A preliminary study for automatic accurate detection of adenomatous polyps in the small intestine

摘要

In this paper we present a novel preliminary study based on state of the art computation techniques applied on WCE video images for extracting features and patterns from different views of the same polyp. The extracted pattern and features are synthesized by using LG registration technique to create better views for each polyp by removing artifacts and noise. The outcome images (views) from each polyp will be used for the training and testing of a machine learning system that will separate the two types of diminutive polyps.