摘要
提出了一种基于局部小波变换和离散余弦变换(DiscreteCosineTransform,DCT)相结合的人脸识别方法,该算法首先利用小波变换对人脸图像做适当层次的小波分解,然后通过离散余弦变换对低频分量作进一步的特征提取和压缩,得到人脸识别特征,最后利用欧氏距离和最近邻分类器进行识别。基于ORL人脸数据库的实验结果表明了该算法的有效性。
A new human face recognition approach based on local wavelet transform and discrete cosine transform（DCT） was proposed. Firstly, some human face images were decomposed using wavelet transform. Secondly the farther feature extraction and compression arc applied to low frequency sub-bands by way of discrete cosine transform, and face recognition features are obtained. Finally, Euclidean distance and minimum distance classifier is utilized in recognition. Simulation experiments are conducted based on face image in ORL （Olivetti Research Laboratory） face database. The results show that the recognition rate is quite high and the train time is notably shortened, so the method is efficient for face recognition.
出处
《微计算机信息》
北大核心
2006年第01Z期205-208,共4页
Control & Automation
基金
广东省自然科学基金资助项目编号:032356
关键词
人脸识别
小波变换
离散余弦变换
face recognition
wavelet transform
discrete cosine transform（DCT）
