De-blurring wireless capsule endoscopy images by total variation minimization

Wireless capsule endoscopy (WCE) finds wide applications in diagnosing diseases in human intestine on account of its convenience and non-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 corrupted by noise and degraded by within-channel or cross-channel blurs. In this paper, we present a total variation (TV) minimization framework for deblurring within-channel blurs for color WCE images. Specifically, the monotone fast iterative shrinkage/thresholding technique combined with the fast gradient projection algorithm, proposed recently by Beck and Teboulle, is extended to deal with multichannel images. In addition, the proposed algorithm is enhanced by incorporating a bisection technique to effectively identify a near optimal value for the regularization parameter of the TV-Frobenius objective function. Experimental results are presented to demonstrate the performance of the proposed algorithm.