Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/104636
Title: Subspace descriptor for texture and its applications
Authors: Law, Y.N.
Lee, H.K.
Yip, A.M. 
Keywords: Feature extraction
Image segmentation
Image texture analysis
Issue Date: 2010
Citation: Law, Y.N.,Lee, H.K.,Yip, A.M. (2010). Subspace descriptor for texture and its applications. Proceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010 2 : 499-504. ScholarBank@NUS Repository.
Abstract: This paper addresses the issue of feature relevance in modeling texture. We propose a new subspace descriptor and an energy minimization model to find the relevant feature subspace at each location. For each pixel, we use the feature distribution in its local patch to captures the relevant feature subspace based on entropy regularisation. Moreover, based on the new descriptor, we propose a novel distance measure which can be used for texture detection. Such a distance and subspace descriptor are also applied for improving texture segmentation and image retrieval. Superior results are obtained compared to existing approaches which confirm the usefulness of the proposed subspace descriptor in image processing.
Source Title: Proceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
URI: http://scholarbank.nus.edu.sg/handle/10635/104636
ISBN: 9781601321541
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

41
checked on Nov 2, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.