A novel method for bleeding detection in Wireless Capsule Endoscopic images

Wireless Capsule Endoscopy is a technique used to detect the abnormalities in the interior of the small intestine. It empowers detailed inspection of interior of the entire gastrointestinal tract in a non-invasive manner. In this paper, a novel method for bleeding detection in WCE image is proposed based on Histogram analysis and Bleeding detector functions. Different histogram statistical parameters such as mean, variance, entropy, skewness etc. are calculated and these features are used to calculate the bleeding detector functions. Depending on the ability to detect the bleeding images, mean and variance of histogram of the WCE image in HSV colour space are considered. Random tree classifier is employed for the purpose of classification. The outcomes demonstrate that the proposed method can accurately detect bleeding and non bleeding images with high accuracy, sensitivity and specificity compared to that of existing methods.