中文摘要：

本文提出了一种提取人脸图像的局部Gabor相位特征,结合Fisher线性判别式,通过特征融合进行人脸识别的方法。该方法首先利用Gabor滤波良好的空间位置与方向选择特性,采用四个频率六个方向的Gabor滤波器对图像进行滤波,然后根据Daugman方法采用局部XOR算子提取滤波图像的局部Gabor相位特征,组成特征图像,最后通过Fisher判别式对每个频率和方向下的特征图像进行降维,融合降维后的特征,采用最近邻分类器进行识别。该方法通过在两个数据库中的实验,证明了较主成分分析法,Fisher线性判别式方法以及Gabor幅值特征融合识别方法更好的识别性能。

英文摘要：

A new face recognition method based on local Gabor phase characteristic fusion and fisher linear discriminant analysis is proposed.In our proposed method,according to the good spatial position and orientation of Gabor filter,a Gabor filter with four frequencies and six orientations is firstly applied to filter face images.Based on Daugman＇s method and the local Exclusive-or（XOR） pattern,local Gabor patterns are then extracted to form the characteristic images.Finally,fisher linear discriminant analysis is used to project the characteristic images of each spatial position and orientation into low dimensional space.Neighbor classifier is adopted to the fused projected characteristics to get the recognition result.Experimental results show that our method consistently outperforms other recognition method based on Principal Component Analysis（PCA）,fisher linear discriminant analysis and Gabor magnitude pattern fusion.