Authors:
Osamu Yamaguchi
1
;
2
and
Kazuhiro Fukui
2
Affiliations:
1
Corporate Research and Development Center, Toshiba Corporation, Japan
;
2
Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Japan
Keyword(s):
Image-set based Classification, Whitening Transformation, Multiple Pseudo-Whitened Mutual Subspace Method, Ensemble Method, CNN Features.
Abstract:
This paper proposes a new image-set-based classification method, called Multiple Pseudo-Whitened Mutual Subspace Method (MPWMSM), constructed under multiple pseudo-whitening. Further, it proposes to combine this method with Convolutional Neural Network (CNN) features to perform higher discriminative performance. MPWMSM is a type of subspace representation-based method like the mutual subspace method (MSM). In these methods, an image set is compactly represented by a subspace in high dimensional vector space, and the similarity between two image sets is calculated by using the canonical angles between two corresponding class subspaces. The key idea of MPWMSM is twofold. The first is to conduct multiple different whitening transformations of class subspaces in parallel as a natural extension of the whitened mutual subspace method (WMSM). The second is to discard a part of a sum space of class subspaces in forming the whitening transformation to increase the classification ability and t
he robustness against noise. We demonstrate the effectiveness of our method on tasks of 3D object classification using multi-view images and hand-gesture recognition and further verify the validity of the combination with CNN features through the Youtube Face dataset (YTF) recognition experiment.
(More)