| 基于EMRBF情感神经网络的人脸识别 |
| |
| 引用本文： | 杨国亮,漆娟娟,张丽. 基于EMRBF情感神经网络的人脸识别[J]. 微型机与应用, 2013, 0(19): 48-51 |
| |
| 作者姓名： | 杨国亮 漆娟娟 张丽 |
| |
| 作者单位： | [1]江西理工大学电气工程与自动化学院,江西赣州341000 [2]玉溪师范学院信息技术工程学院,昆明玉溪653100 |
| |
| 摘 要： | 在现有RBF神经网络基础上引入情感因子，提出了一种情感径向基神经网络（EMRBF），给出了EMRBF的结构，定义了新的训练准则函数，推导出了EMRBF网络权值训练算法，把EMRBF网络用于人脸识别系统。先采用PCA和LDA相结合进行人脸特征提取．然后设计EMRBF人脸分类器。在ORL人脸库上的实验结果表明，EMRBF网络的识别率达到98％，与普通RBF神经网络相比，性能明显提高。
|
| 关 键 词： | 人脸识别 情感因子 准则函数 RBF神经网络 情感神经网络 |
Face recognition based on emotional RBF neural network |
| |
| Yang Guoliang,Qi Juanjuan,Zhang Li. Face recognition based on emotional RBF neural network[J]. Microcomputer & its Applications, 2013, 0(19): 48-51 |
| |
| Authors: | Yang Guoliang Qi Juanjuan Zhang Li |
| |
| Affiliation: | 1.School of Electrical Engineering ＆ Automation,Jiangxi University of Science and Technology,Ganzhou 341000,China; 2.School of Information Technology and Engineering,Yuxi Normal University,Yuxi 653100,China) |
| |
| Abstract: | This paper proposes a face recognition method based on emotional RBF （EMRBF） neural network which introduces an emotional factor to the traditional RBF neural network. It provides the structure of the EMRBF, defines a new training criterion function, deduces EMRBF network weight training algorithm. The method firstly extractes face feature by PCA and LDA, and then designes EMRBF face classifier. The experiment on ORL face database shows that EMRBF network recognition rate reach 98%. EMRBF performance has significantly improve compared to the normal RBF network. |
| |
| Keywords: | face recognition emotional factor criterion function RBF neural network emotional neural network |
| 本文献已被 维普 等数据库收录！ |
