DocumentCode :
2899023
Title :
Lobe Component Analysis Derives Disparity-Selective Filters
Author :
Tang, Hui-Xuan ; Wei, Hui
Author_Institution :
Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai
fYear :
2006
fDate :
13-16 Aug. 2006
Firstpage :
4046
Lastpage :
4049
Abstract :
Neurons in the primary visual cortex are known to segregate in cluster with varying disparity preferences. They function as linear filters that help extracting depth information. This paper investigates the possibility to derive disparity-selective filters by lobe component analysis on stereo images. In experiments, we trained on eighty pairs of stereo images and tested on a sample object at various depths. Response curves were found to resemble characteristics expected for disparity neurons in the primary visual cortex
Keywords :
cellular biophysics; neurophysiology; principal component analysis; unsupervised learning; visual perception; competitive learning; disparity neurons; disparity-selective filters; linear filters; lobe component analysis; primary visual cortex; principal component analysis; stereo images; Band pass filters; Biological system modeling; Brain modeling; Clustering algorithms; Covariance matrix; Cybernetics; Gabor filters; Hebbian theory; Machine learning; Neurons; Nonlinear filters; Pixel; Principal component analysis; Disparity; Learning-based Vision; Lobe Component Analysis; Stereo;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
Type :
conf
DOI :
10.1109/ICMLC.2006.258859
Filename :
4028780
Link To Document :
بازگشت