An optimization approach for using contextual information in computer vision

Local parallel processes are a very efficient way of using contextual information in a very large class of problems commonly encountered in Computer Vision. An approach to the design and analysis of such processes based on the minimization of a global criterion by local computation is presented.

[1]  Olivier D. Faugeras,et al.  Semantic Description of Aerial Images Using Stochastic Labeling , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  M. Mesarovic,et al.  Theory of Hierarchical, Multilevel, Systems , 1970 .

[3]  Marc Berthod,et al.  Scene labeling: an optimization approach , 1980, Pattern Recognit..

[4]  Azriel Rosenfeld,et al.  Cooperating Processes for Low-Level Vision: A Survey , 1981, Artif. Intell..

[5]  Jacques-Louis Lions,et al.  Sur les méthodes numériques en sciences physiques et économiques , 1974 .

[6]  C. Grobstein,et al.  Levels and ontogeny. , 1962, American scientist.

[7]  Olivier D. Faugeras,et al.  Using Context in the Global Recognition of a Set of Objects: An Optimization Approach , 1980, IFIP Congress.

[8]  Olivier D. Faugeras.  Decomposition and decentralization techniques in relaxation labeling , 1981 .

[9]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[10]  D. F. Bradley.  Multilevel Systems and Biology—View of a Submolecular Biologist , 1968 .

[11]  Shimon Ullman,et al.  Relaxation and constrained optimization by local processes , 1979 .

[12]  J M Tenenbaum,et al.  MSYS: A System for Reasoning About Scenes. , 1975 .

[13]  M. Polanyi.  Life's irreducible structure. Live mechanisms and information in DNA are boundary conditions with a sequence of boundaries above them. , 1968, Science.

[14]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  Olivier D. Faugeras,et al.  Improving Consistency and Reducing Ambiguity in Stochastic Labeling: An Optimization Approach , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.