摘要
简述人脸图像的标准化过程,特征脸,LDA算法的原理及实现过程。用特征脸和LDA相结合的方法进行人脸识别,先用特征脸获取最佳描述特征,然后用LDA获取最佳分类特征,并验证了方案的可行性。实验表明:该识别方法识别效果较好,能够适应表情、光照的变换。
This paper briefly discusses the process of face normalization, eigenface,the theory of LDA algorithm and the realization process. The best description feature is obtained by utilizing the PCA and then the best classification feature is acquired by utilizing the LDA. This paper proves the feasibility of the method by experiment.It is proved that the method can get satisfying effect.The method can adapt to the change of face and illumination.
出处
《贵州工业大学学报（自然科学版）》
CAS
2005年第1期72-75,共4页
Journal of Guizhou University of Technology(Natural Science Edition)
基金
贵州省教育厅资助项目(黔科教(2003)205)
