基于Gabor不确定度的嵌入式人脸识别系统  

Embedded face recognition system based on Gabor uncertainty

作　　者：叶继华[1] 王仕民[1] 郭帆[1] 余敏[1] 

机构地区：[1]江西师范大学计算机信息工程学院,南昌330022

出　　处：《计算机应用》2011年第9期2502-2505,2550,共5页journal of Computer Applications

基　　金：国家973计划项目(2007CB316505);江西师范大学科研项目(2009-7)

摘　　要：多尺度Gabor特征的维数和数据量过大,不适合在ARM板上直接实现完成。利用计算每个尺度Gabor特征不确定度并采用加权融合的方法,很好地解决了图像维数和数据量过大的难点。加权融合过程包括多尺度Gabor特征的提取、不确定度权值的计算和加权融合过程;同时使用了类Haar特征提取人脸、利用二维主成分分析(2DPCA)对人脸图像进行降维。基于EELiod 270嵌入式开发平台,使用ORL和Yale图像库对该方法进行了测试,并与其他人脸识别算法进行比较。结果显示,在保证识别率的同时,算法运算量大幅度下降,且实时识别效果良好。Gabor uncertainty features fusion can solve the problem that muhiscale Gabor features are unsuitable for ARM because of huge data and dimensions in the embedded face recognition system. Muhiscale Gabor features were first extracted, and then the uncertain weight was calculated, at last multiscale Gabor features were integrated into one. The embedded face recognition system detected face by using Haar-like features of face, and reduced dimensions by using 2-Dimensional Principal Component Analysis （2DPCA） algorithm. Based on EELiod 270 development board, the performance of face recognition was tested on ORL and Yale. Comparative results with other face recognition algorithms show that a significant decline is got in the amount of arithmetic operations, and a good real-time recognition is obtained while ensuring the recognition rate.

关 键 词：GABOR滤波器 不确定度 HAAR特征 二维主成分分析 嵌入式系统 人脸识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]