A vision based navigation for capsule endoscopies

Abstract

In this paper, a novel navigation method based on vision is proposed by integrating the advantages of watershed and pyramid segmentation methods. Using the idea of the continuity between two successive images, it is possible to give a reasonable advisory when the visual navigation fails. Besides that, we proposed to set a region of interest to accelerate the algorithm, using the method of image morphology to eliminate diverticula and introducing necessary auxiliary operations to avoid medical malpractice. A set of endoscopic images is tested to demonstrate the effectiveness of the proposed approach.