Small intestine bleeding detection using color threshold and morphological operation in WCE images

<span>Wireless capsule endoscopy (WCE) is a significant modern technique for observing the whole gastroenterological tract to diagnose various diseases like bleeding, ulcer, tumor, Crohn's disease, polyps etc in non-invasive manner. However, it will make substantial onus physicians human oversight errors with time consumption manual checking of vast amount image frames. These problems motivate researchers employ computer-aided system classify particular information from Therefore, based on color threshold and morphological operation has been proposed this research recognize specified bleeding images WCE. Besides, A unique classifier, quadratic support vector machine (QSVM) employed classifying non-bleeding statistical feature HSV space. After extensive experiments clinical data, 95.8% accuracy, 95% sensitivity, 97% specificity, 80% precision, 99% negative predicted value 85% F1 score achieved, which outperforms some existing methods regard. It expected that methodology would bring contribution WCE technology. </span>