P.Mohanapriya, M.Sangeetha, Mahendra Institute of Technology, Namakkal, Tamilnadu, India.
DOI : 01.0401/ijaict.2014.01.30
International Journal of Advanced Information and Communication Technology
Received On : September 14, 2014
Revised On : October 21, 2014
Accepted On : November 17, 2014
Published On : December 05, 2014
Volume 01, Issue 08
Pages : 153-159
Abstract
Wireless Capsule Endoscopy (WCE) is a device to detect abnormalities in colon, oesophagus, small intestinal and stomach to distinguish bleeding in WCE images from non-bleeding is a hard job by human reviewing and very time consuming. WCE is a new technology that enables close examination of the interior portion of the entire small intestine without the surgery. In digital image processing the segmentation and classification is very difficult task. If the segmented result is poor then the detection accuracy is very poor. In this paper, we propose a new method for segmentation and classification of bleeding images in WCE video using the threshold technique and neural networks method to obtain the high detection accuracy of bleeding and non-bleeding images. First, the image is converting into HSI colour domain since it is closer to human perception than the other colour domains. Second we segment each images into bleeding and non-bleeding regions using threshold technique. Finally we classify the segmented images into bleeding and non-bleeding by the neural network method with the help of GLCM feature extraction to obtain the better classification performance.
Keywords
Wireless Capsule Endoscopy, Normalized Cut Segmentation, Threshold Technique, Neural Network, Gray Level Co-Occurrence Matrix.
Cite this article
P.Mohanapriya, M.Sangeetha, “An Efficient Approach to Detect Bleeding Region in GI Tract Using Segmentation and Classification Techniques ” INTERNATIONAL JOURNAL OF ADVANCED INFORMATION AND COMMUNICATION TECHNOLOGY, pp.153-159, December 05, 2014.
Copyright
© 2014 P.Mohanapriya, M.Sangeetha. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.