基于CCA的人耳和侧面人脸特征融合的身份识别*

鉴于人耳和人脸特殊的生理位置关系,从非打扰识别的角度出发,提出仅采集侧面人脸图像,利用典型相关分析的思想提取人耳和侧面人脸的关联特征,进行人耳和侧面人脸在特征层的融合.实验结果表明,此方法与单一的人耳或侧面人脸特征识别比较,识别率得到提高.

Multimodal recognition using ear and face profile based on CCA

The fusion of ear and face biometrics could fully utilize their connection relationship of physiological location, and possessed the advantage of recognizing people without their cooperation. First, this method used the face profile images including ear part for recognition. Then according to the algorithm of canonical correlation analysis(CCA),proposed a kind of associated feature based on ear and face profile for classification and recognition. The result of experiment shows that the recognition rate is higher than that of the recognition adopting the single biometrics.