基于最大差值的二维边界Fisher的人脸识别

Face Recognition Based on Two-dimensional Maximum Difference Marginal Fisher Analysis

提出了一种基于最大差值的二维边界Fisher的鉴别分析方法。该方法利用描述类间数据可分性的相似度矩阵Sp与描述类内数据紧致性的相似度矩阵Sc之差作为鉴别准则,从而避免了边界Fisher鉴别分析所遇到的小样本问题。所提方法是直接基于图像矩阵的,与以往的基于图像向量的方法相比,进一步提高了识别的正确率。另外,还揭示了基于最大差值的边界Fisher鉴别方法和边界Fisher鉴别的内在关系。在ORL和Yale人脸数据库上的实验表明,所提方法具有较高的识别率。

A novel two-dimensional maximum difference marginal Fisher discriminant analysis（2DMDMFA） was proposed for face recognition. The algorithm adopts the difference of similarity matrix Sp which characterizes the interclass reparability and similarity matrix S which characterizes the intraclass compactness as discriminant criterion. In such a way,the small sample size problem occurred in marginal Fisher analysis（MFA） is avoided. In addition,the construction of Sp and Sr is directly based on original training image matrices rather vectors. It is not necessary to convert the image matrix into high-dimensional image vector like those previous methods so that the recognition rate is raised. Besides, the relations between the maximum difference marginal Fisher analysis discriminant criterion and marginal Fisher analysis discriminant criterion for feature extraction were revealed. Experimental results on ORL and Yale face database show that the algorithm outperforms the traditional methods in recognition performance.