Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval Export

@article{citeulike:2310513, abstract = {Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for human gait recognition and content-based image retrieval (CBIR). In this paper, we present extensions of our recently proposed marginal Fisher analysis (MFA) to address these problems. For human gait recognition, we first present a direct application of MFA, then inspired by recent advances in matrix and tensor-based dimensionality reduction algorithms, we present matrix-based MFA for directly handling 2-D input in the form of gray-level averaged images. For CBIR, we deal with the relevance feedback problem by extending MFA to marginal biased analysis, in which within-class compactness is characterized only by the distances between each positive sample and its neighboring positive samples. In addition, we present a new technique to acquire a direct optimal solution for MFA without resorting to objective function modification as done in many previous algorithms. We conduct comprehensive experiments on the USF HumanID gait database and the Corel image retrieval database. Experimental results demonstrate that MFA and its extensions outperform related algorithms in both applications.}, author = {Xu, Dong and Yan, Shuicheng and Tao, Dacheng and Lin, S. and Zhang, Hong-Jiang}, booktitle = {Image Processing, IEEE Transactions on}, citeulike-article-id = {2310513}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TIP.2007.906769}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4337772}, doi = {10.1109/TIP.2007.906769}, journal = {Image Processing, IEEE Transactions on}, keywords = {fda, kernel-method, manifold-learning, metric-learning}, number = {11}, pages = {2811--2821}, posted-at = {2008-01-31 10:41:09}, priority = {3}, title = {Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval}, url = {http://dx.doi.org/10.1109/TIP.2007.906769}, volume = {16}, year = {2007} }

TY - JOUR ID - citeulike:2310513 L3 - citeulike-article-id:2310513 N2 - Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for human gait recognition and content-based image retrieval (CBIR). In this paper, we present extensions of our recently proposed marginal Fisher analysis (MFA) to address these problems. For human gait recognition, we first present a direct application of MFA, then inspired by recent advances in matrix and tensor-based dimensionality reduction algorithms, we present matrix-based MFA for directly handling 2-D input in the form of gray-level averaged images. For CBIR, we deal with the relevance feedback problem by extending MFA to marginal biased analysis, in which within-class compactness is characterized only by the distances between each positive sample and its neighboring positive samples. In addition, we present a new technique to acquire a direct optimal solution for MFA without resorting to objective function modification as done in many previous algorithms. We conduct comprehensive experiments on the USF HumanID gait database and the Corel image retrieval database. Experimental results demonstrate that MFA and its extensions outperform related algorithms in both applications. IS - 11 JF - Image Processing, IEEE Transactions on EP - 2821 TI - Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval VL - 16 T2 - Image Processing, IEEE Transactions on SP - 2811 KW - fda KW - kernel-method KW - manifold-learning KW - metric-learning AU - Xu, Dong AU - Yan, Shuicheng AU - Tao, Dacheng AU - Lin, S AU - Zhang, Hong-Jiang PY - 2007/// UR - http://dx.doi.org/10.1109/TIP.2007.906769 ER -