| 自适应半监督边界费舍尔分析 |
| |
| 引用本文： | 姜伟,杨炳儒,隋海峰.自适应半监督边界费舍尔分析[J].计算机科学,2011,38(3):252-253. |
| |
| 作者姓名： | 姜伟 杨炳儒 隋海峰 |
| |
| 作者单位： | 1. 北京科技大学信息工程学院,北京,100083;辽宁师范大学数学学院,大连,116029
2. 北京科技大学信息工程学院,北京,100083 |
| |
| 基金项目： | 本文受国家自然科学基金项目(60875029)资助。 |
| |
| 摘 要： | 基于图的半监督算法已经成功地应用于人脸识别中，算法不仅考虑带标签数据而且利用一致性的假设。传统的算法一致性约束是定义在原特征空间中，但是在原特征空间中定义的一致性不是最好的。提出了自适应半监督边界费舍尔分析算法，它将一致性约束定义在原特征空间和期望低维特征空间中。在CMU PIE和YALE-B数据库上进行了实验，结果表明自适应半监督边界费舍尔分析算法在人脸识别率上有显著的提高。
|
| 关 键 词： | 判别结构，半监督，边界费舍尔分析 |
Adaptive Semi-supervised Marginal Fisher Analysis |
| |
| JIANG Wei,YANG Bing-ru,SUI Hai-feng.Adaptive Semi-supervised Marginal Fisher Analysis[J].Computer Science,2011,38(3):252-253. |
| |
| Authors: | JIANG Wei YANG Bing-ru SUI Hai-feng |
| |
| Affiliation: | (School of Information Engineering,University of Science and Technology Beijing,Beijng 100083,China);(School oI Mathematics,Liaoning formal University,Dalian 116029,China) |
| |
| Abstract: | Graph based semi supervised methods have successfully used in face recognition. These algorithms not only consider the label information, but also utilize a consistency assumption. Conventional algorithms assumed that the consistency constraint is defined on the original feature space. However, the original feature space is not the best for defining consistency. We proposed adaptive semi supervised marginal fisher analysis(ASMFA) by which the consistency constraint is defined in the original feature space and the expected low-dimensional feature space. Experimental results on the CMU PIE and YALE-B databases demonstrate that ASMFA brings signification improvement in face recognition accuracy. |
| |
| Keywords: | Discrirninant structure Semi-supervised Marginal fisher analysis |
| 本文献已被 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
