摘要
从小波变换良好的多尺度特征表达能力和Bayesian方法良好的识别能力出发,提出了一种基于小波的Bayesian人脸识别方法.首先对人脸图像进行小波分解,其次对得到的每幅低频子图进行Bayesian人脸识别,最后利用Yale人脸图像库进行了试验.实验表明,与传统的方法相比较,该方法提高了识别率,降低了运算量.
Wavelet transform has a good ability to express the multi-resolution characteristics and Bayesian theory has demonstrated a success in face detection and face recognition. Bayesian face recognition based on wavelet transform is proposed. Then, Bayesian approach is used to the low-frequency sub-band. Its efficiency and superiority are clarified by comparative experiment on Yale database.
出处
《河南师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2009年第2期50-52,共3页
Journal of Henan Normal University(Natural Science Edition)
基金
国家自然科学基金(60873104)
