DocumentCode :
2636055
Title :
Texture classification using wavelets with a cluster-based feature extraction
Author :
Yu, Gang ; Kamarthi, Sagar V.
Author_Institution :
Shenzhen Grad. Sch., Dept. of Mech. Eng. & Autom., Harbin Inst. of Technol. (HIT), Shenzhen
fYear :
2008
fDate :
10-12 Dec. 2008
Firstpage :
1
Lastpage :
6
Abstract :
After several decades of research, the development of an effective feature extraction method for texture classification is still an ongoing effort. In this paper, we propose a novel approach for texture classification using a new cluster-based feature extraction method that divides the matrices of computed two-dimensional wavelet coefficients into clusters. The features that contain the information effective for classifying texture images are computed from the energy content of the clusters, and these feature vectors serve as input patterns to a neural network for texture classification. The results show that the discrimination performance obtained with the proposed cluster-based feature extraction method is superior to the performance obtained using conventional feature extraction methods, and robust to the rotation and scale invariant texture classification.
Keywords :
discrete wavelet transforms; feature extraction; image classification; image texture; neural nets; pattern clustering; vectors; cluster-based feature extraction; discrimination performance; feature vector; image texture classification; neural network; two-dimensional wavelet coefficient; Discrete wavelet transforms; Feature extraction; Frequency; Gabor filters; Image texture analysis; Mechanical engineering; Robustness; Signal analysis; Statistical analysis; Wavelet analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems and Control in Aerospace and Astronautics, 2008. ISSCAA 2008. 2nd International Symposium on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4244-3908-9
Electronic_ISBN :
978-1-4244-2386-6
Type :
conf
DOI :
10.1109/ISSCAA.2008.4776161
Filename :
4776161
Link To Document :
بازگشت