Color-based template selection for detection of gastric abnormalities in video endoscopy

Color-based segmentation method has been applied for abnormal area selection. Color and texture features are combined for discrimination of abnormal regions and frames. We compare the segmentation results with the current state-of-the-art methods. Computer-aided diagnosis of gastric diseases from endoscopy frames is an important task. Colors are the basic visual features of endoscopic images and also provide clues about abnormal regions in endoscopy frames.