基于LLE和LS-SVM的人脸识别方法

Face Recognition Based on Locally Linear Embedding and Least Squares Support Vector Machines

摘要: 为了提高人脸识别的速度,提出了一种基于局部线性嵌套(LLE)和最小二乘支持向量机(LS-SVM)的人脸识别方法.该方法采用主成分分析(PCA)和LLE相结合的算法,对归一化处理过的人脸图像进行特征提取,利用LS-SVM对人脸图像样本集进行训练和识别,以提高识别的速度.最后将本文方法在ORL人脸数据库上进行试验,结果表明,人脸识别的速度有了一定的提高,识别率达到了90%以上.

Abstract: In order to improve the speed of face recognition, a face recognition method based on locally linear embedding (LLE) and least squares support vector machines (LS-SVM) was proposed. After extracting the features of the pre-processing face images using principal component analysis (PCA) and locally linear embedding, LS-SVM was used to train the feature sets and recognize the faces. And, the speed of face recognition was improved. Finally, the method was tested on the ORL (Olivetti Research Laboratory) face database, the results show that the proposed method can improve the speed of face recognition, and the rate of face recognition exceeds 90%.