Comparative Study of Edge Detection using Renyi Entropy and Differential Evolution

Abstract

Edge detection is an important task in image processing. Edge is defined as the boundary between two regions separated by two relatively distinct gray level properties. Traditional edge detection methods give rise to the exponential increment of computational time. In this paper, edge detection in gray level images is done by using Renyi entropy and differential evolution algorithm. The Renyi entropy is a one- parameter generalization of the Shannon entropy. Here Renyi entropy was calculated for the1dimensional histogram of the images. Differential evolution (DE) is an efficient and powerful population-based stochastic search technique for solving optimization problems, and this has been widely applicable in many scientific and engineering fields. The selection of the initial population in a population-based heuristic optimization method is most important, as it affects the search for a number of iterations and has an influence on the final solution. If the prior information about the optima is not available, then initial population is selected randomly using a pseudorandom numbers. The main advantage of DE algorithm is its simple in structure, easy to use, speed and robustness. I.INTRODUCTION Edge detection is a method which identifies the points in a digital image at which the brightness of the image changes clearly. Edge detection is the boundary between two regions separated by two relatively distinct grey level properties. The applications of edge detection such as image enhancement, water marking, compression, restoration etc. The traditional edge detection algorithms have been developed based on computation of the intensity gradient vector and it is very sensitive to noise in the image. For decreasing the noise some spatial averaging may be combined with differentiation that is known as LOG (laplacian of Gaussian operators). But this method used a 2D linear filter which is similar to second order derivatives and that also sensitive to noise. And the magnitude of the images produces double edges and gives the undesirable effect due to incomplete segmentation. For this reason laplacian combined with smoothing and find the edges via zero crossing and it also time taking. But the proposed a technique which is based on the information theory known as Renyi entropy. Renyi entropy decreases the computation time. To compare the result of Renyi entropy we proposed a new method which is based on optimization algorithm i.e. differential evolution algorithm which is a optimization algorithm. DE is an evolutionary algorithm and it is use to find out the near optimal solutions. For minimizing the total cost and maximize the possible reliability most of the optimization algorithm is used.