Academic literature on the topic 'Images texturées'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Images texturées.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Images texturées":
1
Girod, Luc, and Marc Pierrot-Deseilligny. "L'Égalisation radiométrique de nuages de points 3D issus de corrélation dense." Revue Française de Photogrammétrie et de Télédétection, no. 206 (June 19, 2014): 3–14. http://dx.doi.org/10.52638/rfpt.2014.90.
Abstract:
Si les problèmes de colorimétrie dans le mosaïquage d'images ont fait l'objet d'études approfondies par le passé et qu'ils sont maintenant globalement résolus, il n'en est pas de même pour l'égalisation des scènes non planaires et des produits photogrammétriques 3D associés. En effet, certains produits photogrammétriques ne sont pas des images mais des produits purement 3D, de type nuage de points ou surfaces texturées, notamment. Cependant, la cohérence colorimétrique reste d'une grande importance dans ces cas pour une visualisation plus fluide des résultats. Cet article explore donc des algorithmes de correction colorimétrique à appliquer aux nuages de points dont la couleur provient de plusieurs images et leur implémentation dans la librairie MicMac de l'IGN.Deux points sont ici abordés : la correction du vignettage des images d'une part, ce défaut posant des problèmes d'homogénéité intra-image, et l'égalisation inter-images d'autre part.
2
Boussidi, Brahim, Ronan Fablet, Emmanuelle Autret, and Bertrand Chapron. "Accroissement stochastique de la résolution spatiale des traceurs géophysiques de l'océan: application aux observations satellitaires de la température de surface de l'océan." Revue Française de Photogrammétrie et de Télédétection, no. 202 (April 16, 2014): 66–78. http://dx.doi.org/10.52638/rfpt.2013.52.
Abstract:
Le développement des capteurs satellitaires d'observation des traceurs géophysiques à la surface de l'océan et les algorithmes de traitement associés ont connu un essor important au cours des vingt dernières années. Les différents capteurs satellitaires disponibles présentent des résolutions spatiales et temporelles différentes ainsi que différents niveaux de sensibilité à la couverture nuageuse. Dans le cas des images de température de surface de la mer, ceci se traduit notamment par de forts taux de données manquantes dans les observations de très haute-résolution (de l'ordre de 1kmx1km) contrairement aux observations de basse-résolution (de l'ordre de 25kmx25km). Il existe donc un enjeu fort pour exploiter conjointement les différentes sources d'information disponibles. Dans ce contexte, nous proposons un nouveau modèle stochastique de super-résolution basé sur une augmentation réaliste de l'information texturale des images. L'originalité de ce modèle réside dans la formulation d'a priori stochastiques sur la géométrie des images, qui sont caractéristiques des textures associées aux champs géophysiques à la surface de l'océan. Formellement, ce modèle consiste à modéliser les lignes de niveau de l'image comme des réalisations de marches aléatoires. Ce modèle stochastique s'étend naturellement à la simulation d'images haute-résolution à partir d'une observation basse-résolution. Cet article décrit la formulation mathématique du modèle proposé, ses caractéristiques théoriques ainsi que le schéma numérique mis en oeuvre pour la super-résolution d'images texturées. L'application à la simulation haute-résolution de champs de température de surface de la mer dans une région active de l'océan (courant des Aiguilles) démontre sa pertinence dans le contexte applicatif de la télédétection satellitaire de l'océan. Nous en discutons également les principales contributions ainsi que les différentes extensions possibles.
3
Hemalatha, S., and S. Margret Anouncia. "A Computational Model for Texture Analysis in Images with Fractional Differential Filter for Texture Detection." International Journal of Ambient Computing and Intelligence 7, no. 2 (July 2016): 93–113. http://dx.doi.org/10.4018/ijaci.2016070105.
Abstract:
This paper is dedicated to the modelling of textured images influenced by fractional derivatives for texture detection. As most of the images contain textures, texture analysis becomes the most important for image understanding and it is a key solution for many computer vision applications. Hence, texture must be suitably detected and represented. Nevertheless, existing texture detection algorithms consider texture as a unique feature from edges. The proposed model explores a novel way of developing texture detection algorithm by mimicking edge detection algorithms. The method assumes that texture feature is analogous to edges and thus, the time complexity is reduced significantly. The model proposed in this work is based on Gaussian kernel smoothing, Fractional partial derivatives and a statistical approach. It is justified to be robust to noisy images and possesses statistical interpretation. The model is validated by the classification experiments on different types of textured images from Brodatz album. It achieves higher classification accuracy than the existing methods.
4
Bhaumik, Shubrajit, Viorel Paleu, Dhrubajyoti Chowdhury, Adarsh Batham, Udit Sehgal, Basudev Bhattacharya, Chiradeep Ghosh, and Shubhabrata Datta. "Tribological Investigation of Textured Surfaces in Starved Lubrication Conditions." Materials 15, no. 23 (November 27, 2022): 8445. http://dx.doi.org/10.3390/ma15238445.
Abstract:
The present work investigates the friction reduction capability of two types of micro-textures (grooves and dimples) created on steel surfaces using a vertical milling machine. The wear studies were conducted using a pin-on-disc tribometer, with the results indicating a better friction reduction capacity in the case of the dimple texture as compared to the grooved texture. The microscopic images of the pin surface revealed deep furrows and significant damage on the pin surfaces of the groove-textured disc. An optimization of the textured surfaces was performed using an artificial neural network (ANN) model, predicting the influence of the surface texture as a function of the load, depth of cut and distance between the micro-textures.
5
Oliveira, Miguel, Gi-Hyun Lim, Tiago Madeira, Paulo Dias, and Vítor Santos. "Robust Texture Mapping Using RGB-D Cameras." Sensors 21, no. 9 (May 7, 2021): 3248. http://dx.doi.org/10.3390/s21093248.
Abstract:
The creation of a textured 3D mesh from a set of RGD-D images often results in textured meshes that yield unappealing visual artifacts. The main cause is the misalignments between the RGB-D images due to inaccurate camera pose estimations. While there are many works that focus on improving those estimates, the fact is that this is a cumbersome problem, in particular due to the accumulation of pose estimation errors. In this work, we conjecture that camera poses estimation methodologies will always display non-neglectable errors. Hence, the need for more robust texture mapping methodologies, capable of producing quality textures even in considerable camera misalignments scenarios. To this end, we argue that use of the depth data from RGB-D images can be an invaluable help to confer such robustness to the texture mapping process. Results show that the complete texture mapping procedure proposed in this paper is able to significantly improve the quality of the produced textured 3D meshes.
6
Wen, Mingyun, Jisun Park, and Kyungeun Cho. "Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks." Remote Sensing 13, no. 21 (October 22, 2021): 4254. http://dx.doi.org/10.3390/rs13214254.
Abstract:
This study focuses on reconstructing accurate meshes with high-resolution textures from single images. The reconstruction process involves two networks: a mesh-reconstruction network and a texture-reconstruction network. The mesh-reconstruction network estimates a deformation map, which is used to deform a template mesh to the shape of the target object in the input image, and a low-resolution texture. We propose reconstructing a mesh with a high-resolution texture by enhancing the low-resolution texture through use of the super-resolution method. The architecture of the texture-reconstruction network is like that of a generative adversarial network comprising a generator and a discriminator. During the training of the texture-reconstruction network, the discriminator must focus on learning high-quality texture predictions and to ignore the difference between the generated mesh and the actual mesh. To achieve this objective, we used meshes reconstructed using the mesh-reconstruction network and textures generated through inverse rendering to generate pseudo-ground-truth images. We conducted experiments using the 3D-Future dataset, and the results prove that our proposed approach can be used to generate improved three-dimensional (3D) textured meshes compared to existing methods, both quantitatively and qualitatively. Additionally, through our proposed approach, the texture of the output image is significantly improved.
7
Volkova, Natalya P., and Viktor N. Krylov. "VECTOR-DIFFERENCE TEXTURE SEGMENTATION METHOD IN TECHNICAL AND MEDICAL EXPRESS DIAGNOSTIC SYSTEMS." Herald of Advanced Information Technology 3, no. 4 (November 20, 2020): 226–39. http://dx.doi.org/10.15276/hait.04.2020.2.
Abstract:
The study shows the need for express systems, in which it is necessary to perform the analysis of texture images in various areas of diagnosis, for example, in medical express diagnostics of dermatologic disorders. Since the reliability of decision-making in such systems depends on the quality of image segmentation, which, as a rule, have the nature of spectral-statistical textures, it is advisable to develop methods for segmentation of such images and models for their presentation. A model of spectral-statistical texture is proposed, which takes into account the random nature of changes in the field variations and quasi-harmonics. On its basis, a vector-difference method of texture segmentation has been developed, which is based on the vector transformation of images of spectral and statistical textures based on vector algebra. The stages of the vector-difference method are the following: an evaluation of the spectral texture feature; an evaluation of the statistical texture feature; vector-difference transformation of texture images; a boundary detection of the homogeneous regions. For each pixel of the image in the processing aperture, the features of the spectral and statistical texture are evaluated. Statistical texture evaluation was performed by the quadratic-amplitude transformation. At the stage of vector-difference transformation of texture images, a vector of features of each pixel of an image is constructed, the elements of which are estimates of features of a spectral and statistical texture, and the modulus of the difference of two vectors is calculated. At the stage of boundary detection of homogeneous regions, Canny method was applied. The developed vector-difference texture segmentation method was applied both to model images of spectral-statistical texture and to texture images obtained in technical and medical diagnostics systems, namely, for images of psoriasis disease and wear zones of cutting tools. To compare the segmentation results, frequency-detector and amplitude-detector methods of texture segmentation were applied to these images. The quality of segmentation of homogeneous textured regions was evaluated by the Pratt's criterion and by constructing a confusion matrix. The research results showed that the developed vector-difference texture segmentation method has increased noise tolerance at a sufficient processing speed.
8
Soares, Lucas de Assis, Klaus Fabian Côco, Patrick Marques Ciarelli, and Evandro Ottoni Teatini Salles. "A Class-Independent Texture-Separation Method Based on a Pixel-Wise Binary Classification." Sensors 20, no. 18 (September 22, 2020): 5432. http://dx.doi.org/10.3390/s20185432.
Abstract:
Texture segmentation is a challenging problem in computer vision due to the subjective nature of textures, the variability in which they occur in images, their dependence on scale and illumination variation, and the lack of a precise definition in the literature. This paper proposes a method to segment textures through a binary pixel-wise classification, thereby without the need for a predefined number of textures classes. Using a convolutional neural network, with an encoder–decoder architecture, each pixel is classified as being inside an internal texture region or in a border between two different textures. The network is trained using the Prague Texture Segmentation Datagenerator and Benchmark and tested using the same dataset, besides the Brodatz textures dataset, and the Describable Texture Dataset. The method is also evaluated on the separation of regions in images from different applications, namely remote sensing images and H&E-stained tissue images. It is shown that the method has a good performance on different test sets, can precisely identify borders between texture regions and does not suffer from over-segmentation.
9
Vijay Kumar, Palnati, Pullela S. V. V. S. R. Kumar, Nakkella Madhuri, and M. Uma Devi. "Stone Image Classification Based on Overlapped 5-bit T-Patterns occurrence on 5-by-5 Sub Images." International Journal of Electrical and Computer Engineering (IJECE) 6, no. 3 (June 1, 2016): 1152. http://dx.doi.org/10.11591/ijece.v6i3.9233.
Abstract:
Texture classification is widely used in understanding the visual patterns and has wide range of applications. The present paper derived a novel approach to classify the stone textures based on the patterns occurrence on each sub window. The present approach identifies overlapped nine 5 bit T-patterns (O5TP) on each 5×5 sub window stone image. Based the number of occurrence of T-patterns count the present paper classify the stone images into any of the four classes i.e. brick, granite, marble and mosaic stone images. The novelty of the present approach is that no standard classification algorithm is used for the classification of stone images. The proposed method is experimented on Mayang texture images, Brodatz textures, Paul Bourke color images, VisTex database, Google color stone texture images and also original photo images taken by digital camera. The outcome of the results indicates that the proposed approach percentage of grouping performance is higher to that of many existing approaches.
10
Vijay Kumar, Palnati, Pullela S. V. V. S. R. Kumar, Nakkella Madhuri, and M. Uma Devi. "Stone Image Classification Based on Overlapped 5-bit T-Patterns occurrence on 5-by-5 Sub Images." International Journal of Electrical and Computer Engineering (IJECE) 6, no. 3 (June 1, 2016): 1152. http://dx.doi.org/10.11591/ijece.v6i3.pp1152-1160.
Abstract:
Texture classification is widely used in understanding the visual patterns and has wide range of applications. The present paper derived a novel approach to classify the stone textures based on the patterns occurrence on each sub window. The present approach identifies overlapped nine 5 bit T-patterns (O5TP) on each 5×5 sub window stone image. Based the number of occurrence of T-patterns count the present paper classify the stone images into any of the four classes i.e. brick, granite, marble and mosaic stone images. The novelty of the present approach is that no standard classification algorithm is used for the classification of stone images. The proposed method is experimented on Mayang texture images, Brodatz textures, Paul Bourke color images, VisTex database, Google color stone texture images and also original photo images taken by digital camera. The outcome of the results indicates that the proposed approach percentage of grouping performance is higher to that of many existing approaches.
Dissertations / Theses on the topic "Images texturées":
1
Konik, Hubert. "Contribution de l'approche pyramidale à la segmentation des images texturées." Saint-Etienne, 1994. http://www.theses.fr/1994STET4018.
Abstract:
En réponse au problème de la cotation visuelle assistée par ordinateur des différences d'aspect sur les surfaces textiles, nous nous sommes orientés vers les techniques de multirésolution. Notre contribution porte plus précisement sur leur utilisation dans le domaine de la segmentation via l'approche pyramidale. Après une description et une analyse critique de la structure classique et de ses trop grandes limites (notamment pour la description des objets allonges, des objets en grand nombre ou trop proches,), nous introduisons un nouveau concept : celui des pyramides localisées dans le support image ou pyramides locales. Elles permettent la mise en oeuvre du principe du focus d'attention, par une analyse individuelle et contextuelle des objets. En effet, chaque objet est décrit dans une pyramide centrée sur lui, caractérisant l'adaptativité de la méthode en fonction de la texture de l'image. L'introduction de la notion d'orientations pour la définition des racines de l'objet renforce sa localisation. La méthode est insensible aux translations et plus robuste vis-a-vis des rotations. Elle limite les problèmes intrinsèques de la structure classique du fait de sa trop grande rigidité. Les paramètres nécessaires à la construction des pyramides locales sont extraits de la classification de l'image en terme de micro ou de macro-texture. Celle-ci est obtenue en fonction de l'évolution de paramètres statistiques dans l'unique pyramide globale associée à l'image. Ils reposent sur des considérations perceptuelles de l'analyse de texture. Une étude de classification plus générale est illustrée sur d'autres types de surfaces texturées. En définitive, tous les outils que nous avons développés sont éprouvés sur une application précise, liée à notre domaine d'étude
2
Germain, Christian. "Contribution à la caractérisation multi-échelle de l'anisotropie des images texturées." Phd thesis, Université Sciences et Technologies - Bordeaux I, 1997. http://tel.archives-ouvertes.fr/tel-00166497.
Abstract:
Ce travail est consacré à la caractérisation de l'anisotropie des images. Pour y parvenir, il est établi que, dans le cas de textures complexes, la mesure de l'orientation dominante comme celle de l'anisotropie dépendent fortement de l'échelle à laquelle la texture a été observée.Le premier chapitre définit la notion de texture et celle d'échelle d'observation. Les différentes approches de caractérisation texturale existantes sont présentées et leur aptitude à rendre compte des phénomènes directionnels à différentes échelles d'observation est évaluée.
Le second chapitre présente les méthodes les plus courantes pour l'estimation de l'orientation dominante d'une texture. Un indicateur local est ensuite proposé : le Vecteur Directionnel Moyen. Il s'appuie sur des caractéristiques locales et peut être calculé à toute échelle d'observation. Ses performances sont étudiées sur des images de synthèse et sur des textures naturelles.
Le troisième chapitre introduit un nouvel indicateur d'anisotropie nommé Iso. Il est basé sur le calcul des différences locales des Vecteurs Directionnels Moyens obtenus à une échelle donnée. Ses performances sont comparées à celles des estimateurs classiques de dispersion directionnelle.
Le dernier chapitre est consacré à l'évaluation de l'anisotropie de textures complexes (microscopiques et macroscopiques) en fonction de l'échelle d'observation. Un modèle de texture complexe est construit et le comportement de l'indicateur Iso sur ce modèle est établi. L'indicateur est ensuite appliqué à la caractérisation de textures naturelles et de synthèse. Il est ensuite montré que l'évolution de cet indicateur en fonction de l'échelle d'observation fournit une courbe qui caractérise à la fois l'anisotropie de la texture traitée ainsi que la taille des différentes primitives texturales microscopiques et macroscopiques formant cette texture. L'indicateur Iso , calculé à différentes échelles, est appliqué à des textures synthétiques, à des textures de l'album de Brodatz ainsi qu'à des images de matériaux composites observés par microscopie électronique à transmission.
3
Faucheux, Cyrille. "Segmentation supervisée d'images texturées par régularisation de graphes." Thesis, Tours, 2013. http://www.theses.fr/2013TOUR4050/document.
Abstract:
Dans cette thèse, nous nous intéressons à un récent algorithme de segmentation d’images basé sur un processus de régularisation de graphes. L’objectif d’un tel algorithme est de calculer une fonction indicatrice de la segmentation qui satisfait un critère de régularité ainsi qu’un critère d’attache aux données. La particularité de cette approche est de représenter les images à l’aide de graphes de similarité. Ceux-ci permettent d’établir des relations entre des pixels non-adjacents, et ainsi de procéder à un traitement non-local des images. Afin d’en améliorer la précision, nous combinons cet algorithme à une seconde approche non-locale : des caractéristiques de textures. Un nouveau terme d’attache aux données est dans un premier temps développé. Inspiré des travaux de Chan et Vese, celui-ci permet d’évaluer l’homogénéité d’un ensemble de caractéristiques de textures. Dans un second temps, nous déléguons le calcul de l’attache aux données à un classificateur supervisé. Entrainé à reconnaitre certaines classes de textures, ce classificateur permet d’identifier les caractéristiques les plus pertinentes, et ainsi de fournir une modélisation plus aboutie du problème. Cette seconde approche permet par ailleurs une segmentation multiclasse. Ces deux méthodes ont été appliquées à la segmentation d’images texturées 2D et 3DIn this thesis, we improve a recent image segmentation algorithm based on a graph regularization process. The goal of this method is to compute an indicator function that satisfies a regularity and a fidelity criteria. Its particularity is to represent images with similarity graphs. This data structure allows relations to be established between similar pixels, leading to non-local processing of the data. In order to improve this approach, combine it with another non-local one: the texture features. Two solutions are developped, both based on Haralick features. In the first one, we propose a new fidelity term which is based on the work of Chan and Vese and is able to evaluate the homogeneity of texture features. In the second method, we propose to replace the fidelity criteria by the output of a supervised classifier. Trained to recognize several textures, the classifier is able to produce a better modelization of the problem by identifying the most relevant texture features. This method is also extended to multiclass segmentation problems. Both are applied to 2D and 3D textured images
4
Yum-Oh, Suk. "Utilisation de l'information de phase en segmentation et classification des images texturées." La Rochelle, 1995. http://www.theses.fr/1995LAROS003.
Abstract:
L’étude qui fait l'objet de cette thèse a été menée dans le cadre de l'analyse des textures. Elle contribue à la modélisation de la vision humaine préattentive en introduisant l'information portée par la phase des images texturées filtrées. Les performances du système visuel humain sont en effet particulièrement remarquables en ce qui concerne la vision des textures. Notre système utilise un filtrage multicanaux modelisé par des fonctions de Gabor. L’opération de filtrage par une fonction complexe permet d'obtenir une image en valeur complexe dont le module et la phase renferment des informations importantes. De nombreux auteurs ont avant nous étudié le module. Nous nous intéressons seulement à l'étude de l'information de phase pour extraire des caractéristiques pertinentes sur les textures. L’extraction de l'information de phase est délicate car les valeurs obtenues au moyen de l'operateur Arctangente présente des discontinuités en des endroits imprévisibles. Elle nécessite une procédure dite de déballage de la phase. La phase déballée est formée d'une composante linéaire et d'une composante locale. Du Buf et al. Ont récemment émis l'hypothèse que la connaissance de la phase locale permet de segmenter l'image. Mais, leur méthode présente des inconvénients. Le déballage est très difficile en raison de l'existence de nombreux points zéro. En outre, la méthode n'est applicable qu'a des filtres d'orientations verticale et horizontale. Les deux contributions majeures de notre travail sont: d'une part, une amélioration notable du calcul de la composante linéaire de la phase dans le cas de l'application de filtres orientés oblique et, d'autre part, une méthode originale de calcul de la phase dérivée qui évite la procédure de déballage tout en étant porteuse de l'information de phase utile. Nous avons appliqué nos algorithmes en classification et en segmentation de divers types d'images texturées.
5
Formont, Pierre. "Outils statistiques et géométriques pour la classification des images SAR polarimétriques hautement texturées." Phd thesis, Université Rennes 1, 2013. http://tel.archives-ouvertes.fr/tel-00983304.
Abstract:
Les radars à synthèse d'ouverture (Synthetic Aperture Radar ou SAR) permettent de fournir des images à très haute résolution de la surface de la Terre. Les algorithmes de classification traditionnels se basent sur une hypothèse de bruit gaussien comme modèle de signal, qui est rapidement mise en défaut lorsque l'environnement devient inhomogène ou impulsionnel, comme c'est particulièrement le cas dans les images SAR polarimétriques haute résolution, notamment au niveau des zones urbaines. L'utilisation d'un modèle de bruit composé, appelé modèle SIRV, permet de mieux prendre en compte ces phénomènes et de représenter la réalité de manière plus adéquate. Cette thèse s'emploie alors à étudier l'application et l'impact de ce modèle pour la classification des images SAR polarimétriques afin d'améliorer l'interprétation des classifications au sens de la polarimétrie et à proposer des outils adaptés à ce nouveau modèle. En effet, il apparaît rapidement que les techniques classiques utilisent en réalité beaucoup plus l'information relative à la puissance de chaque pixel plutôt qu'à la polarimétrie pour la classification. Par ailleurs, les techniques de classification traditionnelles font régulièrement appel à la moyenne de matrices de covariance, calculée comme une moyenne arithmétique. Cependant, étant donnée la nature riemannienne de l'espace des matrices de covariance, cette définition n'est pas applicable et il est nécessaire d'employer une définition plus adaptée à cette structure riemannienne. Nous mettons en évidence l'intérêt d'utiliser un modèle de bruit non gaussien sur des données réelles et nous proposons plusieurs approches pour tirer parti de l'information polarimétrique qu'il apporte. L'apport de la géométrie de l'information pour le calcul de la moyenne est de même étudié, sur des données simulées mais également sur des données réelles acquises par l'ONERA. Enfin, une étude préliminaire d'une extension de ces travaux au cas de l'imagerie hyperspectrale est proposée, de par la proximité de ce type de données avec les données SAR polarimétriques.
6
Formont, P. "Outils statistiques et géométriques pour la classification des images SAR polarimétriques hautement texturées." Phd thesis, Supélec, 2013. http://tel.archives-ouvertes.fr/tel-01020050.
Abstract:
Les radars à synthèse d'ouverture (Synthetic Aperture Radar ou SAR) permettent de fournir des images à très haute résolution de la surface de la Terre. Les algorithmes de classification traditionnels se basent sur une hypothèse de bruit gaussien comme modèle de signal, qui est rapidement mise en défaut lorsque l'environnement devient inhomogène ou impulsionnel, comme c'est particulièrement le cas dans les images SAR polarimétriques haute résolution, notamment au niveau des zones urbaines. L'utilisation d'un modèle de bruit composé, appelé modèle SIRV, permet de mieux prendre en compte ces phénomènes et de représenter la réalité de manière plus adéquate. Cette thèse s'emploie alors à étudier l'application et l'impact de ce modèle pour la classification des images SAR polarimétriques afin d'améliorer l'interprétation des classifications au sens de la polarimétrie et à proposer des outils adaptés à ce nouveau modèle. En effet, il apparaît rapidement que les techniques classiques utilisent en réalité beaucoup plus l'information relative à la puissance de chaque pixel plutôt qu'à la polarimétrie pour la classification. Par ailleurs, les techniques de classification traditionnelles font régulièrement appel à la moyenne de matrices de covariance, calculée comme une moyenne arithmétique. Cependant, étant donnée la nature riemannienne de l'espace des matrices de covariance, cette définition n'est pas applicable et il est nécessaire d'employer une définition plus adaptée à cette structure riemannienne. Nous mettons en évidence l'intérêt d'utiliser un modèle de bruit non gaussien sur des données réelles et nous proposons plusieurs approches pour tirer parti de l'information polarimétrique qu'il apporte. L'apport de la géométrie de l'information pour le calcul de la moyenne est de même étudié, sur des données simulées mais également sur des données réelles acquises par l'ONERA. Enfin, une étude préliminaire d'une extension de ces travaux au cas de l'imagerie hyperspectrale est proposée, de par la proximité de ce type de données avec les données SAR polarimétriques.
7
Joseph, Pierre. "Etude expérimentale du glissement sur surfaces lisses et texturées." Paris 6, 2005. http://www.theses.fr/2005PA066214.
8
Paulhac, Ludovic. "Outils et méthodes d'analyse d'images 3D texturées : application à la segmentation des images échographiques." Phd thesis, Université François Rabelais - Tours, 2009. http://tel.archives-ouvertes.fr/tel-00576507.
Abstract:
Le travail présenté dans cette thèse s'inscrit dans le domaine de l'analyse d'images texturées et plus particulièrement d'images 3D (ensembles de voxels). Pour ces dernières, les difficultés d'analyse sont principalement dues à la très grande quantité d'informations à prendre en compte et à traiter, ce qui rend inefficaces les méthodes dédiées aux images 2D. De plus, outre le faible nombre de travaux proposant des méthodes réellement 3D, la majeure partie des méthodes d'analyse de textures existantes n'ont pas une applicabilité très étendue et sont incapables d'identifier certaines classes de textures. En comparaison, le système visuel humain s'adapte à tous types de textures, même en présence d'un contexte défavorable. Les textures sont donc facilement discernées par l'humain, mais très difficiles à définir sous forme d'un modèle mathématique unique offrant une description purement quantitative. Partant de l'hypothèse qu'il est plus pertinent de décrire une texture avec des adjectifs qualificatifs (description qualitative) plutôt qu'avec un modèle mathématique unique, nous avons choisi dans un premier temps de définir un nouvel ensemble de descripteurs de textures permettant une caractérisation qualitative des textures contenues dans les images 3D. Il est difficile de produire une définition consensuelle du terme "texture". Néanmoins, la première contribution de cette thèse est la proposition d'un nouvel ensemble de caractéristiques de textures solides construit à partir de propriétés de textures facilement appréhendable par l'utilisateur humain. Ces nouveaux descripteurs permettent entre autres de décrire des propriétés texturales telles que la directionnalité, la rugosité et le contraste. La deuxième contribution de cette thèse correspond aux techniques multi-résolutions que nous proposons d'exploiter pour extraire ces caractéristiques des images 3D, techniques basées sur une décomposition en ondelette couplée à une analyse des composantes géométriques contenues dans les représentations obtenues. Enfin, le système de segmentation interactif d'images échographiques 3D de la peau, intégrant nos descripteurs de textures solides, couplé à un mécanisme de clustering et à une interface homme-machine adaptée constitue, selon nous, une troisième contribution. Ce système nous a permis de valider expérimentalement la robustesse et la généricité de nos propositions, et intéresse aujourd'hui de nombreux acteurs du monde de la santé (médecins, dermatologues, industriels, ...).
9
Nguyen, Tien Sy. "Extraction de structures fines sur des images texturées : application à la détection automatique de fissures sur des images de surface de chaussées." Phd thesis, Université d'Orléans, 2010. http://tel.archives-ouvertes.fr/tel-00592482.
Abstract:
La dernière décennie a vu l'exploitation d'application d'inspection automatique dans plusieurs domaines grâce à l'avancé des capteurs de vision et des méthodes d'analyse de texture et de segmentation d'images. Cependant, la nature difficile des images de chaussées (fortement texturée), la petite taille des défauts (fissures) conduisent au constat que l'inspection dans ce domaine est réalisée manuellement. Chaque année, en France, des opérateurs doivent visualiser des milliers de kilomètres d'images de route pour y relever des dégradations. Cette façon de faire est couteuse, lente et a un résultat plutôt subjectif. L'objectif de ce travail de thèse est de développer une méthode permettant la détection et la classification des fissures automatiquement sur ces images de chaussées. Le coeur de la thèse est une nouvelle méthode de segmentation, la Free Form Anisotropy (FFA). D'une part, elle permet de prendre en compte simultanément les attributs concernant la forme et l'intensité des pixels d'une fissure pour la détection. D'autre part, une nouvelle modélisation est utilisée en recherchant des chemins minima dans des graphes (images) afin de trouver la forme de la fissure dès qu'elle est présente dans l'image. Après la segmentation, l'extraction et la classification de défauts sont réalisées par une transformée de Hough et par le calcul de l'orientation locale des pixels. Les résultats expérimentaux ont été obtenus à partir de plusieurs bases d'images et compares avec des méthodes existantes.
10
Karoui, Imen. "Segmentation par méthodes markoviennes et variationnelles des images texturées : application à la caractérisation sonar des fonds marins." Télécom Bretagne, 2007. http://www.theses.fr/2007TELB0035.
Abstract:
Cette thèse s'inscrit dans la continuité des collaborations de l'Ifremer et de l'ENST-Bretagne sur le thème de l'estimation objective et automatique des caractéristiques physiques des fonds marins et la mise en place d'algorithmes de segmentation des cartographies associées. Dans cette thèse on s'attache plus particulièrement à exploiter l'information texturale présente dans des images sonar haute résolution. Ce mémoire de thèse comprend trois parties. Les deux premières concernent les domaines de l'analyse et de la segmentation des images texturées. La troisième partie présente une adaptation de ces algorithmes à la caractérisation et à la segmentation des images de fonds marins. Dans la première partie, nous caractérisons les textures par un ensemble de distributions empiriques de leurs réponses à des bancs de filtres. Nous fusionnons les descripteurs élémentaires en définissant une nouvelle mesure de similarité entre textures dans l'espace de ces attributs. Notre mesure de similarité est calculée selon une somme pondérée de divergence de Kullback-Leibler entre les attributs élémentaires de textures. Les poids sont estimés de manière à maximiser le critère de la marge globale. Selon la valeur des poids, on opère une sélection des attributs les plus pertinents que nous utilisons effectivement pour la discrimination entre textures. Dans la deuxième partie, nous utilisons cette mesure de similarité pour la segmentation supervisée et non supervisée d'images texturées. Nous proposons deux algorithmes: un algorithme "basé pixel" et formulé dans un cadre markovien et un autre "basé région" formulé dans un cadre variationnel et implanté selon la technique des ensembles de niveaux. Dans la troisième partie, nous présentons une application à la caractérisation et la cartographie des fonds marins par imagerie sonar. Nous évoquons le problème de la dépendance angulaire des attributs de texture et nous décrivons les modifications apportées aux méthodes de caractérisation et de segmentation proposées afin de tenir compte de cette variation angulaireThis work is concerned with the characterization and the segmentation of high resolution sonar images. We are interested in the texture information within these images. The report is divided into three parts. The two former parts are concerned with natural texture analysis in general. The third one presents an application to sonar image segmentation. In the first part, we describe texture by a set of empirical distribution estimated on texture responses to a set of different filters computed for different parameterizations. We fuse the contribution of the different features using a weighting scheme: we define a new similarity measure between textures, as a weighted sum of Kullback-Leibler divergence between texture features. The weights are estimated according to global margin maximization criterion. According to weight values, we select the most discriminating features. In the second part, we exploit this similarity measure to develop supervised and unsupervised segmentation algorithms. We propose two segmentation methods: one "pixel-based" method formulated in a bayesian based Markov Random Field (MRF) framework and a variational "region-based" approach implemented with the level set technique. In the third part, we present an application to the characterization and the segmentation of sonar images. We show sidescan sonar feature dependency with incidence angles and we describe the modification of our similarity measure and our segmentation algorithms to take into account the angular feature dependency
Books on the topic "Images texturées":
1
Hung, Chih-Cheng, Enmin Song, and Yihua Lan. Image Texture Analysis. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-13773-1.
2
Stoichita, Victor. Les Fileuses de Velazquez: Textes, textures, images. Paris]: Fayard, 2018.
3
Gimel’farb, Georgy L. Image Textures and Gibbs Random Fields. Dordrecht: Springer Netherlands, 1999. http://dx.doi.org/10.1007/978-94-011-4461-2.
4
Gimel'farb, Georgy L. Image Textures and Gibbs Random Fields. Dordrecht: Springer Netherlands, 1999.
5
Gimelʹfarb, Georgiĭ Lʹvovich. Image textures and Gibbs random fields. Dordrecht: Kluwer Academic Publishers, 1999.
6
Harris, David Earl. Texture analysis of skin cancer images. Ann Arbor, Mich: UMI, 1991.
7
Korn, Christopher A. Markov random field textures and applications in image processing. Monterey, Calif: Naval Postgraduate School, 1997.
8
Wood, E. J. Carpet texture measurement using image analysis. Christchurch: Wronz, 1987.
9
Spann, Michael. Texture description and segmentation in image processing. Birmingham: University of Aston. Department of Electrical and Electronic Engineering, 1985.
10
Chaki, Jyotismita, and Nilanjan Dey. Texture Feature Extraction Techniques for Image Recognition. Singapore: Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-15-0853-0.
Book chapters on the topic "Images texturées":
1
Xie, Xianghua, and Majid Mirmehdi. "Texture Exemplars for Defect Detection on Random Textures." In Pattern Recognition and Image Analysis, 404–13. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/11552499_46.
2
Magnenat-Thalmann, Nadia, and Daniel Thalmann. "Texture." In Image Synthesis, 221–46. Tokyo: Springer Japan, 1987. http://dx.doi.org/10.1007/978-4-431-68060-4_12.
3
Peters, James F. "Texture and Texture Set Patterns." In Topology of Digital Images, 301–15. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014. http://dx.doi.org/10.1007/978-3-642-53845-2_11.
4
Tomita, Fumiaki, and Saburo Tsuji. "Image Segmentation." In Computer Analysis of Visual Textures, 37–55. Boston, MA: Springer US, 1990. http://dx.doi.org/10.1007/978-1-4613-1553-7_3.
5
Jähne, Bernd. "Texture." In Digital Image Processing, 185–92. Berlin, Heidelberg: Springer Berlin Heidelberg, 1991. http://dx.doi.org/10.1007/978-3-662-11565-7_9.
6
Jähne, Bernd. "Texture." In Digital Image Processing, 185–92. Berlin, Heidelberg: Springer Berlin Heidelberg, 1993. http://dx.doi.org/10.1007/978-3-662-21817-4_9.
7
Jähne, Bernd. "Texture." In Digital Image Processing, 413–24. Berlin, Heidelberg: Springer Berlin Heidelberg, 2002. http://dx.doi.org/10.1007/978-3-662-04781-1_15.
8
Jähne, Bernd. "Texture." In Digital Image Processing, 383–94. Berlin, Heidelberg: Springer Berlin Heidelberg, 1997. http://dx.doi.org/10.1007/978-3-662-03477-4_12.
9
Jähne, Bernd. "Texture." In Digital Image Processing, 185–92. Berlin, Heidelberg: Springer Berlin Heidelberg, 1995. http://dx.doi.org/10.1007/978-3-662-03174-2_9.
10
Kinser, Jason M. "Texture Recognition." In Image Operators, 221–42. First edition. | Boca Raton, FL: CRC Press/Taylor & Francis Group, [2019] |: CRC Press, 2018. http://dx.doi.org/10.1201/9780429451188-16.
Conference papers on the topic "Images texturées":
1
Sanzharov, Vadim Vladimirovich, and Vladimir Alexandrovich Frolov. "Viewpoint Selection for Texture Reconstruction with Inverse Rendering." In 33rd International Conference on Computer Graphics and Vision. Keldysh Institute of Applied Mathematics, 2023. http://dx.doi.org/10.20948/graphicon-2023-66-77.
Abstract:
Viewpoint selection methods have a variety of applications in different fields of computer graphics and computer vision, including shape retrieval, scientific visualization, image-based modeling and others. In this paper we investigate the applicability of existing viewpoint selection methods to the problem of textures reconstruction using inverse rendering. First, we use forward rendering to produce path-traced images of a textured object. Then we apply different view quality metrics to select a set of images for texture reconstruction. Finally, we perform material and texture reconstruction using these image sets and evaluate the quality of the results. We show that using viewpoint selection methods allows to achieve faster inverse rendering times while maintaining quality of the results.
2
Kimura, Soichiro, Kensuke Tobitani, and Noriko Nagata. "BTF Prediction Model using Unsupervised Learning." In 8th International Conference on Control, Modeling and Computing (CMC 2022). Academy and Industry Research Collaboration Center (AIRCC), 2022. http://dx.doi.org/10.5121/csit.2022.120505.
Abstract:
The impressions evoked by textures are called affective textures, and are considered to be important in evaluating and judging the quality of an object. And, technologies for understanding and controlling sensory textures are needed in product design. In this study, we propose a BTF prediction method using DNN as a first attempt to generate textures based on affective texture recognition. The method uses a series of continuously varying viewpoint angles of a texture image as the input signal. This method enables the generation of texture images with continuously changing angles. We tested the validity of the proposed method by using textile, wood and paper. The results show that the proposed method is effective for predicting diffuse reflection optical properties and irregular and regular patterns.
3
Turner, Mark R. "Gabor functions and textural segmentation." In OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1985. http://dx.doi.org/10.1364/oam.1985.wj38.
Abstract:
This paper investigates the applicability of Gabor functions to textural segmentation. Gabor functions are sinusoidal plane waves in 2-D Gaussian envelopes. The choice of parameters characterizing the geometry of an individual Gabor function affects its spatial extent as well as orientation and spatial frequency tuning. Daugman has indicated that these functions belong to a class of filters having optimal joint resolution in the 2-D space and 2-D frequency domains. They are, therefore, appropriate filter choices for tasks which require selective measurement in these domains. Textural segmentation appears to be one of those tasks. A set of Gabor functions of different frequencies and orientations is applied by computer program to images containing regions of different texture. This process produces a kind of localized and orientation selective frequency spectrum of various fields in the image. The program then attempts to delineate the boundaries of the textured regions by identifying spectrum differences between these fields. Gabor functions are effective in distinguishing between many of the textures used in psychophysical studies differing in first- or second-order statistics. Additional textures in which the difference is related to some aspect of the collinearity of the texture elements have also been tried with promising results.
4
Aloimonos, John (Yannis), and Paul Chou. "Detection of surface orientation from texture." In OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1985. http://dx.doi.org/10.1364/oam.1985.ww1.
Abstract:
Texture density depends on both the orientation and the depth of the textured plane in view. Previous approaches stated that because of this fact (i.e., density depends on both scaling and foreshortening), density cannot be used to recover surface orientation under perspective projection. In this paper we prove that these two effects (scaling and foreshortening) can be separated and so texture density can be used to uniquely recover surface orientation. We present algorithms that are based on strong (texels) and weak (edges) segmentation. Experimental results on natural images, based on the Gibsonian uniform density assumption, are very good; these images include grass fields, gravel paths, brick walls, aerial photographs of towns or parking lots, ocean waves, man-made artificial texture (cloth, carpet, etc.). Our algorithms first preprocess the image to find texels (and if this is not possible, to find edges) and then using the assumption that the texture-elements are uniformly distributed on the world plane (Gibson), they recover its orientation. An extension of our theory to curved surfaces is also discussed.
5
Quediman, Barbara, Enrique Estrada, Radompon Sungkorn, and Jonas Toelke. "BHI Logs and ML Automated Pre-Salt Carbonate: Texture Recognition and Petrophysical Properties Propagation Using Image Log, Core Images and Porosity-Permeability From Plugs." In 2022 SPWLA 63rd Annual Symposium. Society of Petrophysicists and Well Log Analysts, 2022. http://dx.doi.org/10.30632/spwla-2022-0095.
Abstract:
Identifying depositional facies and diagenetic modifications from BHI logs in sections without core is challenging due to heterogeneities in fabric of the carbonaceous rock, which are below the resolution of the BHI logs in these complex reservoirs. This is mainly due to different diagenetic processes resulting in different types of reservoir rocks (RRTs) with different petrophysical properties in the same geological facies. This work describes an innovative new workflow that uses a deep learning model to identify heterogeneities of fabric (textures) in complex carbonate reservoirs in sections without core; as input we use conventional (gamma ray, density, neutron, sonic), NMR, BHI (acoustic imaging) logs, core CT images and physical porosity and permeability measurements from plugs. This new workflow combines supervised deep learning and unsupervised machine learning methods, consisting of four steps: (1) Identification of textures in Core CT (2) Calibration of features of BHI logs in core section (3) Training a deep learning model with cropped images from BHI logs to extract texture curves (4) train a machine learning regression model with texture curves, WL logs and plug porosity and permeability values to propagate prediction of textures, porosity and permeability along the well. The texture curves generated by the ML model are in good match with the recognized core section textures (CT Images). The results show that the NMR Total Porosity has a good correlation with the porosity predicted by the regression model. In addition, the petrophysical data from plugs measured in the laboratory show a good match with the porosity and permeability predicted in the core zone. In the non-core zone, the predicted textures by the ML model relate to the heterogeneities of the carbonaceous rock fabric and the propagation of the petrophysical properties have good correlation with the predicted textures. In some cases, vuggy porosity combined with fractures do not allow correct porosity measurement with NMR or density tools due to the sensitivity of these tools to poor borehole conditions. In these cases, the NMR presents a fast relaxation of the T2 distribution due to the heterogeneity of these carbonaceous fabric and therefore the porosity and permeability measurements will be affected. The ML model uses CT Textures to calibrate BHI Crops in the core section zone and NMR and Basic logs as input, improving the recognition of the textural heterogeneities and refine the traditional Rock typing of these complex Pre-Salt carbonate reservoirs.
6
Shi, Jingang, Yusi Wang, Songlin Dong, Xiaopeng Hong, Zitong Yu, Fei Wang, Changxin Wang, and Yihong Gong. "IDPT: Interconnected Dual Pyramid Transformer for Face Super-Resolution." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/182.
Abstract:
Face Super-resolution (FSR) task works for generating high-resolution (HR) face images from the corresponding low-resolution (LR) inputs, which has received a lot of attentions because of the wide application prospects. However, due to the diversity of facial texture and the difficulty of reconstructing detailed content from degraded images, FSR technology is still far away from being solved. In this paper, we propose a novel and effective face super-resolution framework based on Transformer, namely Interconnected Dual Pyramid Transformer (IDPT). Instead of straightly stacking cascaded feature reconstruction blocks, the proposed IDPT designs the pyramid encoder/decoder Transformer architecture to extract coarse and detailed facial textures respectively, while the relationship between the dual pyramid Transformers is further explored by a bottom pyramid feature extractor. The pyramid encoder/decoder structure is devised to adapt various characteristics of textures in different spatial spaces hierarchically. A novel fusing modulation module is inserted in each spatial layer to guide the refinement of detailed texture by the corresponding coarse texture, while fusing the shallow-layer coarse feature and corresponding deep-layer detailed feature simultaneously. Extensive experiments and visualizations on various datasets demonstrate the superiority of the proposed method for face super-resolution tasks.
7
Silva, Daniel, and Romuere Silva. "Evaluation of Texture Maps as Input to Extract Deep Features in Glaucoma Diagnosis." In Encontro Nacional de Inteligência Artificial e Computacional. Sociedade Brasileira de Computação - SBC, 2020. http://dx.doi.org/10.5753/eniac.2020.12151.
Abstract:
Glaucoma is a significant cause of blindness in the world. Doctors use computerized images to detect these diseases. Early detection of the disease increases the chances of treatment, reducing the adverse effects. This work proposes an evaluation of texture maps combinations as input to Convolutional Neural Networks for glaucoma classification in retinal images. In our experiments, we used three textures maps, three CNN architectures, and three classifiers. We achieve a Kappa =0.708±0.054 and a Accuracy = 0.859±0.021. We conclude that using the combination of texture maps can improve the automatic detection of glaucoma compared to single-channel inputs, and could be used by state-of-the-art methods to improve their classification rates.
8
Domash, Lawrence, Vincent Ryan, and Parviz Tayebati. "Optical processing of fractal images." In OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1992. http://dx.doi.org/10.1364/oam.1992.thqq3.
Abstract:
Fractal textures occur in natural scenary or satellite images (clouds, ocean waves). However, processing of fractal image data to extract measurements such as fractal dimension is highly computation-intensive when serial digital methods are used. Massively parallel nonlinear optical processing methods are proposed to characterize fractal images in real time. A photorefractive real time image processor performing a combined convolution/correlation operation is used to measure the correlation dimension of sample fractal patterns. The optical algorithm employs an image autocorrelation performed simultaneously with an optical convolution by using a spatially multiplexed array of 9–100 discs of various radii setting a range of scales. A digital neural network in the correlation plane evaluates the maximum intensity in each light patch and computes the fractal dimension. By placing phase screens or window functions in the third port, additional fractal analyses may be accomplished, including iterated function system encoding. Double convolution involving two different images and a kernel provides scale sensitive image comparison, closely related to wavelet analysis. Real time nonlinear optical coprocessing appears useful in several different approaches to characterization of fractal imagery. Preliminary experimental results will be presented.
9
Turner, Mark R. "Local spectral analysis of texture gradients." In OSA Annual Meeting. Washington, D.C.: Optica Publishing Group, 1989. http://dx.doi.org/10.1364/oam.1989.tuu28.
Abstract:
The perspective image of an obliquely inclined textured surface exhibits shape and density distortions of texture elements. These distortions also systematically shift the projection of the spatial frequencies of which the texture is comprised. Using a set of filters with suitable spatial frequency and orientation resolution, the inclination angle of many textured surfaces may be estimated from these frequency shifts. An algorithm has been developed which uses the amplitude distributions of 2-D Gabor filters to perform this calculation on planar surfaces. The algorithm may be viewed as operating in parallel on a number of patches of the image and consolidating a global inclination value of lateral propagation of local inclination estimates between regions.
10
Yang, S., Y. Wang, and C. Shrivastava. "Sedimentary Analysis Via Automatic Image Segmentation and Clustering with the LWD OBM Resistivity Image: A Case Study from Gulf of Mexico." In SPE Annual Technical Conference and Exhibition. SPE, 2023. http://dx.doi.org/10.2118/214908-ms.
Abstract:
Abstract Microfacies analysis is the first step for depositional environment interpretation and sand body prediction. Textural details from borehole images are building blocks for facies analysis, representing different paleo sediimentation conditions. Associated workflows have been applied on high resolution borehole images by geologists and log analysts manually. Automation via machine learning solutions provides an opportunity to improve the working efficiency and accuracy. Such an approach has given satisfactory results with post-drilling wireline images. In this paper, the improved workflow for sedimentary analysis was applied and validated with a logging-while-drilling (LWD) resistivity imager in oil-based mud environment (OBM). The OBM LWD resistivity image in oil-based mud provides 72 data points at single depth from 4 different frequencies of electromagnetic measurements with a patented processing. The non-gap resistivity image gives more confident texture characterization. The continuous histogram and correlogram derived from image data were used for image segmentation. In each image segmentation, multiple vector properties were extracted from image data representing different texture features including adoptive variogram horizontally. Agglomerative clustering was selected for its stability and repeatability. The internally built dendrogram allows to automatically determine the number of clusters by finding a stable distance between the clusters’ hierarchy branches. In addition to the features extracted from image data, optional petrophysical logs with variable weights may be fed to the algorithm for a better classification. A case study from Gulf of Mexico is being used to demonstrate this workflow with Hi-Res LWD image. More than 10 different sedimentary geometries were classified automatically from image and petrophysical logs. The microfacies were named manually from sedimentary geometries with the related geological concept accordingly. The fluvial channel and delta sedimentary environment were interpretated finally from microfacies association. The interpretation results were compared and validated with published dips-based solution as well. This is the first time for the automatic borehole image segmentation with LWD OBM images. The working efficiency was improved a lot through this workflow and the accuracy of microfacies interpretation was guaranteed by machine learning solution.
Reports on the topic "Images texturées":
1
Alhasan, Ahmad, Brian Moon, Doug Steele, Hyung Lee, and Abu Sufian. Chip Seal Quality Assurance Using Percent Embedment. Illinois Center for Transportation, December 2023. http://dx.doi.org/10.36501/0197-9191/23-029.
Abstract:
This study investigates the use of macrotexture as an indicator of the percent embedment (PE) of aggregate in a chip seal and ultimately, as a quality assurance tool for chip seals. The study included an extensive field- and controlled-testing program from 24 chip seal sections constructed in Illinois. Surface texture measurements were acquired using a high-speed texture profiler and a stationary laser texture device. The analysis showed that stationary texture measurements were more consistent and reliable for estimating PE and characterizing chip seals in the field. Moreover, the ground truth PE values were estimated using an image analysis algorithm implemented on side-view images of cores extracted in the field. The ground truth PE values were estimated using four approaches: the average elevation method, percent embedment of each aggregate method, the peak method, and the aggregate circumference method. The analysis showed that the correlations between the different PE estimation methods are relatively weak, indicating the various methods provide different information and may relate to different characteristics. The general regression models for PE values estimated using the average elevation method and the mean profile depth (MPD) acquired using laser texture scans and the average least dimension (ALD) yielded the highest R2 value of 0.50. The model showed a consistent decreasing trend between PE and MPD estimated using laser texture scans and side-view images. Moreover, the model matched the expected behavior that PE should reach 100% as MPD reaches 0. Finally, four models were recommended correlating PE estimated using the average elevation and each aggregate methods to the MPD (mm) estimated from laser texture scans and ALD (mm) estimated from side-view images.
2
McKay, Paul, and C. A. Blain. An Automated Approach to Extracting River Bank Locations from Aerial Imagery Using Image Texture. Fort Belvoir, VA: Defense Technical Information Center, January 2013. http://dx.doi.org/10.21236/ada609737.
3
LaCascia, Marco, John Isidoro, and Stan Sclaroff. Head Tracking via Robust Registration in Texture Map Images. Fort Belvoir, VA: Defense Technical Information Center, August 1998. http://dx.doi.org/10.21236/ada366993.
4
Carasso, Alfred S. Singular integrals, image smoothness, and the recovery of texture in image deblurring. Gaithersburg, MD: National Institute of Standards and Technology, 2003. http://dx.doi.org/10.6028/nist.ir.7005.
5
Wendelberger, James G. Localized Similar Image Texture in Images of Sample Laser Confocal Microscope for Area: FY15 DE07 SW C1 Zone 1 & 2 Section b. Office of Scientific and Technical Information (OSTI), February 2019. http://dx.doi.org/10.2172/1496724.
6
Gletsos, M., S. G. Mougiakakou, G. K. Matsopoulos, K. S. Nikita, and D. Kelekis. Classification of Hepatic Lesions From CT Images Using Texture Features and Neural Networks. Fort Belvoir, VA: Defense Technical Information Center, October 2001. http://dx.doi.org/10.21236/ada412422.
7
Pe-Piper, G., D. J W Piper, J. Nagle, and P. Opra. Petrography of bedrock and ice-rafted granules: Flemish Cap, offshore Newfoundland and Labrador. Natural Resources Canada/CMSS/Information Management, 2022. http://dx.doi.org/10.4095/331224.
Abstract:
This Open File report provides petrographic information from a scanning electron microscope study of granules and small pebbles in four selected trawl samples from Flemish Cap. The mineral composition of the granules was determined by energy dispersive spectroscopy (EDS) and textures are shown in backscattered electron images (BSE). It complements Open File 8359 on the heavy mineral assemblage on Flemish Cap. Granules on the central shoals appear to be derived from outcropping Avalonian basement; those to the east and west are predominantly ice-rafted in origin. These data improve our understanding of the source of the voluminous sands on Flemish Cap and the characteristics of the Avalonian basement rocks on southern Flemish Cap.
8
Du, Li-Jen. Segmentation of Synthetic Aperture Radar (SAR) Images of Ocean Surface by the Texture Energy Transform Method. Fort Belvoir, VA: Defense Technical Information Center, August 1988. http://dx.doi.org/10.21236/ada199536.
9
Andrawes, Bassem, Ernesto Perez Claros, and Zige Zhang. Bond Characteristics and Experimental Behavior of Textured Epoxy-coated Rebars Used in Concrete Bridge Decks. Illinois Center for Transportation, January 2022. http://dx.doi.org/10.36501/0197-9191/22-001.
Abstract:
The deterioration of bridge decks is a problem typically associated with the corrosion of the reinforcing steel. This issue was partially controlled during the 1970s with the incorporation of the epoxy-coating protection system. However, research later demonstrated that the smooth surface resulting from the epoxy-coating application reduces most of the friction between the rebar and the surrounding concrete. Consequently, forces acting on the rib faces are reconfigured in such a way that the radial components increase, triggering the early development of cracks. To mitigate both the reduction of bonding and the formation of cracks, the Illinois Department of Transportation proposed a new type of coated bars: textured epoxy-coated (TEC) bars. Over the last few years, different projects have been executed to understand and improve the characteristics of TEC rebars. This report is a continuation of research performed at the University of Illinois Urbana-Champaign to evaluate the bond behavior of TEC bars. The experimental program starts by characterizing, qualitatively and quantitatively, the roughness of the TEC rebars. Next, their bond-slip interaction embedded in concrete is evaluated through pull-out tests. Finite element models of these tests are developed to validate the behavior observed as the textured reinforcement loses anchorage with concrete. Based on these results, the experimental program then aims to study the impact of the drying shrinkage, temperature change, and flexural demands on two large-scale bridge deck specimens reinforced, individually, with TEC and standard epoxy-coated bars. The results collected from both specimens using digital image correlation and strain gauges are compared to explore the differences exhibited by the traditional and the new type of reinforcement coatings in terms of stress distribution in bridge decks. Finally, given the specialized equipment and time-consuming procedure needed to calculate the roughness parameters of TEC bars, an empirical, weight-based approach is developed as a rapid method for assessing the rebars’ roughness on-site.
10
King, E. L., A. Normandeau, T. Carson, P. Fraser, C. Staniforth, A. Limoges, B. MacDonald, F. J. Murrillo-Perez, and N. Van Nieuwenhove. Pockmarks, a paleo fluid efflux event, glacial meltwater channels, sponge colonies, and trawling impacts in Emerald Basin, Scotian Shelf: autonomous underwater vehicle surveys, William Kennedy 2022011 cruise report. Natural Resources Canada/CMSS/Information Management, 2022. http://dx.doi.org/10.4095/331174.
Abstract:
A short but productive cruise aboard RV William Kennedy tested various new field equipment near Halifax (port of departure and return) but also in areas that could also benefit science understanding. The GSC-A Gavia Autonomous Underwater Vehicle equipped with bathymetric, sidescan and sub-bottom profiler was successfully deployed for the first time on Scotian Shelf science targets. It surveyed three small areas: two across known benthic sponge, Vazella (Russian Hat) within a DFO-directed trawling closure area on the SE flank of Sambro Bank, bordering Emerald Basin, and one across known pockmarks, eroded cone-shaped depression in soft mud due to fluid efflux. The sponge study sites (~ 150 170 m water depth) were known to lie in an area of till (subglacial diamict) exposure at the seabed. The AUV data identified gravel and cobble-rich seabed, registering individual clasts at 35 cm gridded resolution. A subtle variation in seabed texture is recognized in sidescan images, from cobble-rich on ridge crests and flanks, to limited mud-rich sediment in intervening troughs. Correlation between seabed topography and texture with the (previously collected) Vazella distribution along two transects is not straightforward. However there may be a preference for the sponge in the depressions, some of which have a thin but possibly ephemeral sediment cover. Both sponge study sites depict a hereto unknown morphology, carved in glacial deposits, consisting of a series of discontinuous ridges interpreted to be generated by erosion in multiple, continuous, meandering and cross-cutting channels. The morphology is identical to glacial Nye, or mp;lt;"N-mp;lt;"channels, cut by sub-glacial meltwater. However their scale (10 to 100 times mp;lt;"typicalmp;gt;" N-channels) and the unique eroded medium, (till rather than bedrock), presents a rare or unknown size and medium and suggests a continuum in sub-glacial meltwater channels between much larger tunnel valleys, common to the eastward, and the bedrock forms. A comparison is made with coastal Nova Scotia forms in bedrock. The Emerald Basin AUV site, targeting pockmarks was in ~260 to 270 m water depth and imaged eight large and one small pockmark. The main aim was to investigate possible recent or continuous fluid flux activity in light of ocean acidification or greenhouse gas contribution; most accounts to date suggested inactivity. While a lack of common attributes marking activity is confirmed, creep or rotational flank failure is recognized, as is a depletion of buried diffuse methane immediately below the seabed features. Discovery of a second, buried, pockmark horizon, with smaller but more numerous erosive cones and no spatial correlation to the buried diffuse gas or the seabed pockmarks, indicates a paleo-event of fluid or gas efflux; general timing and possible mechanisms are suggested. The basinal survey also registered numerous otter board trawl marks cutting the surficial mud from past fishing activity. The AUV data present a unique dataset for follow-up quantification of the disturbance. Recent realization that this may play a significant role in ocean acidification on a global scale can benefit from such disturbance quantification. The new pole-mounted sub-bottom profiler collected high quality data, enabling correlation of recently recognized till ridges exposed at the seabed as they become buried across the flank and base of the basin. These, along with the Nye channels, will help reconstruct glacial behavior and flow patterns which to date are only vaguely documented. Several cores provide the potential for stratigraphic dating of key horizons and will augment Holocene environmental history investigations by a Dalhousie University student. In summary, several unique features have been identified, providing sufficient field data for further compilation, analysis and follow-up publications.