Abnormal image detection using texton method in wireless capsule endoscopy videos

Authors:
Ruwan Dharshana Nawarathna;JungHwan Oh;Xiaohui Yuan;Jeongkyu Lee;Shou Jiang Tang
Affiliations:
Department of Computer Science and Engineering, University of North Texas, Denton, TX, U.S.A;Department of Computer Science and Engineering, University of North Texas, Denton, TX, U.S.A;Department of Computer Science and Engineering, University of North Texas, Denton, TX, U.S.A;Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT, U.S.A;Shou Jiang Tang, Endoscopy Center, Trinity Mother Frances Hospitals and Clinics, Tyler, TX, U.S.A
Venue:
ICMB'10 Proceedings of the Second international conference on Medical Biometrics
Year:
2010

Citing 7
Cited 0

Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons

International Journal of Computer Vision
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Classifying Images of Materials: Achieving Viewpoint and Illumination Independence

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
A Statistical Approach to Texture Classification from Single Images

International Journal of Computer Vision - Special Issue on Texture Analysis and Synthesis
Image retrieval based on the texton co-occurrence matrix

Pattern Recognition
Face recognition with local gabor textons

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of the main goals of Wireless Capsule Endoscopy (WCE) is to detect the mucosal abnormalities such as blood, ulcer, polyp, and so on in the gastrointestinal tract. Only less than 5% of total 55,000 frames of a WCE video typically have abnormalities, so it is critical to develop a technique to automatically discriminate abnormal findings from normal ones. We introduce “Texton” method which has been successfully used for image texture classification in non-medical domains. A histogram of Textons (exemplar responses occurring after convolving an image with a set of filters called “Filter bank”) called a “Texton Histogram” is used to represent an abnormal or a normal region. Then, a classifier (i.e., SVM or K-NN, and etc.) is trained using the Texton Histograms to distinguish images with abnormal regions from ones without them. Experimental results on our current data set show that the proposed method achieves promising performances.