Image Euclidean Distance-based Two-dimensional Local Diversity Preserving Projection
-
摘要: 主成分分析可以较好地保持数据的全局多样性几何属性, 在模式识别、机器学习、图像识别等领域有着很重要的作用. 缺点是他不能较好地保持局部数据的多样性几何属性, 且忽略了图像像素之间的相互关系, 导致算法性能不够好, 且对模式形变比较敏感. 对此问题, 提出了一种基于图像欧氏距离的二维局部多样性保持投影. 该方法利用邻接图描述局部数据之间的变化关系, 然后利用图像欧氏距离度量数据间的多样性几何属性, 有效地将图像像素之间的相互关系嵌入到目标函数中. 和主成分分析相比, 所提方法较好地保持了局部数据的多样性几何属性, 而且明确考虑了图像像素之间的相互关系, 对模式形变具有好的鲁棒性. 在Yale, AR及PIE三个人脸库上的实验结果证明了所提算法的有效性.Abstract: Previous works have demonstrated that principal component analysis (PCA) well preserves the global information, i.e., diversity of data, and plays an important role in pattern recognition, machine learning, and image processing. However, PCA ignores the spatial relationships among pixels in images and does not well preserve the local diversity of data, which will impair the recognition accuracy and lead to unstableness to the perturbation of images. To address these problems, a novel approach, namely image Euclidean distance based two-dimensional local diversity preserving projection (IED-2DLDPP) is proposed. IED-2DLDPP constructs an adjacency graph to model the variation of data and employs image Euclidean distance to characterize the diversity of data, which explicitly considers the spatial relationships among pixels in the images. Extensive experiments on Yale, AR, and PIE databases show the efficiency of the proposed method.
-
[1] Yan S C, Xu D, Zhang B Y, Zhang H J. Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51 [2] Fukunaga K. Introduction to statistical Pattern Recognition (Second edition). New York: Academic Press, 1990 [3] Turk M A, Pentland A P. Face recognition using eigenfaces. In: Proceedings of the 1991 IEEE Computer Society Conferences on Computer Vision and Pattern Recognition. Maui, HI: IEEE, 1991. 586-591 [4] Belhumeur P N, Hespanha J P, Kriegman D J. Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720 [5] Yang J, Zhang D, Frangi A F, Yang J Y. Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137 [6] Gao Quan-Xue, Liang Yan, Pan Quan, Cheng Yong-Mei. Face recognition based on expressive features. Acta Automatica Sinica, 2006, 32(3): 386-392 (高全学, 梁彦, 潘泉, 程咏梅. 基于描述特征的人脸识别研究. 自动化学报, 2006, 32(3): 386-392) [7] He R, Hu B G, Zheng W S, Kong X W. Robust principal component analysis based on maximum correntropy criterion. IEEE Transactions on Image Processing, 2011, 20(6): 1485-1494 [8] Fang Wei-Tao, Ma Peng, Cheng Zheng-Bin, Yang Dan, Zhang Xiao-Hong. 2-dimensional projective non-negative matrix factorization and its application to face recognition. Acta Automatica Sinica, 2012, 38(9): 1503-1512 (方蔚涛, 马鹏, 成正斌, 杨丹, 张小洪. 二维投影非负矩阵分解算法及其在人脸识别中的应用. 自动化学报, 2012, 38(9): 1503-1512) [9] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science, 2000, 290(5500): 2323-2326 [10] Kong D G, Ding C H Q, Huang H, Nie F P. An iterative locally linear embedding algorithm. In: Proceeding of the 29th International Conference on Machine Learning (ICML), Edinburgh, Scotland, 2012. 1647-1654 [11] Tenenbaum J B, de Silva V, Langford J C. A global geometric framework for nonlinear dimensionality reduction. Science, 2000, 290(5500): 2319-2323 [12] You D, Hamsici O C, Martinez A M. Kernel optimization in discriminant analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(3): 631-638 [13] Scholkopf B, Smola A, Muller K R. Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 1998, 15(5): 1299-1319 [14] He X F, Yan S C, Hu Y X, Niyogi P, Zhang H J. Face recognition using laplacianfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340 [15] He X F, Cai D, Yan S C, Zhang H J. Neighborhood preserving embedding. In: Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China: IEEE, 2005. 1208-1213 [16] Fan Z Z, Xu Y, Zhang D. Local linear discriminant analysis framework using sample neighbors. IEEE Transactions on Neural Networks, 2011, 22(7): 1119-1132 [17] Huang Y, Xu D, Nie F P. Semi-supervised dimension reduction using trace ratio criterion. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(3): 519-526 [18] Gao Quan-Xue, Xie De-Yan, Xu Hui, Li Yuan-Zheng, Gao Xi-Quan. Supervised feature extraction based on information fusion of local structure and diversity information. Acta Automatica Sinica, 2010, 36(8): 1107-1114 (高全学, 谢德燕, 徐辉, 李远征, 高西全. 融合局部结构和差异信息的监督特征提取算法. 自动化学报, 2010, 36(8): 1107-1114) [19] Hu D W, Feng G Y, Zhou Z T. Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition. Pattern Recognition, 2007, 40(1): 339-342 [20] Gao Q X, Xu H, Li Y Y, Xie D Y. Two-dimensional supervised local similarity and diversity projection. Pattern Recognition, 2010, 43(10): 3359-3363 [21] Gao Q X, Liu J J, Zhang H J, Hou J, Yang X J. Enhanced fisher discriminant criterion for image recognition. Pattern Recognition, 2012, 45(10): 3717-3724 [22] Gao Q X, Zhang H J, Liu J J. Two-dimensional margin, similarity and variation embedding. Neurocomputing, 2012, 86: 179-183 [23] Postnikov M M. Lectures in Geometry, Semester I: Analytic Geometry. Moscow: Mir Publishers, 1982 [24] Wang L W, Zhang Y, Feng J F. On the Euclidean distance of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1334-1339 [25] Golub G H, Van Loan C F. Matrix Computations (Third edition). Baltimore: The Johns Hopkins University Press, 1996
点击查看大图
计量
- 文章访问数: 1535
- HTML全文浏览量: 47
- PDF下载量: 1681
- 被引次数: 0