基于拉普拉斯方向的差值线性判别分析  

Different Linear Discriminant Analysis Based on Laplacian Orientations

作　　者：李照奎[1,2] 丁立新[1] 王岩[2] 何进荣[1] 周凌云[1] 

机构地区：[1]武汉大学软件工程国家重点实验室武汉大学计算机学院,武汉430072 [2]沈阳航空航天大学计算机学院,沈阳110136

出　　处：《计算机科学》2014年第6期161-165,203,共6页Computer Science

基　　金：国家自然科学基金(60975050,60902053);广东省省部产学研结合专项(2011B090400477);珠海市产学研合作专项(2011A050101005,2012D0501990016);珠海市重点实验室科技攻关项目(2012D0501990026)资助

摘　　要：标准的LDA方法通常有3个问题:1)为了确保类内散度矩阵的非奇异性,必须首先通过PCA进行维数约简,这限制了对更多维数空间的使用;2)当每人只有单个训练样本时,类内散度矩阵必然奇异,此时LDA无法工作;3)缺乏对像素间的局部相关性的考虑。为了解决这些问题,提出一种基于拉普拉斯方向的差值线性判别分析方法。该方法通过拉普拉斯方向实现更鲁棒的图像相异性测度,通过引入差值散度矩阵来避免类内散度矩阵的奇异性。实验结果显示,该算法对表情变化、光照改变及不同遮挡情况获得了更高的识别率,尤其针对光照变化,效果更加显著。For the traditional linear discriminant analysis method,there are usually three questions：1） In order to ensure that the within-class scatter matrix is nonsingular,the principal component analysis must firstly is performed,which limits the effect of multidimensional space.2） If the number of training samples per person is single,the within-class scatter matrix is generally singular,and the method does not work.3）Without considering the partial correlation between pixels.To address these problems,this paper proposed a different linear discriminant analysis based on Laplacian orientations.The usage of the Laplacian orientations results in a more robust dissimilarity measures between images.The introduction of the difference scatter matrix avoids the singularity of the within-class scatter matrix.Experiments show that the proposed method has better robustness for facial expressions,illumination changes and different occlusions,and achieves a higher recognition rate.Especially for illumination changes,the effect is better.

关 键 词：拉普拉斯方向 维数约简 线性判别分析 鲁棒的相异性度量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]