Adaptive Diffusion for Capsule Endoscopy Images

The capsule endoscopy approved by U.S. FDA in 2001 has been widely used to detect the diseases in human gastrointestinal tract. However, the contrast of the images produced by this small device is often low due to some reasons. In this paper, we propose a new adaptive diffusion algorithm to enhance the capsule endoscopy images. Based on the behavior analysis of the anisotropic diffusion and the characteristics of the capsule endoscopy images, we design two conduction functions in edge direction and gradient direction respectively to enhance capsule endoscopy images. Experimental results on real capsule endoscopy images show that this new adaptive diffusion outperforms the original anisotropic diffusion so as to help the doctors to diagnose.