Image Set Classification Using Holistic Multiple Order Statistics Features and Localized Multi-kernel Metric Learning
Authors:
- Jiwen LuJLJiwen Lu
- Gang WangGWGang Wang
- Pierre MoulinPMPierre Moulin
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 329-336
Abstract
This paper presents a new approach for image set classification, where each training and testing example contains a set of image instances of an object captured from varying viewpoints or under varying illuminations. While a number of image set classification methods have been proposed in recent years, most of them model each image set as a single linear subspace or mixture of linear subspaces, which may lose some discriminative information for classification. To address this, we propose exploring multiple order statistics as features of image sets, and develop a localized multi-kernel metric learning (LMKML) algorithm to effectively combine different order statistics information for classification. Our method achieves the state-of-the-art performance on four widely used databases including the Honda/UCSD, CMU Mobo, and Youtube face datasets, and the ETH-80 object dataset.Keywords
This publication has 24 references indexed in Scilit:
- Face Recognition Using Sparse Approximated Nearest Points between Image SetsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Sparse approximated nearest points for image set classification2011
- Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching2011
- Is that you? Metric learning approaches for face identification2009
- Multiple Kernel Clustering2009
- Fast image search for learned metrics2008
- Localized multiple kernel learning2008
- Discriminative Learning and Recognition of Image Set Classes Using Canonical CorrelationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- From still image to video-based face recognition: an experimental analysis2004
- Face recognition using temporal image sequence2002