基于多级CS-LBP特征融合的人脸识别方法

通常,采用中心对称局部二值模式CS-LBP对人脸图像只进行一次特征提取,提取的纹理特征不够丰富。因此,本文利用CS-LBP多次提取人脸图像更丰富的纹理特征,提出了多级CS-LBP特征融合的人脸识别算法。首先,用CS-LBP对原始人脸图像进行特征提取;然后,对所得特征图像再进行相同方式的特征提取,这样能够得到原始人脸图像的多级CS-LBP特征图像;最后,将每一级特征图像的分块直方图特征进行融合并用于人脸识别。在ORL、Yale标准人脸库上的实验结果表明,相比人脸图像的一级CS-LBP特征,多级CS-LBP特征融合的方法能够显著提高识别精度。

A Face Recognition Method Based on the Fusion of Multi-Level Center-Symmetric Local Binary Pattern Features

Generally, the center symmetric local binary pattern (CS LBP) is used to extract features from the  face images only once, by which the extracted texture features are not adequate to represent the face images. Therefore, we employ CS LBP to extract more abundant and informative texture features for more times, and a new face recognition method is proposed which is on the basis of the fusion of multi level center symmetric local binary pattern features. In this method, first, the CS LBP is utilized to extract the first level features from the original face image; then, the second level features are extracted from the  feature image by CS LBP again; likewise, we can obtain the multi level texture features and then fuse different level features to represent face images. The experimental results on the ORL and Yale face databases demonstrate that compared with one level face image features, the method of fusing the  multi level CS LBP features can improve the face recognition accuracy obviously.