Relaxation: Evaluation and Applications

Authors:
Gyorgy Fekete;Jan-Olof Eklundh;Azriel Rosenfeld
Affiliations:
Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742.;National Defense Research Institute, Linkö/ping, Sweden/ Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742.;Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742.
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1981

Citing 0
Cited 2

Models and algorithms for computing the common labelling of a set of attributed graphs

Computer Vision and Image Understanding
Active graph matching based on pairwise probabilities between nodes

SSPR'12/SPR'12 Proceedings of the 2012 Joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition

Quantified Score

Hi-index	0.14

Visualization

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.