DocumentCode :
2988748
Title :
Subset selection using rough set in wavelet packet based texture classification
Author :
Wang, Qiong ; Li, Hong ; Liu, Jian
Author_Institution :
Sch. of Math. & Stat., Hua Zhong Univ. of Sci. & Technol., Wuhan
Volume :
2
fYear :
2008
fDate :
30-31 Aug. 2008
Firstpage :
662
Lastpage :
666
Abstract :
Rough set based attribute significance measure and reduction is proposed in this paper, after we decompose textures using wavelet packet and extract the l1-norm as features, condition attributes are discretized with equal width binning method. We deduce the classification rules with the selected feature subset. The classification performance is tested on a set of 13 Brodatz texture, the averaged classification results show that the proposed algorithm can get rid of redundancy and only a few of the features can fulfill the classification task without reducing accuracy.
Keywords :
feature extraction; image texture; pattern classification; rough set theory; wavelet transforms; Brodatz texture; rough set; subset selection; texture classification; wavelet packet decomposition; Discrete wavelet transforms; Feature extraction; Frequency; Image analysis; Image texture analysis; Information analysis; Pattern analysis; Wavelet analysis; Wavelet packets; Wavelet transforms; Attribute reduction; Rough set; Texture classification; Wavelet packet decomposition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-2238-8
Electronic_ISBN :
978-1-4244-2239-5
Type :
conf
DOI :
10.1109/ICWAPR.2008.4635862
Filename :
4635862
Link To Document :
بازگشت