Gestion des informations dans les premieres etapes de la vision par ordinateur. (Information management in the first stages of computer vision)

Dans le cadre de la vision par ordinateur, la facon d'aborder les problemes est delicate. En ce qui concerne la detection des premiers indices visuels, tels que les contours ou les regions, l'approche theorique est difficile, car le but n'est pas clairement defini. Notre approche consiste a avancer pas a pas vers une solution satisfaisante en nous preoccupant essentiellement de la gestion des informations pour traduire une expertise humaine. Nous proposons des principes simples pour une gestion efficace des informations, tels que l'accumulation des informations, leur complementarite, leur "objectivite" et leur "liberte" de mouvement. Ces principes mettent en avant les problemes de controle, d'adaptation au contexte local et l'organisation de l'algorithme. Une structure de controle incrementale nous semble particulierement efficace pour mettre en oeuvre nos principes et preparer une strategie heuristique. Ainsi, en "copiant" notre expertise, nous avons realise un nouveau detecteur de contours avec seuillage adaptatif dont les resultats nous paraissent meilleurs que ceux obtenus avec des detecteurs classiques sur de nombreuses images. Ce detecteur ne necessite l'utilisation d'aucun seuil et detecte a la fois les contours de type "marche" et les contours de type "trait". Nous proposons egalement un algorithme de cooperation entre un processus de croissance de region par agregation de pixels et notre detecteur de contours. Comparee a d'autres techniques de cooperation, notre structure de controle est beaucoup plus souple, la gestion des informations ayant ete etudiee pour obtenir au moment opportun, a l'endroit desire, les informations complementaires permettant un meilleur controle de la decision. Il reste toutefois a parfaire notre cooperation en exploitant plus d'informations, en particulier au niveau de la forme des regions generees. Notre conclusion est que la segmentation souffre peut-etre d'une modelisation trop restrictive. Pour progresser dans ce domaine, il faut sans doute aborder les problemes differemment.

[1]  C. Garbay,et al.  A new paradigm for segmentation , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[2]  Takashi Matsuyama.  Expert systems for image processing: Knowledge-based composition of image analysis processes , 1989, Comput. Vis. Graph. Image Process..

[3]  Sang Uk Lee,et al.  A comparative performance study of several global thresholding techniques for segmentation , 1990, Comput. Vis. Graph. Image Process..

[4]  Ling-Hwei Chen.  A two-phase area-level line/edge detector , 1992, Pattern Recognit..

[5]  Theodosios Pavlidis,et al.  Picture Segmentation by a Tree Traversal Algorithm , 1976, JACM.

[6]  M. Nagao,et al.  Edge preserving smoothing , 1979 .

[7]  Harry Wechsler,et al.  Finding the rib cage in chest radiographs , 1977, Pattern Recognit..

[8]  Azriel Rosenfeld,et al.  A Threshold Selection Technique , 1974, IEEE Transactions on Computers.

[9]  S. Grossberg.  How does a brain build a cognitive code , 1980 .

[10]  Robert Bergevin,et al.  Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Harry G. Barrow,et al.  Experiments in Interpretation-Guided Segmentation , 1977, Artificial Intelligence.

[12]  Robert M. Haralick,et al.  Context dependent edge detection , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Ingemar J. Cox,et al.  Line recognition , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[14]  Jun Shen,et al.  An optimal linear operator for step edge detection , 1992, CVGIP Graph. Model. Image Process..

[15]  Amlan Kundu.  Robust edge detection , 1990, Pattern Recognit..

[16]  Jake K. Aggarwal,et al.  The integration of region and edge-based segmentation , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[17]  John P. McDermott,et al.  Rule-Based Interpretation of Aerial Imagery , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Irvin Sobel,et al.  Neighborhood coding of binary images for fast contour following and general binary array processing , 1978 .

[19]  Margaret M. Fleck.  Multiple widths yield reliable finite differences , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[20]  Theodosios Pavlidis,et al.  Why progress in machine vision is so slow , 1992, Pattern Recognit. Lett..

[21]  Theodosios Pavlidis,et al.  Integrating Region Growing and Edge Detection , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Michael A. Arbib,et al.  Computational Techniques in the Visual Segmentation of Static Scenes. , 1977 .

[23]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[24]  Alberto Martelli,et al.  An application of heuristic search methods to edge and contour detection , 1976, CACM.

[25]  Fredrik Bergholm,et al.  Edge Focusing , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  King-Sun Fu,et al.  A survey on image segmentation , 1981, Pattern Recognit..

[27]  Catherine Garbay,et al.  KISS: a multiagent segmentation system , 1993 .

[28]  Kathryn T. Spoehr,et al.  Visual Information Processing , 1982 .

[29]  Kannan,et al.  ON IMAGE SEGMENTATION TECHNIQUES , 2022 .

[30]  Jean-Marc Chassery,et al.  An Iterative Segmentation Method Based on a Contextual Color and Shape Criterion , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Irving Biederman,et al.  Human image understanding: Recent research and a theory , 1985, Comput. Vis. Graph. Image Process..

[33]  Véronique Clément.  Raisonnements cognitifs appliqués au pilotage d'algorithmes de traitement d'images , 1990 .

[34]  Walter D. Fisher.  On Grouping for Maximum Homogeneity , 1958 .

[35]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[36]  R A Kirsch,et al.  Computer determination of the constituent structure of biological images. , 1971, Computers and biomedical research, an international journal.

[37]  Katsushi Ikeuchi,et al.  Generating an interpretation tree from a CAD model for 3D-object recognition in bin-picking tasks , 1987, International Journal of Computer Vision.

[38]  Tomaso A. Poggio,et al.  On Edge Detection , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  David Malah,et al.  A study of edge detection algorithms , 1982, Comput. Graph. Image Process..

[40]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[41]  Takashi Matsuyama,et al.  SIGMA: A Framework for Image Understanding - Integration of Bottom-Up and Top-Down Analysis , 1985, IJCAI.

[42]  Robert M. Haralick,et al.  Digital Step Edges from Zero Crossing of Second Directional Derivatives , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Jitendra Malik,et al.  Detecting and localizing edges composed of steps, peaks and roofs , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[44]  Donald Geman,et al.  Boundary Detection by Constrained Optimization , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[46]  D H Hubel,et al.  Brain mechanisms of vision. , 1979, Scientific American.

[47]  Joan S. Weszka,et al.  A survey of threshold selection techniques , 1978 .

[48]  M. K. Khan,et al.  Machine identification of human faces , 1981, Pattern Recognition.

[49]  Claude L. Fennema,et al.  Scene Analysis Using Regions , 1970, Artif. Intell..

[50]  Keith Price,et al.  Picture Segmentation Using a Recursive Region Splitting Method , 1998 .

[51]  J. M. Chassery,et al.  Edge-region segmentation process based on generalized Voronoi diagram representation , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[52]  Vincent Torre,et al.  Localization and Noise in Edge Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[53]  Robert M. Haralick,et al.  Gradient threshold selection using the facet model , 1988, Pattern Recognit..

[54]  John F. Haddon,et al.  Generalised threshold selection for edge detection , 1988, Pattern Recognit..

[55]  Osamu Nakamura,et al.  Identification of human faces based on isodensity maps , 1991, Pattern Recognit..

[56]  Margaret M. Fleck.  Some Defects in Finite-Difference Edge Finders , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[57]  Ferdi van der Heijden,et al.  Evaluation of edge detectors using average risk , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[58]  Martin D. Levine,et al.  Low Level Image Segmentation: An Expert System , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[59]  S. Grossberg.  Cortical dynamics of three-dimensional form, color, and brightness perception: I. Monocular theory , 1987, Perception & psychophysics.