PROJECT TITLE :

Scaled Heavy Ball Acceleration of the Richardson Lucy Algorithm for 3D Microscopy Image Restoration - 2014

ABSTRACT:

The Richardson-Lucy algorithm is one of the foremost vital in image deconvolution. However, a downside is its slow convergence. A important acceleration was obtained using the technique proposed by Biggs and Andrews (BA), which is implemented in the deconvlucy function of the image processing MATLAB toolbox. The BA technique was developed heuristically with no proof of convergence. In this paper, we have a tendency to introduce the heavy-ball (H-B) technique for Poisson information optimization and extend it to a scaled H-B technique, which includes the BA technique as a special case. The strategy features a proof of the convergence rate of O(K-two), where k is the quantity of iterations. We have a tendency to demonstrate the superior convergence performance, by a speedup issue of 5, of the scaled H-B method on both synthetic and real 3D pictures.