| 基于改进的监督LLE人脸识别算法 |
| |
| 引用本文： | 李白燕,李平,陈庆虎.基于改进的监督LLE人脸识别算法[J].电视技术,2011,35(19):105-108. |
| |
| 作者姓名： | 李白燕 李平 陈庆虎 |
| |
| 作者单位： | 1. 黄淮学院信息工程系,河南驻马店,463000
2. 武汉大学电子信息学院,湖北武汉,430079 |
| |
| 基金项目： | 河南省科技发展计划项目(112102310473) |
| |
| 摘 要： | LLE是一种无监督的非线性降维方法,广泛应用于人脸特征提取,但是该方法缺乏样本点的类别信息.提出了一种新方法,在LLE的基础上引入有监督的学习机制和增加样本点的类别信息,通过减少类内距离而增加类间距离和最小化局部数据的全局重构误差,同时结合核邻域保持投影方法(KNPP)来提取高维人脸数据的非线性特征.算法有利于分类识别...
|
| 关 键 词： | 非线性降维 类别信息 监督 局部线性嵌入 人脸识别 |
Face Recognition Algorithm Based on Improved Supervised LLE |
| |
| LI Baiyan,LI Ping,CHEN Qinghu.Face Recognition Algorithm Based on Improved Supervised LLE[J].Tv Engineering,2011,35(19):105-108. |
| |
| Authors: | LI Baiyan LI Ping CHEN Qinghu |
| |
| Affiliation: | LI Baiyan1,LI Ping1,CHEN Qinghu2(1.Department of Information Engineering,Huanghuai University,Henan Zhumadian 463000,China,2.School of Electronic Information,Wuhan University,Wuhan 430079,China) |
| |
| Abstract: | LLE is an unsupervised nonlinear dimensionality reduction method,widely used in facial feature extraction,but the method is lack of class label information of sample points.A new method is proposed based on the LLE with introducing supervised learning mechanism and increasing class label information of the sample points,by shrinking the intraclass distance while expanding the interclass distance to get the enhanced supervised locally linear embedding and minimizing the global reconstruction error of local d... |
| |
| Keywords: | nonlinear dimensionality reduction class label information supervised local linear embedding face recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
