure.2) mais l’approche Random Forest donne un bon compromis à 82.4%. En conclusion la principale contrainte industrielle d’obtenir un taux de détection de défaut de 100% est ici approchée mais avec un taux de l’ordre de 90%. Les taux de mauvaises détections (Faux positifs ou Faux Négatifs) peuvent être améliorés, leur origine étant dans l’aspect de l’usinage du tube dans certaines parties, « Hard Bending ».De plus, la méthodologie développée peut être appliquée à l’inspection, par MPI ou non, de différentes lignes de produits métalliques / Industrial surface inspection of tubular material based on Magnetic Particle Inspection (MPI) is a challenging task. Magnetic Particle Inspection is a well known method for Non Destructive Testing with the goal to detect the presence of crack in the tubular surface. Currently Magnetic Particle Inspection for tubular material in Vallourec production site is stillbased on the human inspector judgment. It is time consuming and tedious job. In addition, itis prone to error due to human eye fatigue. In this thesis we propose a machine vision approach in order to detect the defect in the tubular surface MPI images automatically without human supervision with the best detection rate. We focused on crack like defects since they represent the major ones. In order to fulfill the objective, a methodology of machine vision techniques is developed step by step from image acquisition to defect classification. The proposed framework was developed according to industrial constraint and standard hence accuracy, computational speed and simplicity were very important. Based on Magnetic Particle Inspection principles, an acquisition system is developed and optimized, in order to acquire tubular material images for storage or processing. The characteristics of the crack-like defects with respect to its geometric model and curvature characteristics are used as priory knowledge for mathematical morphology and linear filtering. After the segmentation and binarization of the image, vast amount of defect candidates exist. Aside from geometrical and intensity features, Multi resolution Analysis wasperformed on the images to extract textural features. Finally classification is performed with Random Forest classifier due to its robustness and speed and compared with other classifiers such as with Support Vector Machine Classifier. The parameters for mathematical morphology, linear filtering and classification are analyzed and optimized with Design Of Experiments based on Taguchi approach and Genetic Algorithm. The most significant parameters obtained may be analyzed and tuned further. Experiments are performed ontubular materials and evaluated by its accuracy and robustness by comparing ground truth and processed images. This methodology can be replicated for different surface inspection application especially related with surface crack detection