Efficient contrast enhancement of images using hybrid ant colony optimisation, genetic algorithm, and simulated annealing

Hoseini, Pourya; Shayesteh, Mahrokh G.

doi:10.1016/j.dsp.2012.12.011

Cited by 75 publications

(31 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though Sobel is applicable as a local operator, a global operator should be used to ensure that contrast enhancement is applied to the entire image rather than just the edges [13]. c) Entropy In Information Theory, entropy is a measure of the uncertainty or average unpredictability in a random variable, which is equivalent to its information content [21,22].…”

Section: ) Genetic Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary approach and Spline Interpolation for contrast enhancement

Gupta¹,

Nag²,

Savani³

et al. 2013

2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)

View full text Add to dashboard Cite

In this paper, image contrast enhancement techniques are explored and two novel approaches are proposed. The first approach uses a Super Resolution based Convolution kernel in Lab colour space which is optimized using Genetic Algorithms, for the evolutionary generation of the kernel values. The employed fitness function tends to provide a balance between contrast and naturalness of images. The second approach is called Spline Interpolation which works by fitting a continuous three dimensional curve through (0,0,0), the current pixel's RGB value and (255,255,255). These methods are compared with standard techniques on a database of bio-medical images and general images. The results indicate that the proposed methods overcome the drawbacks of existing methods.

show abstract

Section: ) Genetic Algorithmsmentioning

confidence: 99%

“…Various combinations of metaheuristics have been proposed. In [13,14], a Genetic Algorithm sets the controlling parameters for Ant Colony Optimization (ACO), another meta-heuristic. In [15], ACO is used as a local search for GA.…”

Section: Genetic Algorithmmentioning

confidence: 99%

Evolutionary approach and Spline Interpolation for contrast enhancement

Gupta¹,

Nag²,

Savani³

et al. 2013

2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)

View full text Add to dashboard Cite

show abstract

“…When there are more and more ants passing a path, the residual pheromone concentration of this path will increase gradually and the probability for the ants to choose this path also increases, suggesting the positive feedback of information. In the meanwhile, with the increase of time, the pheromone intensity will decrease gradually [13,14].…”

Section: Basic Principle Of Ant Colony Algorithmmentioning

confidence: 99%

Image Restoration Based on Hybrid Ant Colony Algorithm

2015

View full text Add to dashboard Cite

Image restoration is the process to eliminate or reduce the image quality degradation in the digital image formation, transmission and recording and its purpose is to process the observed degraded image Keywords: Image Restoration, Ant Colony Algorithm, Genetic AlgorithmCopyright © 2015 Universitas Ahmad Dahlan. All rights reserved. IntroductionImage restoration is to research how to restore the degraded image into real image, or to research how to invert the information obtained into the information related to the real objective [1]. Certain degree of degradation and distortion are inevitable in the formation, transmission, storage, recording and display of the image. Since image quality degradation may be caused in every link of the formation of digital image, in many cases, the image needs to be restored in order to get high-quality digital image [2].In the past decades, domestic and foreign scholars have made extensive and in-depth research in image restoration technology. Many one-dimensional signal processing and estimation theories, including inverse filtering, minimum mean error estimation and Bayesian estimation, have been used in the field of image restoration, thus forming numerous restoration algorithms. In terms of certain specific restoration problems, the scholars usually integrate many ideas and methods [3]. With the continuous development of signal processing theories, many new processing ideas and restoration methods keep emerging. In drastic contrast with the typical mathematical programming principles, some bionic intelligent optimization algorithms such as ant colony algorithm, genetic algorithm, artificial neural network technology, artificial immune algorithm and swarm intelligence algorithm, have been raised and studied by simulating the natural eco-system to seek the complicated optimization problems. These algorithms have greatly enriched modern optimization technology and provided feasible solutions to those optimization problems which are difficult to be handled by traditional optimization technology. Ant colony algorithm is a heuristic bionic evolutionary system based on population. By adopting distributed plus-feedback parallelization, this algorithm is easy to combine with other methods and it also has strong robustness, however, this algorithm requires long search time and it is easy to result in pre-mature and stagnation behaviors, slowing its convergence rate. On the other hand, genetic algorithm is a randomized adaptive search algorithm by referring to the natural selection and natural genetic mechanism and it can compute the non-linear multi-dimensional data space in a quick and effective manner. Therefore, the integration of these two techniques or algorithms can eliminate their own shortcomings and setbacks and utilize their own advantages in the image restoration [4,5]. This paper firstly summarizes the theory of image restoration systematically and analyzes the basic principle of ant colony algorithm. Then, it focuses on the research of the

show abstract

“…Hence algorithm in each step has less chance in choosing bad solutions. Thus an efficient contrast image enhancement using Ant colony optimization, Genetic Algorithm and Simulated Annealing [17] was proposed. This method is fast with global transformation of intensities but since the usage of Evolutionary methods -GA, ACO and SA are slow and robust.…”

Section: Direct Contrast Enhancement Techniquesmentioning

confidence: 99%