Motion Compensated Restoration of Colonoscopy Images

Colonoscopy examinations are widely used for detecting colon cancer and many other colon abnormalities. Unfortunately, the resulting colon videos often have artifacts caused by camera motion and specular highlights caused by light reflections from the wet colon surface. To address these problems, we have developed a method for motion compensated colonoscopy image restoration. Our approach utilizes RANSAC-based image registration to align sequences of N consecutive images in the colonoscopy video and restores each frame of the video using information from these aligned images. We compare image alignment quality when N adjacent images are registered to each other versus registering images with larger step sizes between them. Three types of image pre processing were evaluated in our work. We found that the removal of non-informative images prior to image registration produced better alignment results and reduced processing time. We also evaluated the effects of image smoothing and resizing as a pre processing step for image registration.