基于LBP和几何混合特征的人脸识别

Face Recognition Based on LBP and Geometric Hybrid Feature

提出一种基于ASM几何特征和LBP局部特征的人脸识别新方法。该方法首先使用ASM算法对样本数据进行区域筛选,然后通过LBP特征与ASM特征构建融合特征对人脸进行识别。本文使用JAFFE人脸数据库和CK+数据库进行算法测试,实验结果表明本文提出的方法比单独使用ASM和LBP特征在人脸识别率上有较大的改善。

This paper presents a new method of face recognition based on ASM geometry features and LBP local features. Firstly,the ASM algorithm is used to filter on the sample data. Then,the LBP features are combined with the ASM features to build the fusion feature of face recognition. In this paper,the JAFFE face database and CK ＋ database are used to test the algorithm.The experimental results show that the method proposed in this paper has a greater improvement of rate in face recognition than using ASM or LBP alone.