Title :
A unified random field model based neural approach to pixel labeling problems in computer vision
Author :
Parthasarathy, Guturu ; Raj, Perugu Ananth
Author_Institution :
Dept. of Electron. & Electr. Commun. Eng., Indian Inst. of Technol., Kharagpur, India
fDate :
27 Jun- 2 Jul 1994
Abstract :
In this paper, we establish a nexus between the Gibbs random field models and recurrent neural networks and present a unified neural network approach based on this to pixel labeling problems in computer vision. We also present a case study with photometric stereo problem for demonstrating the viability of the present approach
Keywords :
Markov processes; computer vision; dynamic programming; recurrent neural nets; stereo image processing; Gibbs random field models; computer vision; photometric stereo imaging; pixel labeling; recurrent neural networks; unified random field model; Computer vision; Degradation; Inverse problems; Labeling; Motion detection; Neural networks; Photometry; Pixel; Recurrent neural networks; Stereo vision;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374871