Detection of abnormalities in wireless capsule endoscopy frames using local fuzzy patterns

Wireless capsule endoscopy (WCE) is a relatively new technology that captures images of the entire gastrointestinal tract non-invasively and painlessly. A large number of frames are captured during an examination. The main difficulty for physicians is to review the frames visually. In recent years, some methods have been devised to help physicians. Here, a novel method is devised to distinguish among frames whether the frames contain abnormal region or not. This goal is achieved using local fuzzy patterns (LFP) that is compared with rotation invariant local binary patterns (LBP). In addition to this comparison, four color channels (red, hue, green, and gray scale) are examined to find the best one for using LFP. Experimental results indicate that LFP is a powerful method for texture detection, and can develop the LBP results in the WCE frames.