Harmony Search Algorithm and its Use in Digital Image Processing

Abstract

Classical methods often face big difficulties in solving image processing problems when images contain noise and distortions. For such images, the use of optimization approaches has been extended. This paper explores application of the Harmony Search (HS) algorithm to digital image processing. HS is a meta-heuristic optimization algorithm inspired by musicians improvising new harmonies while performing. In this paper, we consider two tasks as examples: circle detection and motion estimation, both issues are approached as optimization problems. In such approach, circle detection uses a combination of three edge points as parameters to construct candidate circles. A matching function determines if such candidate circles are actually present in a given image. In motion estimation, the HS algorithm is used to find a motion vector that minimizes the sum of absolute differences between two consecutive images. Experimental results show that the generated solutions are able to properly solve the problems under consideration.