Analysis of the gastrointestinal status from wireless capsule endoscopy images using local color feature

Because of a few great advantages such as non-invasiveness and no sedation over traditional endoscopies and other imaging techniques for gastrointestinal diseases, the wireless capsule endoscopy invented by Given Imaging has found its wide applications in hospitals. However, one problem with this new technology is that too many images to be examined by eyes become a huge burden to physicians, so it is very necessary to help the physician do analysis or diagnosis using computerized methods. In this paper, a new method aimed for abnormal region detection is proposed. This new approach makes use of local color feature, also a very important clue for diagnosis by physicians, to discriminate between normal region and abnormal region. Experimental results show rather promising performance of the proposed scheme.