Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.cviu.2012.05.003
Title: Scale-space texture description on SIFT-like textons
Authors: Xu, Y.
Huang, S.
Ji, H. 
Fermüller, C.
Keywords: Image feature
Multi-fractal analysis
Texture
Wavelet tight frame
Issue Date: Sep-2012
Citation: Xu, Y., Huang, S., Ji, H., Fermüller, C. (2012-09). Scale-space texture description on SIFT-like textons. Computer Vision and Image Understanding 116 (9) : 999-1013. ScholarBank@NUS Repository. https://doi.org/10.1016/j.cviu.2012.05.003
Abstract: Visual texture is a powerful cue for the semantic description of scene structures that exhibit a high degree of similarity in their image intensity patterns. This paper describes a statistical approach to visual texture description that combines a highly discriminative local feature descriptor with a powerful global statistical descriptor. Based upon a SIFT-like feature descriptor densely estimated at multiple window sizes, a statistical descriptor, called the multi-fractal spectrum (MFS), extracts the power-law behavior of the local feature distributions over scale. Through this combination strong robustness to environmental changes including both geometric and photometric transformations is achieved. Furthermore, to increase the robustness to changes in scale, a multi-scale representation of the multi-fractal spectra under a wavelet tight frame system is derived. The proposed statistical approach is applicable to both static and dynamic textures. Experiments showed that the proposed approach outperforms existing static texture classification methods and is comparable to the top dynamic texture classification techniques. © 2012 Elsevier Inc. All rights reserved.
Source Title: Computer Vision and Image Understanding
URI: http://scholarbank.nus.edu.sg/handle/10635/104076
ISSN: 10773142
DOI: 10.1016/j.cviu.2012.05.003
Appears in Collections:Staff Publications

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

Google ScholarTM

Check

Altmetric


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