DocumentCode :
3279791
Title :
Contour extraction of images on parallel computer-local, parallel and stochastic algorithm which learns energy parameters
Author :
Hongo, Sadayuki ; Kawato, Mitsuo ; Inui, Toshio ; Miyake, Sei
Author_Institution :
ATR, Kyoto, Japan
fYear :
1989
fDate :
0-0 1989
Firstpage :
161
Abstract :
The stochastic relaxation algorithm for S. Geman and D. Geman (1984), which is based on the Markov random-field (MRF) model of images, was implemented on a hypercube parallel computer for contour extraction of human face images. The local energy parameters that define the MRF model were estimated by the authors´ learning algorithm (1989), while supervised by a desirable object contour as a teaching signal. D. Geman´s constrained optimization method (1987) was utilized to avoid flaws in a fast simulated annealing. The contours extracted by the learning stochastic relaxation method were systematically compared with those obtained by several conventional edge detection methods. The contours extracted by the authors´ method include few discontinuity points and small amounts of noise, and faithfully represent the true contours. The authors propose an algorithm, multiple-level, multiple-resolution MRF, which is an extension of the original MRF. This model can incorporate a priori knowledge about the global structures in images and still be implemented in a local and parallel mode.<>
Keywords :
Markov processes; computerised pattern recognition; computerised picture processing; learning systems; neural nets; optimisation; parallel processing; Markov random field model; computer vision; constrained optimization; contour extraction; energy parameters; fast simulated annealing; hypercube parallel computer; learning algorithm; multiple-level multiple-resolution method; noise; parallel computer; pattern recognition; picture processing; stochastic relaxation algorithm; Image processing; Learning systems; Markov processes; Neural networks; Optimization methods; Parallel processing; Pattern recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
Type :
conf
DOI :
10.1109/IJCNN.1989.118575
Filename :
118575
Link To Document :
بازگشت