Bleeding Detection through Wireless Capsule Endoscopy (wce)

The wireless capsule endoscopy (WCE), is an imaging technology which is recently established and doesn’t require any wired device. This device detects abnormalities in GI tract i.e.( colon, esophagus, small intestine and stomach). A WCE video consists of 57000 images. It is very hard to examine by clinicians. To determine bleeding images out of fifty seven thousand WCE images makes the task very hard and expensive. Here,[19] our goal is to develop an automatic obscure bleeding detection method by using super pixel segmentation and[4] support vector machine (SVM) classifier. In this paper, SVM and super pixel segmentation is used for this problem. Our experiments show that SVM and super pixel segmentation[19] can be very efficient and may yield very high accuracy rate.