Une approche incrémentale à base de processus coopératifs et adaptatifs pour la segmentation des images en niveaux de gris. (An incremental approach based on cooperative and adaptive processes for grey level image segmentation)

Un des objectifs de la vision par ordinateur consiste a extraire a partir d'un important volume de donnees brutes issues des images, celles qui s'avereront pertinentes pour une exploitation ulterieure. Les primitives extraites de l'image sont communement de type contour, correspondant a des zones de transition objectivement visibles, et de type region, correspondant a des regroupements de pixels de l'image avec des caracteristiques d'homogeneite communes. Une necessaire gestion de l'information est obtenue par la repartition de la tâche de segmentation au sein d'entites independantes, localisees de facon precise dans l'image, possedant chacune une primitive particuliere a segmenter de type contour ou region, et construisant ces objets de maniere incrementale, c'est-a-dire pixel par pixel. L'originalite de l'approche reside dans la cooperation instauree entre la construction des contours et des regions. Les deux types de segmenteurs fonctionnent conjointement a l'etiquetage des pixels de l'image, sous une forme pseudo-parallele, en tirant avantage de leurs atouts reciproques. Un detecteur de contour instancie de nouveaux detecteurs de regions de part et d'autre de son extremite en construction, afin de valider son existence, tandis qu'un detecteur de regions instancie des detecteurs de contours a sa frontiere, afin de borner son expansion. L'ensemble constitue un arbre d'entites de segmentation cooperantes, dependant chacune les unes des autres, par filiation. Une telle approche permet une forte adaptation locale, puisque chaque primitive est detectee par une instance d'un detecteur generique, pouvant modifier ses parametres internes independamment des autres instances. La cooperation est reelle, puisqu'elle est integree au mecanisme de decision. L'implantation d'un sequenceur de tâches anonymes, permet enfin de simuler le pseudo-parallelisme, et repose grandement sur des mecanismes classiques reserves generalement au domaine des systemes d'exploitation.

[1]  Hsun K. Liu,et al.  Two and three dimensional boundary detection , 1977 .

[2]  Marco Padula,et al.  Anthropocentric data management: a medical case , 1994 .

[3]  Herbert Freeman,et al.  Determining the minimum-area encasing rectangle for an arbitrary closed curve , 1975, CACM.

[4]  Pepe Siy,et al.  Forward/Backward Contour Tracing with Feedback , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[6]  Jean-Michel Jolion,et al.  Regions growing with the stochastic pyramid: Application in landscape ecology , 1996, Pattern Recognit..

[7]  Raymond Reiter,et al.  A Logical Framework for Depiction and Image Interpretation , 1989, Artif. Intell..

[8]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

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

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

[11]  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,.

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

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

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

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

[16]  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,.

[17]  David L. Milgram,et al.  Region extraction using convergent evidence , 1979 .

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

[19]  Carl Hewitt,et al.  Viewing Control Structures as Patterns of Passing Messages , 1977, Artif. Intell..

[20]  Catherine GarbayGroupe Visia,et al.  Evaluation of Edge Detectors: Critics and Proposal , 1996 .

[21]  Rodney A. Brooks,et al.  Integrated systems based on behaviors , 1991, SGAR.

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

[23]  Piero Mussio,et al.  Cooperative Visual Environments for the Design of Effective Visual Systems , 1993, J. Vis. Lang. Comput..

[24]  Stephen R. Bourne The Unix System , 1982 .

[25]  Aravaipa Canyon Basin,et al.  Volume 3 , 2012, Journal of Diabetes Investigation.

[26]  Dominique Barba,et al.  Image segmentation by region-contour cooperation for image coding , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[27]  Yu Xiaohan,et al.  Image segmentation combining region growing and edge detection , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[28]  Randall Davis,et al.  Negotiation as a Metaphor for Distributed Problem Solving , 1988, Artificial Intelligence.

[29]  TING-CHUEN PONG,et al.  Experiments in segmentation using a facet model region grower , 1984, Comput. Vis. Graph. Image Process..

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

[31]  Jake K. Aggarwal,et al.  The Integration of Image Segmentation Maps using Region and Edge Information , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Barbara Hayes-Roth,et al.  A Blackboard Architecture for Control , 1985, Artif. Intell..

[33]  Sacha Krakowiak PRINCIPES DES SYSTEMES D'EXPLOITATION DES ORDINATEURS , 1987 .

[34]  Luc Steels,et al.  Cooperation between distributed agents through self-organisation , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[35]  Ronald W. Schafer,et al.  Multilevel thresholding using edge matching , 1988, Comput. Vis. Graph. Image Process..

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

[37]  Victor R. Lesser,et al.  The Use of Meta-Level Control for Coordination in a Distributed Problem Solving Network , 1983, IJCAI.

[38]  John F. Haddon,et al.  Image Segmentation by Unifying Region and Boundary Information , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Theodosios Pavlidis,et al.  Integrating region growing and edge detection , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.