The Community for Technology Leaders
Green Image
Issue No. 04 - April (1981 vol. 3)
ISSN: 0162-8828
pp: 459-469
Gyorgy Fekete , Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742.
Jan-Olof Eklundh , National Defense Research Institute, Linköping, Sweden; Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742.
Azriel Rosenfeld , Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742.
ABSTRACT
Probabilistic relaxation labeling processes are iterative parallel schemes that use contextual information to reduce local ambiguities. The behavior of these processes can be described by examining the rates of change and entropies of the probability vectors at each iteration. Examples are given comparing three relaxation processes as applied to several basic image analysis tasks.
INDEX TERMS
CITATION

G. Fekete, J. Eklundh and A. Rosenfeld, "Relaxation: Evaluation and Applications," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 3, no. , pp. 459-469, 1981.
doi:10.1109/TPAMI.1981.4767131
89 ms
(Ver 3.3 (11022016))