Gabor小波和SLLE在人脸识别中的应用

Application of Gobor Wavelet and SLLE in Face Recognition

为了提高人脸识别算法的识别率,提出了一种基于Gabor小波和SLLE的人脸识别算法.该算法首先采用Gabor小波对归一化的人脸图像进行多方向、多分辨率滤波,并提取其对应不同方向、不同尺度的多个Gabor幅值特征,然后采用监督的局部线性嵌入算法对Gabor特征进行维数约简,最后使用最近邻分类器进行分类判决.在ORL、YALE人脸库上进行实验,结果表明,该算法平均识别率比其他算法提高3.5%～37.8%,有效提高了人脸识别算法的性能.

In order to improve the recognition rate of face recognition algorithm, this paper presents a new algorithm of face recognition based on Gabor wavelet transform and Supervised Locally Linear Embedding （SLLE）. First of all, Gabor wavelet is introduced as a method to extract Gabor magnitude features by convolving the normalized face image with multi -scale and multi -orientation Gabor filters. In the feature extraction module, the dimension of Gabor features are reduced by Supervised Locally Linear Embedding （SLLE）. classification. The result of experiment increase in recognition rate compared performance effectively. Finally, a minimum -distance classifier is trained for on the ORL and YALE face database shows a 3.5 % - 37.8% to others. The proposed algorithm improves face recognition