Volume : III, Issue : VIII, August - 2013

Non Subsampled Shearlet Transform Based Texture Classification Using Sub Band Energy

Mrs. M. Kanchana, Dr. P. Varalakshmi

Abstract :

In this paper, an efficient approach for the classification of texture images based on non subsampled shearlet transform (NSST) is proposed. The classification of texture is achieved by extracting sub band energy from the shearlet decomposed image. First, the texture image is decomposed by NSST at various decomposition levels with multidirections. Then the proposed sub band energy is extracted from each sub–band of the decomposed image. Sub band energies are used as features to classify the given texture image using robust nearest neighbor classifier. Brodatz database texture images are used to evaluate the proposed method. The performance is compared with state of art techniques involving wavelet transform, gabor transform and statistical features. The results show that the NSST based classification provides better classification accuracy

Keywords :

Article: Download PDF   DOI : 10.36106/ijar  

Cite This Article:

Mrs. M. Kanchana, Dr. P. Varalakshmi Non Subsampled Shearlet Transform Based Texture Classification Using Sub Band Energy Indian Journal of Applied Research, Vol.III, Issue.VIII August 2013

Number of Downloads : 800

References :