LOBE COMPONENT ANALYSIS DERIVES DISPARITY- SELECTIVE FILTERS

摘要：

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.

关键词： Stereo Disparity Lobe Component Analysis Learning-based Vision

作者: HUI-XUAN TANG HUI WEI

作者单位: Lab of Algorithm for Cognitive Models, Department of Computer Science and Engineering Fudan University, Shanghai 200433, China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 4046-4049

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）