Title: Jawbone texture classification using contourlets

Authors: T. Kalpalatha Reddy, N. Kumaravel

Addresses: SKR Engineering College/ECE, Anna University, Chennai, India. ' College of Engineering/ECE, Anna University, Chennai, India

Abstract: In this paper, a feasibility study of human jawbone CT data set classification using contourlet transform is presented. A number of first-order, second-order texture parameters and grey-level run-length parameters are derived from the sub-bands of the contourlet decomposition and are used for classification. The results shows that by using the SVM classifier the combination of the features from grey level and 1st order statistics achieved overall classification accuracy >0.7273. Features selected from the contourlet-based co-occurrence Matrix performed better with overall classification accuracy >0.8667. To increase the success rate, the classification is done using the combination of CSF and CCF which produced a mean success rate of 100%.

Keywords: contourlet transforms; dental CT; SVM classifiers; linear classifiers; jawbone texture; texture classification; computed tomography; support vector machines; feature selection.

DOI: 10.1504/IJBET.2010.035510

International Journal of Biomedical Engineering and Technology, 2010 Vol.4 No.4, pp.370 - 377

Published online: 30 Sep 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article