Visual Saliency Detection based on Topographic Independent Component Analysis

摘要：

A computational model of visual saliency detection is proposed based on topographic independent component analysis. This model consists of three steps: first training basis functions and extracting features which represents complex cell responses by topographic independent component analysis, then estimating feature distributions, and finally calculating self-information and obtaining saliency maps. It is demonstrated by numerical examples that the proposed model could detect saliency regions in some circumstances when previous related model couldnt, and predict human attention fixations better than other models.

关键词： visual saliency detection topographic independent component analysis computational model

作者: Xin Wei Chunguang Li

作者单位: Department of Information Science & Electronic Engineering Zhejiang University Hangzhou, China

会议类型: 国际会议

会议名称: 2010 IEEE 10th International Conference on Signal Processing(第十届信号处理国际会议 ICSP 2010)

会议地点: 北京

会议语种:英文

页码: 1244-1247

在线出版日期: 2010-08-24（万方平台首次上网日期，不代表论文的发表时间）