|
|||||
|
|
| 一种改进的最大间距准则人脸识别方法 | |
| 引用本文： | 刘亚亚. 一种改进的最大间距准则人脸识别方法[J]. 科学技术与工程, 2013, 13(9): 2566-2571 |
| 作者姓名： | 刘亚亚 |
| 作者单位： | 商洛学院数学与计算科学系 |
| 基金项目： | 陕西省教育厅科研计划项目(11JK0512);陕西省教育科学“十二五”规划课题(SGH12443);商洛学院科研基金项目(11SKY003,12SKY010);商洛学院教育教学改革项目(10jyjx02006) |
| 摘 要： | 针对最大间距准则在人脸特征提取过程中的不足,提出一种统计不相关的加权最大间距准则人脸特征提取方法。首先对最大间距准则的类间散度矩阵和类内散度矩阵加乘权函数。然后在准则函数中利用双参数调节类间散度和类内散度对特征抽取的影响力。最后通过Schmidt正交化得到统计不相关的最佳鉴别矢量集。在ORL和Yale人脸图像库上的仿真实验结果表明,克服了最大间距准则的缺点,提高了人脸识别率。 |
| 关 键 词： | 人脸识别 加权最大间距准则 统计不相关 特征提取 |
| 收稿时间： | 2012-11-07 |
| 修稿时间： | 2012-12-10 |
An Improved Face Recognition Method Based on Maximum Margin Criterion |
|
| Liu yaya. An Improved Face Recognition Method Based on Maximum Margin Criterion[J]. Science Technology and Engineering, 2013, 13(9): 2566-2571 | |
| Authors: | Liu yaya |
| Affiliation: | (Department of Mathematics and Computer Science,Shangluo University,Shangluo 726000,P.R.China) |
| Abstract: | According to the shortage of maximum margin criterion in the face feature extraction process, this paper presents a statistical uncorrelated weighted maximum margin criterion face feature extraction method. Firstly , add weight function by class between divergence matrix and class inside divergence matrix, and then using double parameters in the criterion function to control the influence of the feature extraction on class between divergence and class inside divergence.Finally through the Schmidt orthogonalization get statistical uncorrelated optimal identification vector set.Experimental results on ORL face database and Yale face database show that this method overcomes the shortcomings of the maximum margin criterion, and improve the face recognition rate. |
| Keywords: | face recognition weighted maximum margin criterion satistical uncorrelated feature extraction |
| 本文献已被 CNKI 等数据库收录！ | |
| 点击此处可从《科学技术与工程》浏览原始摘要信息 | |
| 点击此处可从《科学技术与工程》下载全文 | |