DocumentCode :
1705856
Title :
Variational phasor mean field model for object recognition
Author :
Takahashi, Haruhisa
Author_Institution :
Univ. of Electro-Commun., Tokyo
fYear :
2008
Firstpage :
490
Lastpage :
493
Abstract :
The variational phasor mean field model (VPMF) for Markov random fields can well represent marginal distribution as well as correlation among the sites. The network is represented by complex equations, which consist of phase equations and variational mean-field equations; thus the VPMF enables not only to improve the accuracy of the mean field approximation but also to give additional correlational relation between units with the cosine of the phase differences. In this report we discuss VPMF as an object recognition tool, and show that it provides efficient learning methods through computer experiments.
Keywords :
Markov processes; approximation theory; correlation methods; object recognition; variational techniques; Markov random fields; correlational relation; learning method; mean field approximation; object recognition; phase equation; variational phasor mean field model; Difference equations; Distributed computing; Face detection; Learning systems; Markov random fields; Object recognition; Random processes; Sequences; Support vector machines; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, Control and Signal Processing, 2008. ISCCSP 2008. 3rd International Symposium on
Conference_Location :
St Julians
Print_ISBN :
978-1-4244-1687-5
Electronic_ISBN :
978-1-4244-1688-2
Type :
conf
DOI :
10.1109/ISCCSP.2008.4537275
Filename :
4537275
Link To Document :
بازگشت