计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (34): 200-203.

• 工程与应用 • 上一篇    下一篇

基于2DPCA和RBF神经网络的人脸识别方法

白雪飞,李 茹   

  1. 山西大学 计算机与信息技术学院,太原 030006
    计算智能与中文信息处理省部共建教育部重点实验室,太原 030006
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-01 发布日期:2007-12-01
  • 通讯作者: 白雪飞

Face recognition method based on 2DPCA and RBF neutral network

BAI Xue-fei,LI Ru   

  1. School of Computer & Information Technology,Shanxi University,Taiyuan 030006,China
    Key Laboratory of Ministry of Education for Computation Intelligence and Chinese Information Processing,Taiyuan 030006,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-01 Published:2007-12-01
  • Contact: BAI Xue-fei

摘要: 采用2DPCA方法提取人脸图像的特征值,通过RBF神经网络进行训练和识别,提出一种基于2DPCA和RBF神经网络的人脸识别方法,并将此方法应用于ORL人脸库。实验结果表明,该方法不仅具有较好的人脸图像识别能力,而且能明显缩短识别算法的运行时间。

关键词: 二维主成分分析, RBF神经网络, 人脸识别

Abstract: A new approach for human face recognition based on 2DPCA and RBF neutral network is proposed.This method is tested on the standard ORL face database.Experimental results demonstrate that the combined method based on 2DPCA and RBFNN can achieve a better performance in recognition accuracy than other method and this method cost less computational time.

Key words: two-dimensional principal component analysis, RBF neutral network, face recognition