Distributed Local Search for Elastic Image Matching

We propose a distributed local search (DLS) algorithm, which is a parallel formulation of a local search procedure in an attempt to follow the spirit of standard local search metaheuristics. Applications of different operators for solution diversification are possible in a similar way to variable neighborhood search. We formulate a general energy function to be equivalent to elastic image matching problems. A specific example application is stereo matching. Experimental results show that the GPU implementation of DLS seems to be the only method that provides an increasing acceleration factor as the instance size augments, among eight tested energy minimization algorithms.