We propose two automatic methods for detecting bleeding in wireless capsule endoscopy videos of the small intestine. The first one uses solely the color information, whereas the second one incorporates the assumptions about the blood spot shape and size. The original idea is namely the definition of a new color space that provides good separability of blood pixels and intestinal wall. Both methods can be applied either individually or their results can be fused together for the final decision. We evaluate their individual performance and various fusion rules on real data, manually annotated by an endoscopist.

Charles University 2nd Department of Internal Medicine Gastroenterology Faculty of Medicine and University Hospital Sokolská 581 Hradec Králové 500 05 Czech Republic

Institute of Information Theory and Automation The Czech Academy of Sciences Pod vodárenskou veží 4 182 08 Prague 8 Czech Republic

University of Hradec Králové Center for Basic and Applied Research Faculty of Informatics and Management Hradecká 1249 Hradec Králové 500 03 Czech Republic

References provided by Crossref.org