文献类型：会议论文

英文题名：A Novel Computational Model for Visual Attention

作者：Zhang, Huawei[1];Zhang, Qiaorong[1];Liu, Haibo[2]

第一作者：张华伟

通讯作者：Zhang, HW[1]

机构：[1]Henan Univ Finance & Econ, Coll Comp & Informat Engn, Zhengzhou, Peoples R China;[2]Harbin Engn Univ, Coll Comp Sci & Technol, Harbin, Peoples R China

第一机构：河南财经政法大学计算机与信息工程学院

通讯机构：[1]corresponding author), Henan Univ Finance & Econ, Coll Comp & Informat Engn, Zhengzhou, Peoples R China.|[1048412]河南财经政法大学计算机与信息工程学院;[10484]河南财经政法大学;

会议论文集：3rd International Symposium on Electronic Commerce and Security (ISECS)

会议日期：JUL 29-31, 2010

会议地点：Guangzhou, PEOPLES R CHINA

语种：英文

外文关键词：visual attention; computational model; resolution-varying; visual saliency; salient region

摘要：A new computational model for selective visual attention is proposed in this paper. This model simulates the depth-first and resolution-varying visual searching mechanism of human visual system. Firstly, visual saliency of each part is computed at the coarsest resolution. According to the visual saliency, the most salient region is selected. Then the inner details of the selected region are analyzed at a finer resolution. This process is done iteratively until every salient region and its inner has been processed under different resolutions respectively. The proposed model has been tested on many natural images. Experiment results and analysis are presented in this paper. It is showed that the proposed model is valid.