基于LBP和PCA特征提取的人脸识别

为有效解决局部二元模式(LBP)在人脸识别特征提取时维数过高的问题,提出了一种结合LBP特征和主成分分析(PCA)的人脸识别方法.首先,对人脸图像进行分块,提取其LBP直方图特征,然后使用PCA方法对特征向量进行降维,最后将降维后的特征向量用于识别.在FERET人脸库上的实验结果表明:相对于原始LBP表达方法,结合LBP和PCA的人脸表达能有效降低计算复杂度,同时也较好地保持了原有识别精度.

Feature Extraction Using LBP and PCA for Face Recognition

To address the problem that the dimension of the feature vector extracted by Local Binary Pattern(LBP) for face recognition is too high,an efficient feature extraction method using LBP and Principal Component Analysis(PCA) has been introduced in this paper.The original face image is firstly divided into sub-images,and then the LBP operator is applied to extract the histogram feature.The feature dimensions are further reduced by using PCA for the final face recognition.The experimental results on FERET datab...