摘要
针对非参数特征分析(nonparametric feature analysis,NFA)方法需将图像矩阵转化为向量后进行特征提取,导致数据维数很大,计算复杂等缺点,提出M2DPCA+NFA相结合的方法。新方法对图像矩阵进行分块,再采用2DPCA进行特征提取,再实行NFA。该方法能有效提取图像的局部特征,而由于考虑到类内、类间的差异,可弥补PCA的缺陷。在ORL人脸库和XM2VTS人脸库上对LDA方法、NFA方法以及本方法分别进行了评价和测试,结果显示,所提方法在识别效果上优于LDA方法和NFA方法。
In this paper an improved face recognition algorithm is proposed based on the combination of modular 2DPCA and NFA because of NFA.NFA first transforms an image matrix to a vector which caused high dimensionality and computational complexity.In this paper the original images are divided into modular sub-images,then NFA is utilized on the new pattern which is obtained by modular 2DPCA to extract the final features from the sub-images.The new method considered the difference of between-classes and within-class while extracted local feature of the image,and make up the flaw of the PCA.The experimental results obtained on the facial database ORL and XM2VTS show that the recognition performance of the new method is superior to that of the primary method of LDA and NSA.
出处
《电子设计工程》
2011年第13期163-165,共3页
Electronic Design Engineering