EDA-Based Optimal Gabor Kernels Scale and Orientation Selection for Facial Ezpression Recognition

摘要：

In order to reduce Gabor features dimension and remove redundant information between features, we propose a new Gabor features dimension reduction method that utilizes Estimation of distribution algorithms (EDA) to search optimal Gabor kernels scales and orientations. We equate feature dimension reduction problem to optimal Gabor kernels scales and orientations selection problem. This method is applied to facial expression recognition. Experimental results on JAFFE database demonstrate that our method is more effective for both dimension reduction and image representation than traditional Gabor filter bank.

关键词： EDA Gabor Facial ezpression recognition

作者: ZHENG Qiumei LV Xinghui SHI Gongxi

作者单位: College of Computer and Communication Engineering China University of Petroleum Dongying, China

会议类型: 国际会议

会议名称: 第四届国际计算机新科技与教育学术会议(2009 4th International Conference on Computer Science & Education)

会议地点: 南京

会议语种:英文

页码: 113-117

在线出版日期: 2009-07-25（万方平台首次上网日期，不代表论文的发表时间）