Saliency based Ulcer Detection for Wireless Capsule Endoscopy Diagnosis/strong>
Abstract— Ulcer is one of the most common symptoms of many serious diseases in the human digestive tract. Especially for the ul-cers in the small bowel where other procedures cannot adequately visualize,wireless capsule endoscopy WCE < Final Year Projects 2016 > is increasingly being used in the diagnosis and the clinical management. Because WCE generates large amount of images from the whole process of inspection, computer-aided detection of ulcer is considered an indispensable relief to clinicians. we propose an effective saliency detection method based on multi-level superpixel representation to outline the ulcer candidates. To ﬁnd the perceptually and semantically meaningful salient regions, we ﬁrst segment the image into multi-level superpixel segmentations.