DocumentCode
3057512
Title
An optimization algorithm for determining the compatibility coefficients of relaxation labeling processes
Author
Pelillo, Marcello ; Refice, Mario
Author_Institution
Dept. of Comput. Sci., Bari Univ., Italy
fYear
1992
fDate
30 Aug-3 Sep 1992
Firstpage
145
Lastpage
148
Abstract
The problem of determining compatibility coefficients for relaxation labeling processes has received considerable attention and a number of different methods have been suggested. The authors propose a method developed within an optimization framework. After formulating the problem of determining the coefficients as a nonlinear programming problem, they develop a gradient-descent algorithm for solving it. Results on an application of relaxation processes are given
Keywords
nonlinear programming; pattern recognition; compatibility coefficients; gradient-descent algorithm; nonlinear programming; optimization algorithm; relaxation labeling processes; Bibliographies; Computer science; Iterative algorithms; Labeling; Linear programming; Machine vision; Measurement standards; Optimization methods; Probability distribution; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location
The Hague
Print_ISBN
0-8186-2915-0
Type
conf
DOI
10.1109/ICPR.1992.201741
Filename
201741
Link To Document