Color Face Recognition Based on Quaternion Zernike Moment Invariants and Quaternion BP Neural Network

摘要：

As an active research topic, many algorithms have been presented for face recognition. However, they mainly utilize the monochromatic intensity information. Among a few color face recognition methods, most of them treat the three channels separately. In this paper, a color face image is treated in a holistic manner by using the quaternion theory. We then propose a new algorithm for color face recognition, which uses the quaternion Zernike moment invariants and the quaternion BP neural network for the color face recognition. Experimental results on the Collection of Facial Images (Grimace) database, including major expression variation and considerable variation in head turn and tilt, show that the proposed method is better than the conventional ones in recognition rate.

关键词： color face recognition quaternion Zernike moment moment invariants quaternion BP neural network

作者: Beijing Chen Huazhong Shu Gang Chen Jun Ge Limin Luo

作者单位: Laboratory of Image Science and Technology, Southeast University, Nangjing, China Centre de Recherch Laboratory of Image Science and Technology, Southeast University, Nangjing, China Centre de Recherch Laboratory of Image Science and Technology, Southeast University, Nangjing, China

会议类型: 国际会议

会议名称: 2010 International Conference on Information Security and Artificial Intelligence(2010年信息安全与人工智能国际会议 ISAI 2010)

会议地点: 成都

会议语种:英文

页码: 809-812

在线出版日期: 2010-12-17（万方平台首次上网日期，不代表论文的发表时间）