Bleeding detection in wireless capsule endoscopy images by support vector classifier

Wireless capsule endoscopy (WCE) is a great breakthrough for Gastrointestinal (GI) Tract diagnoses, and it can view the entire gastrointestinal tract, especially the small intestine without invasiveness and sedation. However, a tough problem associated with this new technology is that too many images to be inspected by naked eyes cause a huge burden to physicians, so it is significant to find an automatic diagnosis method. In this paper, a new automatic algorithm for bleeding detection in WCE images is proposed. This new approach mainly focuses on color feature which is also a very effective clue used by physicians for diagnosis. We propose six color features in HSI color space to discriminate between bleeding and normal status. Then we use support vector classifier to verify the performance of the proposed features and judge the status of the images. Experimental results show that the proposed features and classification method is effective and the average accuracy can achieve approximately 97%.