Abstract:
This paper proposes a new Linear Discriminant Analysis(LDA) for face recognition based on the graph embedding and regularization. The unsupervised optimal class separate criterion is built, and it proposes a method to get this projection vector on the graph embedding frame. It can get a huge save of computational consumption and utilize the class information of samples more effectively. Experimental results demonstrate the effectiveness and efficiency of this method.
Key words:
face recognition,
graph embedding,
regularization,
Linear Discriminant Analysis(LDA)
摘要:
提出一种基于图嵌入正则化的人脸线性判别分析方法。构造非监督最优类可分准则,基于图嵌入理论,求解该最优类可分准则下的最优投影向量,在非监督的图嵌入框架下利用样本局部类别信息提高人脸识别率,降低矩阵计算复杂度。在典型的人脸数据库上的实验证明了该方法的有效性。
关键词:
人脸识别,
图嵌入,
正则化,
线性判别分析
CLC Number:
YANG An-Beng, CHEN Song-Jiao, HU Feng-. Face Linear Discriminant Analysis Based on Graph Embedding and Regularization[J]. Computer Engineering, 2011, 37(12): 164-165.
杨安平, 陈松乔, 胡鹏. 基于图嵌入正则化的人脸线性判别分析[J]. 计算机工程, 2011, 37(12): 164-165.