| 基于认知的人脸识别方法研究 |
| |
| 引用本文： | 刘瑶,王国胤,杨勇,于洪.基于认知的人脸识别方法研究[J].计算机工程与设计,2011,32(12):4119-4121,4128. |
| |
| 作者姓名： | 刘瑶 王国胤 杨勇 于洪 |
| |
| 作者单位： | 重庆邮电大学计算机科学与技术研究所,重庆,400065 |
| |
| 基金项目： | 国家自然科学基金项目，重庆市自然科学基金项目 |
| |
| 摘 要： | 提出一种基于认知的人脸识别方法:从结构信息和特征信息两方面分别进行加工对人脸进行识别。该方法模拟人类认知过程,提取LDA特征表征人脸结构信息,并就此做出初步识别得到最近邻人脸类别。针对挑选出的相似类别人脸采用2DPCA获取人脸特征信息,并基于模糊隶属度进行精确识别。在ORL和Yale人脸库的实验结果验证了该方法是有效的,并且对各种复杂情况具有一定鲁棒性。
|
| 关 键 词： | 人脸识别 人脸认知 结构信息 特征信息 线性鉴别分析 二维主元分析 |
Face recognition based on human cognition |
| |
| LIU Yao,WANG Guo-yin,YANG Yong,YU Hong.Face recognition based on human cognition[J].Computer Engineering and Design,2011,32(12):4119-4121,4128. |
| |
| Authors: | LIU Yao WANG Guo-yin YANG Yong YU Hong |
| |
| Affiliation: | LIU Yao,WANG Guo-yin,YANG Yong,YU Hong(Institute of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China) |
| |
| Abstract: | A new face recognition algorithm based on the cognitive theory is proposed,recognizing faces by two independent parts: configural information and featural information.This algorithm simulates the process of human cognition.LDA is performed on face image matrix to form configural information,which is used to select the nearest neighborhood classes.And then,2DPCA is used to extract featural information from the selected faces.Furthermore,according to the featural information,an accurate decision based on fuzz... |
| |
| Keywords: | face recognition face cognition configural information featural information LDA 2DPCA |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
