Learning Discriminative Canonical Correlations for Object Recognition with Image Sets
We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object’s appearance due to changing camera pose and lighting conditions. The concept of Canonical Correlations (also known as principal angles) can be viewed as the angles between two subspaces. As a way of comparing sets of vectors or images, canonical correlations offer many benefits in accuracy, efficiency, and robustness compared to the classical parametric distribution-based and non-parametric sample-based methods. Here, this is demonstrated experimentally for reasonably sized data sets using existing methods exploiting canonical correlations. Motivated by their proven effectiveness, a novel discriminative learning over sets is proposed for object recognition. Specifically, inspired by classical Linear Discriminant Analysis (LDA), we develop a linear discriminant function that maximizes the canonical correlations of within-class sets and minimizes the canonical correlations of between-class sets. The proposed method significantly outperforms the state-of-the-art methods on two different object recognition problems using face image sets with arbitrary motion captured under different illuminations and image sets of five hundred general object categories taken at different views.
KeywordsFace Recognition Singular Value Decomposition Object Recognition Linear Discriminant Analysis Canonical Correlation
Unable to display preview. Download preview PDF.
- 1.Lee, K., Yang, M., Kriegman, D.: Video-based face recognition using probabilistic appearance manifolds. In: CVPR, pp. 313–320 (2003)Google Scholar
- 4.Arandjelović, O., Shakhnarovich, G., Fisher, J., Cipolla, R., Darrell, T.: Face recognition with image sets using manifold density divergence. In: CVPR (2005)Google Scholar
- 5.Satoh, S.: Comparative Evaluation of Face Sequence Matching for Content-based Video Access. In: Int’l Conf. on Automatic Face and Gesture Recognition (2000)Google Scholar
- 6.Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. PAMI 19(7), 711–720 (1997)Google Scholar
- 8.Yamaguchi, O., Fukui, K., Maeda, K.: Face recognition using temporal image sequence. AFG 10, 318–323 (1998)Google Scholar
- 10.Kim, T.K., Arandjelović, O., Cipolla, R.: Learning over Sets using Boosted Manifold Principal Angles (BoMPA). In: BMVC (2005)Google Scholar
- 11.Fukui, K., Yamaguchi, O.: Face recognition using multi-viewpoint patterns for robot vision. In: Int’l Symp. of Robotics Research (2003)Google Scholar
- 16.Toshiba. Facepass., http://www.toshiba.co.jp/rdc/mmlab/tech/w31e.htm
- 17.Oja, E.: Subspace Methods of Pattern Recognition. Research Studies Press (1983)Google Scholar