主元分析变换空间上的鉴别共同矢量人脸识别方法

基金项目: 国家863计划资助项目(2008AA04Z209)；国家自然科学基金资助项目(60675049)；浙江省自然科学基金资助项目(Y106414)

详细信息

Discriminant Common Vectors in Principal Component Analysis Transformed Space for Face Recognition

¹State Key Laboratory of Industrial Control Technology,Zhejiang University,388 Yuhangtang Road,Hangzhou 310027,China

Funds: 国家863计划资助项目(2008AA04Z209)；国家自然科学基金资助项目(60675049)；浙江省自然科学基金资助项目(Y106414)

摘要: 给出了在主元分析(PCA)变换空间上求取DCV投影矩阵的方法(PCA+DCV),在保留所有鉴别信息的条件下,显著降低了算法复杂度,提高了运算效率。进一步提出了依据主元成分对应特征值进行适度权重的DCV识别方法(WPCA+DCV),一定程度上减小因光照、饰物遮挡等造成的面部变化带来的识别影响,增强表征信息,提高识别率。在ORL、YALE和AR人脸库上的实验结果证实了本方法的性能。
- 主元分析 /
- 鉴别共同矢量 /
- 人脸识别 /
- 小样本问题
Abstract: In this paper,we first offer an efficient algorithm to perform DCV in principal component analysis(PCA) transformed space.In this way,we reduce the algorithm's complexity and improve the efficiency whilst preserving the whole discriminant information.Then,the new algorithm further facilitates us to subtly weight the facial components in PCA space according to corresponding eigenvalues,which is potential to enrich the representative information and thus improves DCV's recognition performance.The experiments conducted on ORL,YALE and AR face database demonstrate the effectiveness of our method.
- PCA /
- DCV /
- face recognition /
- small sample size