针对表情和光照变化等对人脸识别影响的问题,提出一种基于子模式双向二维线性判别分析(Sub-pattern two-di-rectional two-dimensional linear discriminant analysis,Sp-(2D)2 LDA)的人脸识别方法。该方法首先对原图像进行分块处理,并保持子块间的空间关系,然后对各个子训练样本集从行方向和列方向同时利用2DLDA 进行特征抽取,最后把各个子特征矩阵拼接成一对应原始图像的特征矩阵,并采用最近邻分类器进行分类识别。在 ORL 及 Yale 人脸库上的试验结果表明,Sp-(2D)2 LDA 有效降低了鉴别特征的维数,减少了表情和光照变化的影响,获得了较好的识别性能。
To reduce the impacts of the variations of expression and illumination,a novel face recogni-tion method based on sub-pattern two-directional two-dimensional linear discriminant analysis (Sp-(2D)2 LDA)is presented in this paper.Firstly,Sp-(2D)2 LDA divides the original images into smaller sub-images and keeps the spatial relationship between the sub-images.Secondly,it simultaneously ap-plies 2DLDA to the subsets of the training samples in the row and column directions to extract local sub-features.Finally,the sub-features are synthesized into global features and nearest neighbor clas-sifier is used for classification.The experimental results on Yale and ORL face databases show that the proposed Sp-(2D)2 LDA method effectively reduce not only the dimension of the eigenvectors,but also the influence of variations in illumination and facial expression.Thus,the proposed method has better classification performances than the other related methods.
参考文献
| [1] | 李鹏飞;许金凯;韩文波;宋鸿飞.基于S3C2440的人脸识别平台的设计[J].液晶与显示,2014(3):417-421. |
| [2] | 李定珍;郭建昌.B2DPCA和ELM人脸识别算法研究[J].液晶与显示,2013(3):440-445. |
| [3] | Adini Y.;Moses Y..Face recognition: the problem of compensating for changes in illumination direction[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,19977(7):721-732. |
| [4] | Belhumeur P.N.;Hespanha J.P..Eigenfaces vs. Fisherfaces: recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,19977(7):711-720. |
| [5] | 周大可;杨新;彭宁嵩.改进的线性判别分析算法及其在人脸识别中的应用[J].上海交通大学学报,2005(4):527-530. |
| [6] | 庄哲民;张阿妞;李芬兰.基于优化的LDA算法人脸识别研究[J].电子与信息学报,2007(9):2047-2049. |
| [7] | Jian Yang;Zhang D.;Frangi A.F.;Jing-yu Yang.Two-dimensional PCA: a new approach to appearance-based face representation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,20041(1):131-137. |
| [8] | Ming Li;Baozong Yuan.2D-LDA: A statistical linear discriminant analysis for image matrix[J].Pattern recognition letters,20055(5):527-532. |
| [9] | Yang J;Zhang D;Yong X;Yang JY.Two-dimensional discriminant transform for face recognition[J].Pattern Recognition: The Journal of the Pattern Recognition Society,20057(7):1125-1129. |
| [10] | Noushath S;Kumar GH;Shivakumara P.(2D)(2) LDA: An efficient approach for face recognition[J].Pattern Recognition: The Journal of the Pattern Recognition Society,20067(7):1396-1400. |
| [11] | 王文豪;严云洋.基于图像分块的LDA人脸识别[J].计算机工程与设计,2007(12):2889-2891. |
| [12] | 延伟东;彭国华.基于分块FLD的图像特征提取方法[J].科学技术与工程,2006(19):3107-3110. |
| [13] | 王磊;武敬飞;贾莉.一种基于双向模块2DLDA的人脸识别方法[J].电子测量与仪器学报,2013(8):760-765. |
| [14] | Chen SC;Zhu YL.Subpattern-based principle component analysis[J].Pattern Recognition: The Journal of the Pattern Recognition Society,20045(5):1081-1083. |
| [15] | 张先武;郭雷.基于子模式双向二维主成分分析的人脸识别[J].光电子·激光,2009(11):1498-1502. |
| [16] | Han Ke;Zhu Xiuchang.RESEARCH ON TWO-DIMENSIONAL LDA FOR FACE RECOGNITION[J].电子科学学刊（英文版）,2006(06):943-947. |
| [17] | 杜海顺;柴秀丽;汪凤泉;张帆.一种基于双向2DLDA特征融合的人脸识别方法[J].仪器仪表学报,2009(9):1880-1885. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%