Please use this identifier to cite or link to this item:
Title: A novel texture descriptor using over-complete wavelet transform and its fractal signature
Authors: Wang, Q
Feng, D
Issue Date: 2005
Publisher: Springer
Source: In WK Leow, MS Lew, TS Chua, WY Ma, L Chaisorn & EM Bakker (Eds.), Image and video retrieval : 4th international conference, CIVR 2005, Singapore, July 20-22, 2005 : proceedings, p. 476-486. Berlin ; New York: Springer, 2005 How to cite?
Series/Report no.: Lecture notes in computer science ; v. 3568
Abstract: In the paper, we proposed a novel feature descriptor using over-complete wavelet transform and wavelet domain based fractal signature for texture image analysis and retrieval. Traditionally, discrete wavelet frame took the first order derivative of smoothing function into account, which is equivalent to Canny edge detection, with the specific case using Gaussian function as smoothing function. The second order derivative Spline Wavelet has more stronger ability to distinguish the variation of the edge width than the first order one. The over-complete B-Spline wavelet scheme is discussed and the finite impulse response of over-complete wavelet transform is also represented in the paper. In feature extraction phase, 56 dimensional statistical features, including means and variances in positive and negative parts of wavelet coefficients, are extracted respectively. At the same time, the fractal signature based on the fractal surface area function in a Besov space is very accurate and robust for gray scale texture classification so that 24 dimensional over-complete wavelet based fractal feature is extracted. Experimental results have shown that the proposed method is reasonable to describe the characteristics of the texture in temporal-frequent and fractal domains and can achieve the highest retrieval rate comparing with Gabor filter, first order derivative over-complete wavelet transformation, and some other pyramid-structured wavelet transformation considered.
ISBN: 9783540278580
DOI: 10.1007/11526346_51
Appears in Collections:Book Chapter

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Last Week
Last month
Citations as of Dec 10, 2018

Google ScholarTM



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