DocumentCode :
2582568
Title :
Contourlet based feature extraction and classification for Wireless Capsule Endoscopic images
Author :
Junzhou, Chen ; Run, He ; Li, Zhang ; Qiang, Peng ; Tao, Gan
Author_Institution :
Dept. of Comput. Sci. & Technol., Southwest Jiaotong Univ., Chengdu, China
Volume :
1
fYear :
2011
fDate :
15-17 Oct. 2011
Firstpage :
219
Lastpage :
223
Abstract :
Wireless Capsule Endoscopy (WCE) is a late-model non-invasive device to detect abnormalities in small intestine. The traditional diagnostic method that only depending on clinicians´ naked eyes is time-consuming and labor-intensive. It is necessary to develop a computer-aided system to alleviate the burden of clinicians. In this paper, a new color-texture feature extraction method is proposed for the classification of normal and abnormal WCE tissue images. The Contourlet Transform is introduced and used for each color channel of each WCE image in HSV color space. Finally, we construct a 288-dimensions feature vector by calculating the 3-order color moments for each baseband generated by using the Contourlet Transform. Real experiments using different classifiers in various color spaces are implemented to evaluate the performance of the proposed method.
Keywords :
biological tissues; endoscopes; feature extraction; image classification; image colour analysis; image texture; medical image processing; transforms; 3-order color moments; HSV color space; WCE tissue image classification; color channel; color-texture feature extraction method; computer-aided system; contourlet transform; contourlet-based feature extraction; feature classification; small-intestine abnormality detection; wireless capsule endoscopic images; Endoscopes; Feature extraction; Hemorrhaging; Image color analysis; Intestines; Support vector machines; Transforms; Feature Extraction and Classification; The Contourlet Transform; Wireless Capsule Endoscopy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering and Informatics (BMEI), 2011 4th International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9351-7
Type :
conf
DOI :
10.1109/BMEI.2011.6098233
Filename :
6098233
Link To Document :
بازگشت