Pre-processing technique based on discrete cosine transform (DCT) and anisotropic contrast diffusion for wireless capsule endoscopy images

Abstract

Wireless capsule endoscopy (WCE) is useful to detect abnormal area in human digestive tract. However, many WCE images have low quality such as rather dark and noisy. Pre-processing is an important step in Computer Aided Detection (CAD) system to enhance the quality of WCE images in order to detect the abnormalities easier. To further enhance the image quality, anisotropic diffusion with Hessian matrix proposed by B. Li is applied to get contrast the image. However, this method still has weakness where an image is not sharp. To overcome this problem, Discrete Cosine Transform (DCT) is employed with anisotropic contrast diffusion in our proposed scheme. Experimental results of the proposed method are also presented in this paper.