Wireless Capsule Endoscopy (WCE) is a painless and noninvasive technique that allows physicians to visualize the entire small bowel. Before WCE was introduced, examining the entire small bowel was impossible without surgical procedure. Although WCE is a technology breakthrough, the manual video diagnosis session is time consuming and is prone to human cognition errors. Therefore, gastroenterologists urge computer vision researchers to develop computer-aided diagnosis systems to assist the review session. In this paper, we would like to present an ulcer detection scheme that identifies ulcers in WCE video. A saliency map is created by means of channel mixer to highlight suspicious regions. Once the suspicious regions are identified, we extract textural features along the contour and classify them using a trained classifier for ulcer validation.