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

doi:10.1016/j.dsp.2012.12.011

Digital Signal Processing

Volume 23, Issue 3, May 2013, Pages 879-893

https://doi.org/10.1016/j.dsp.2012.12.011 Get rights and content

Abstract

In this paper, we propose a hybrid algorithm including Genetic Algorithm (GA), Ant Colony Optimisation (ACO), and Simulated Annealing (SA) metaheuristics for increasing the contrast of images. In this way, contrast enhancement is obtained by global transformation of the input intensities. Ant colony optimisation is used to generate the transfer functions which map the input intensities to the output intensities. Simulated annealing as a local search method is utilised to modify the transfer functions generated by ant colony optimisation. And genetic algorithm has the responsibility of evolutionary process of antsʼ characteristics. The employed fitness function operates automatically and tends to provide a balance between contrast and naturalness of images. The results indicate that the new method achieves images with higher contrast than the previously presented methods from the subjective and objective viewpoints. Further, the proposed algorithm preserves the natural look of input images.

Graphical abstract

Section snippets

Pourya Hoseini received the B.S. degree in electrical and electronics engineering from Azad University of Lahijan, Lahijan, Iran in 2007, and the M.S. degree in electronics and microelectronics engineering from Urmia University, Urmia, Iran in 2011. His research interests are analog and digital circuit design, hardware implementation of artificial intelligence, fuzzy systems, neural networks, evolutionary algorithms, and image processing.

References (18)

Z.J. Lee et al.
Genetic algorithm with ant colony optimization (GA–ACO) for multiple sequence alignment
Appl. Soft Comput.
(2008)
S. Nemati et al.
A novel ACO–GA hybrid algorithm for feature selection in protein function prediction
Expert Syst. Appl.
(2009)
J. Tian et al.
Ant colony optimization algorithm for wavelet-based image interpolation using a three-component exponential mixture model
Expert Syst. Appl.
(2011)
J. Tian et al.
AntShrink: Ant colony optimization for image shrinkage
Pattern Recogn. Lett.
(2010)
G. Ramponi
A cubic unsharp masking technique for contrast enhancement
Signal Process.
(1998)
T. White, B. Pagurek, F. Oppacher, ASGA: Improving the ant system by integration with genetic algorithms, in:...
A. Rezaee
Extracting edge of images with ant colony
J. Electr. Eng.
(2008)
J. Tian, W. Yu, S. Xie, An ant colony optimization algorithm for image edge detection, in: IEEE Congress on...
A.R. Malisia, H.R. Tizhoosh, Applying ant colony optimization to binary thresholding, in: IEEE ICIP, 2006, pp....

There are more references available in the full text version of this article.

Cited by (82)

Enhanced sparrow search algorithm based on improved game predatory mechanism and its application
2024, Digital Signal Processing: A Review Journal
In response to the problems of strong randomness in initialization, imperfect search mechanism and tendency to fall into local optimum when dealing with complex optimization problems by sparrow search algorithm (SSA), an enhanced sparrow search algorithm (ESSA) is proposed, which combines Hammersley low difference sequence (HLDS) and centroid opposition-based learning (COBL), improved game predatory mechanism (GPM) and elastic collision strategy (EC). The ESSA can improve the initial individual quality, and avoid the attraction of local optima. In addition, the ESSA can effectively improve the search mechanism by increasing information exchange of individuals and balancing global search and local development. The effectiveness of ESSA is verified through simulation experiments of benchmark functions and variational modal decomposition (VMD) parameter optimization.
Optimized hyperbolic tangent function-based contrast-enhanced mammograms for breast mass detection
2023, Expert Systems with Applications
Citation Excerpt :
The proposed system is evaluated and executed in MATLAB, 2017a in a PC with an Intel i7 processor operating at 2.6 GHz and with 8 GB RAM. To evaluate the efficiency of the proposed framework, the experiment was conducted on two different standard databases, and the results were further compared with other state-of-the-art techniques such as CLAHE (Zuiderveld, 1994) and other nature-inspired enhancement methods (Chen et al., 2018; Hoseini & Shayesteh, 2013; Kanmani & Narsimhan, 2018; Zhou et al., 2019), which offer a promising performance. Broadly, the overall performance evaluation can be categorized into three parts.
Breast cancer is a grave concern among women due to its high mortality rate in women as compared to that in men. Mass, an early symptom of breast cancer, is difficult to detect due to its subtle nature. Mammography, an effective and most preferred screening technique, generally uses low-contrast images where identification of some of the mass lesions from surrounding normal tissues is a difficult task even for skilled radiologists. Therefore, to alleviate the issue, this paper introduces an effective computer-aided detection scheme based on a novel contrast enhancement scheme for mammograms to automate the localization procedure of mass cases. Hyperbolic tangent function, a simple yet effective method, is introduced as an enhancement transfer function whose adjustable parameter is optimized by the Tunicate swarm algorithm, a nature-inspired optimization algorithm, via fitness function. To minimize the false positives generated after the detection, the median robust extended local binary pattern, a texture-based descriptor, is introduced, which possesses the ability to capture both micro- and macro-structure information from an image patch. The analysis includes four classifiers: Fisher linear discriminant analysis, K-nearest neighbor, support vector machine, and an ensemble classifier in the feature-based classification for false positive reduction (FPR). The proposed approach of automatic detection of masses when verified using two standard databases, mini-MIAS and Digital Database for Screening Mammography, comprised 68 and 550 mammograms, respectively, achieved sensitivities of 95.3% and 94.1% with 0.36 and 0.40 false positives per image after false positive reduction.
Optimized histogram computation model using cuckoo search for color image contrast distortion
2021, Digital Signal Processing: A Review Journal
This paper proposes a novel optimized histogram modification framework using a cuckoo search (CS) algorithm for brightness preserved contrast enhancement. The histogram modification has been modeled as an optimization problem and the CS algorithm is used to find an optimum solution. The proposed method's chief objective is to find a fair tradeoff between contrast improvement and mean-brightness preservation. A new target histogram has been generated using the CS algorithm using a target function composed of tuning parameters. The extent of the image contrast range can be adjusted by selecting appropriately designed tuning parameters. The proposed technique can control the enhancement with the values chosen to fix the enhancement level and retain the enhanced image features. Finally, the optimized histogram generated from the CS algorithm is employed in the histogram equalization (HE) process to generate the final enhanced image. Its performance is validated with qualitative and quantitative assessment against well-known state-of-the-art techniques.
A novel enhanced cuckoo search algorithm for contrast enhancement of gray scale images
2019, Applied Soft Computing Journal
A good contrast image has a significant role in different image processing applications and computer vision algorithms. One of the most common contrast enhancement approaches is histogram equalization (HE) that enhances the contrast of an image globally. However, it gives rise to some over-enhanced regions, loss of detail information, and enhancement of noise. In order to improve the performance of the HE algorithm, local HE and adaptive HE algorithms have been proposed but with limited success. Recently, an evolutionary algorithm named cuckoo search (CS) algorithm has been employed for automatic image contrast enhancement showing promising performance. In this paper, we propose a novel enhanced cuckoo search (ECS) algorithm for image contrast enhancement. In addition, we propose a new range of search space for the parameters of the local/global enhancement (LGE) transformation that need to be optimized. The proposed ECS algorithm is applied to several low contrast test images and its performance is compared with that of the CS algorithm. Next, we compare the performance of the ECS algorithm with artificial bee colony algorithm using the proposed LGE transformation and a global transformation. In the last stage of performance evaluation, the ECS algorithm is compared with several image enhancement algorithms, namely, HE, CLAHE, Particle Swarm Optimization (PSO), CS, modified CS and CS-PSO algorithms. In all cases, we have shown the superiority of the ECS algorithm in terms of several performance measures.
Edge Detection Algorithm for In-Pixel Lighting Via Genetic Optimization Algorithm
2024, AIP Conference Proceedings
Aerospace image processing using bio-inspired algorithms
2024, AI and Blockchain Optimization Techniques in Aerospace Engineering

View all citing articles on Scopus

Mahrokh G. Shayesteh received the B.S. degree from University of Tehran, Tehran, Iran, the M.S. degree from Khajeh Nassir University of Technology, Tehran, Iran, and the Ph.D. degree from Amir Kabir University of Technology, Tehran, Iran, all in electrical engineering. She is now an associate professor at Urmia University. She is also working with the Wireless Research Lab., ACRI, Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran. Her research interests are wireless communication systems, spread spectrum, and image processing.

View full text

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

Abstract

Graphical abstract

Section snippets

Appl. Soft Comput.

Expert Syst. Appl.

Expert Syst. Appl.

Pattern Recogn. Lett.

Signal Process.

Extracting edge of images with ant colony

J. Electr. Eng.