Performance Enhancement of Differential Evolution by Incorporating Lévy Flight and Chaotic Sequence for the Cases of Satellite Images

Abstract

Differential Evolution (DE) is a simple but powerful evolutionary algorithm. Crossover Rate (CR) and Mutation Factor (F) are the most important control parameters in DE. Mutation factor controls the diversification. In traditional DE algorithm CR and F are kept constant. In this paper, the values of CR and F are modified to enhance the capability of traditional DE algorithm. In the first modified algorithm chaotic sequence is used to perform this modification. In the next modified algorithm Lévy Flight with chaotic step size is used for such enhancement. In the second modified DE, population diversity has been used to build population in every generation. As a result the algorithm does not converge prematurely. Both modified algorithms have been applied to optimize parameters of the parameterized contrast stretching function. The algorithms are tested for satellite image contrast enhancement and the results are compared, which show that DE via chaotic Lévy and population diversity information outperforms the traditional and chaotic DE in the image enhancement domain.

Differential Evolution and Its Applications in Image Processing Problems: A Comprehensive Review

“…A parameter adaptive DE with opposition-based learning, optional archive, and current top-best mutation strategy was used for search space diversification and convergence speed Priya et al [ 218 ] Security of health imagery with temper detection Recursive Dither Modulation (RDM) with DE Recursive dither modulation (RDM) is used to embed the hospital logo, doctor’s identification code, etc., and DE was used to increase the scheme's performance Ayala et al [ 219 ] Segmentation of image based on thresholding Beta DE (BDE) The optimal, -level threshold of a given image with the Otsu criterion was determined using Beta-DE. The proposed method used a beta distribution approach to implement DE's F and CR values at every generation Dhal et al [ 220 ] Contrast enhancement of satellite image DE with chaotic levy flight The values of DE's control parameters were modified with a chaotic sequence and then modified levy flight with a chaotic step size to enhance the algorithm's performance. The modified algorithm is used to optimize the parameters of a contrast stretching function Ferreira et al [ 221 ] Restoration of underwater image Image restoration based on MODE This problem consists of the task of obtaining the parameters of the Trucoo model.…”

Local search-based dynamically adapted bat algorithm in image enhancement domain

“…exp is the exponential operator. All the above enhancement models have been formulated as maximisation problem as it is proved that if any of the above stated objective function is maximised then the quality of the enhanced image always better than the input image for some specific application Ghosh, 2009, 2011;Munteanu and Rosa, 2001;Pal et al, 1994;Hashemi et al, 2010;Coelho et al, 2009;Dhal et al, 2015aDhal et al, , 2015bDhal et al, , 2015cDhal et al, , 2015dDhal et al, , 2017bDhal et al, , 2017aShanmugavadivu et al, 2014;Braik et al, 2007;Quraishi et al, 2012;Das, 2016, 2015;Quraishi et al, 2013). Therefore, the general maximisation problem is formulated as:…”

“…In this study, image enhancement techniques (Gonzalez and Woods, 2002) have been formulated as optimisation problems and solved by nature inspired optimisation algorithms. Genetic algorithm (GA), particle swarm optimisation (PSO), differential evolution (DE), Cuckoo search (CS), artificial bee colony (ABC), firefly algorithm (FA) are some nature inspired metaheuristic algorithms which were effectively used in image enhancement field Ghosh, 2009, 2011;Munteanu and Rosa, 2001;Pal et al, 1994;Hashemi et al, 2010;Coelho et al, 2009;Dhal et al, 2015aDhal et al, , 2015bDhal et al, , 2015cDhal et al, , 2015dDhal et al, , 2017bDhal et al, , 2017aShanmugavadivu et al, 2014;Braik et al, 2007;Quraishi et al, 2012;Das, 2016, 2015;Quraishi et al, 2013). PSO gave better results than GA in the image enhancement domain by maximising employed entropy-based objective function.…”

“…CS and FA also outperformed PSO by considering the ability to maximise or minimise some benchmark mathematical functions (Yang, 2010c(Yang, , 2010b. The performance of these algorithms can be increased by some mechanism such as use of different random number generators to modify the solutions (Coelho et al, 2009;Dhal et al, 2015bDhal et al, , 2015cDhal et al, , 2015d, use of different inertia weight to get a better convergence rate (Dhal et al, 2015d;Bansal et al, 2011), use of communication between solutions (Caponetto et al, 2003) and so on. Mutation factor and crossover rate had been modified by chaotic sequence of traditional DE algorithm and experimental result showed that modified DE was far better than traditional DE in image enhancement field with faster convergence rate and also maintained a good diversity property (Coelho et al, 2009).…”

“…Mutation factor and crossover rate had been modified by chaotic sequence of traditional DE algorithm and experimental result showed that modified DE was far better than traditional DE in image enhancement field with faster convergence rate and also maintained a good diversity property (Coelho et al, 2009). Lévy flight with chaotic step length had been used to generate new solutions and one population diversity measurement technique had been used as a safe guard from premature convergence in Dhal et al (2015bDhal et al ( , 2015c to modify FA and DE respectively, which outperformed the traditional FA and DE in the image enhancement domain by maximising the employed objective function with faster convergence rate. A newly proposed metaheuristic algorithm called bat algorithm (BA) which is developed based on the echolocation behaviour of bats, already outperformed GA and PSO (Yang, 2010a(Yang, , 2013, also gave better results than CS algorithm in image enhancement field (Dhal et al, 2015d).…”