Image classification with manifold learning for out-of-sample data

Han, Yahong, Xu, Zhongwen, Ma, Zhigang and Huang, Zi (2013) Image classification with manifold learning for out-of-sample data. Signal Processing, 93 8: 2169-2177. doi:10.1016/j.sigpro.2012.05.036

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Han, Yahong
Xu, Zhongwen
Ma, Zhigang
Huang, Zi
Title Image classification with manifold learning for out-of-sample data
Journal name Signal Processing   Check publisher's open access policy
ISSN 0165-1684
1872-7557
Publication date 2013-08-01
Year available 2012
Sub-type Article (original research)
DOI 10.1016/j.sigpro.2012.05.036
Open Access Status Not yet assessed
Volume 93
Issue 8
Start page 2169
End page 2177
Total pages 9
Place of publication Netherlands
Publisher Elsevier
Language eng
Subject 2207 Control and Systems Engineering
1712 Software
1711 Signal Processing
1707 Computer Vision and Pattern Recognition
2208 Electrical and Electronic Engineering
Abstract The successful applications of manifold learning in computer vision and multimedia research show that the geodesic distance along the manifold is more meaningful than Euclidean distance in the linear space. Therefore, in order to get better performance of image classification, it is preferable to have classifier defined on the low-dimensional manifold. However, most of the manifold learning algorithms do not provide explicit mapping of the unseen data. In this paper, we propose a framework of image classification with manifold learning for out-of-sample data. The method of local and global regressive mapping for manifold learning simultaneously learns the low-dimensional embedding of the input data and a mapping function for out-of-sample data extrapolation. The low-dimensional manifold embedding of large-scale images can be obtained by the mapping functions. Utilizing the supervised classifier, we predict class labels for test images in the learned low-dimensional manifold. Experiments on two large-scale image datasets demonstrate that the proposed framework has better performance of image classification than the kernelized dimension reduction methods.
Formatted abstract
The successful applications of manifold learning in computer vision and multimedia research show that the geodesic distance along the manifold is more meaningful than Euclidean distance in the linear space. Therefore, in order to get better performance of image classification, it is preferable to have classifier defined on the low-dimensional manifold. However, most of the manifold learning algorithms do not provide explicit mapping of the unseen data. In this paper, we propose a framework of image classification with manifold learning for out-of-sample data. The method of local and global regressive mapping for manifold learning simultaneously learns the low-dimensional embedding of the input data and a mapping function for out-of-sample data extrapolation. The low-dimensional manifold embedding of large-scale images can be obtained by the mapping functions. Utilizing the supervised classifier, we predict class labels for test images in the learned low-dimensional manifold. Experiments on two large-scale image datasets demonstrate that the proposed framework has better performance of image classification than the kernelized dimension reduction methods.

Highlights ► We propose a framework of image classification with manifold learning for out-of-sample data. ► We learn the low-dimensional embedding of the input images. ► We learn a mapping function for out-of-sample images. ► We get better performance compared with kernelized dimension reduction methods.
Keyword Image classification
Manifold learning
Out-of-sample
Nonlinear dimensionality reduction
Retrieval
Distance
Similarity
Eigenmaps
Framework
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ
Additional Notes Available online 13 June 2012

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2014 Collection
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 16 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 20 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Sun, 09 Jun 2013, 10:07:29 EST by System User on behalf of School of Information Technol and Elec Engineering