Fast algorithms for restoration of color wireless capsule endoscopy images

Wireless capsule endoscopy (WCE) has been widely adopted to diagnose diseases in human intestine on account of its convenience and invasiveness to the patients. Due to complicated environment of the intestine and intrinsic restrictions of the equipment in terms of image acquisition and transmission, however, raw WCE images are often blurred and noise contaminated. In this paper, we report several new developments for the restoration of color WCE images in a total variation (TV) minimization framework. Specifically, the monotone fast iterative shrinkage/thresholding algorithm combined with the fast gradient projection algorithm, proposed recently by Beck and Teboulle, is extended to deal with vector-valued (e.g. color) images. The new algorithm also incorporates a bisection technique to tune the weighting parameter of the TV-Frobenius objective function to its optimal value quickly and accurately. Experimental results are presented to demonstrate the performance of the proposed algorithm.