Abstract
Wireless capsule endoscopy (WCE) is an emerging technology that aims to detect pathology in the patient gastrointestinal tract. Physicians can use WCE to detect various gastrointestinal diseases at early stages. However, the diagnosis is tedious because it requires reviewing hundreds of frames extracted from the captured video. This tedious task has promoted researchers' efforts to propose automated diagnosis tools of WCE frames in order to detect symptoms of gastrointestinal diseases. In this paper, we propose an automatic multiple bleeding spots detection using WCE video. The proposed approach relies on two main components: (1) a feature extraction intended to capture the visual properties of the multiple bleeding spots, and (2) a supervised and unsupervised learning techniques which aim to accurately recognize multiple bleeding.