Hyper-heuristic Image Enhancement (HHIE): A Reinforcement Learning Method for Image Contrast Enhancement

Conventional contrast enhancement methods such as histogram equalization (HE) have not obtained acceptable results on many different low-contrast images and they also cannot automatically handle various images. These problems are a result of specifying parameters manually for the sake of producing high-contrast images. We proposed an automatic image contrast enhancement on Hyper-heuristic. In this study, simple exploiters are proposed to improve the contrast of current image. To select these exploiters appropriately, reinforcement learning is proposed. This selection is based on the functional history of these exploiters. Having multi aim of preserving brightness, retaining the shape features of the original histogram, and controlling on the rate of over-enhancement are the achievements of the proposed method. These objectives are suitable for the application of consumer electronics. By this simulation results, it has been shown that in terms of visual assessment, absolute mean brightness error (AMBE) and peak signal-to-noise (PSNR) of the proposed method are superior to literature methods.

[1]  Mohsen Ebrahimi Moghaddam,et al.  An image contrast enhancement method based on genetic algorithm , 2010, Pattern Recognit. Lett..

[2]  Dae San Kim,et al.  Home network message specification for white goods and its applications , 2002, IEEE Trans. Consumer Electron..

[3]  Yeong-Taeg Kim,et al.  Contrast enhancement using brightness preserving bi-histogram equalization , 1997 .

[4]  Ahmad Faraahi,et al.  A novel memetic feature selection algorithm , 2013, The 5th Conference on Information and Knowledge Technology.

[5]  Reza Khajouei,et al.  Prognosis and Early Diagnosis of Ductal and Lobular Type in Breast Cancer Patient , 2017, Iranian journal of public health.

[6]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[7]  Cheolkon Jung,et al.  Automatic Contrast-Limited Adaptive Histogram Equalization With Dual Gamma Correction , 2018, IEEE Access.

[8]  Saeid Saryazdi,et al.  Eye detection in digital images: challenges and solutions , 2016, ArXiv.

[9]  A. Bahrampour,et al.  Predicting of liver disease using Hidden Markov Model , 2016 .

[11]  Hossein Nezamabadi-pour,et al.  Exploring and Exploiting Effectively Based Hyper-Heuristic Approach for Solving Travelling Salesman Problem , 2011 .

[12]  Min Gyo Chung,et al.  Recursively separated and weighted histogram equalization for brightness preservation and contrast enhancement , 2008, IEEE Transactions on Consumer Electronics.

[13]  Hamid Reza Naji,et al.  Memetic Feature Selection Algorithm Based on Efficient Filter Local Search , 2013 .

[14]  Hossein Nezamabadi-pour,et al.  Cooperating of Local Searches based Hyperheuristic Approach for Solving Traveling Salesman Problem , 2011, IJCCI.

[15]  Mitra Montazeri.  Light Intensity Adjustment and Noise Removal for Medical Image Enhancement , 2016 .

[16]  Montazeri Mitra,et al.  HHFS: Hyper-heuristic feature selection , 2016, Intelligent Data Analysis.

[17]  Abd. Rahman Ramli,et al.  Contrast enhancement using recursive mean-separate histogram equalization for scalable brightness preservation , 2003, IEEE Trans. Consumer Electron..

[18]  Paul L. Rosin.  Edges: saliency measures and automatic thresholding , 1997, Machine Vision and Applications.

[19]  Om Prakash Verma,et al.  Contrast enhancement using entropy-based dynamic sub-histogram equalisation , 2016, IET Image Process..

[20]  A. Beigzadeh,et al.  Machine learning models in breast cancer survival prediction. , 2016, Technology and health care : official journal of the European Society for Engineering and Medicine.

[21]  Li Chen,et al.  Image contrast enhancement using an artificial bee colony algorithm , 2018, Swarm Evol. Comput..

[22]  Comparison of the Accuracy of Digital Image -based and Patient Visit-based Diagnoses in an Iranian Dermatology Clinic , 2013 .

[23]  Abdullah Al Mamun,et al.  An evolutionary memetic algorithm for rule extraction , 2010, Expert Syst. Appl..

[24]  Qian Chen,et al.  Image enhancement based on equal area dualistic sub-image histogram equalization method , 1999, IEEE Trans. Consumer Electron..

[25]  Leila Ahmadian,et al.  Futures Studies in Health: Choosing the Best Intelligent Data Mining Model to Predict and Diagnose liver Cancer in Early Stage , 2015 .

[26]  Seyyed Meysam Mousavi,et al.  Using Advanced Statistical Models to Predict the Non-Communicable Diseases , 2015, Iranian journal of public health.

[27]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[28]  Kuldeep Singh,et al.  Image enhancement using Exposure based Sub Image Histogram Equalization , 2014, Pattern Recognit. Lett..

[29]  F. Saitoh.  Image contrast enhancement using genetic algorithm , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[30]  Om Prakash Verma,et al.  Fuzzy-Contextual Contrast Enhancement , 2017, IEEE Transactions on Image Processing.

[31]  Mahdieh Soleymani Baghshah,et al.  Selecting Efficient Features via a Hyper-Heuristic Approach , 2016, ArXiv.

[32]  Kuldeep Singh,et al.  Enhancement of low exposure images via recursive histogram equalization algorithms , 2015 .

[33]  Mahdieh Soleymani Baghshah,et al.  Hyper-Heuristic Algorithm for Finding Efficient Features in Diagnose of Lung Cancer Disease , 2015, ArXiv.

[34]  Zhaoquan Cai,et al.  Improving sampling-based image matting with cooperative coevolution differential evolution algorithm , 2017, Soft Comput..

[35]  P. W. Jones,et al.  Digital Image Compression Techniques , 1991 .

[36]  Hossein Nezamabadi-pour,et al.  Automatic extraction of eye field from a gray intensity image using intensity filtering and hybrid projection function , 2011, 2011 International Conference on Communications, Computing and Control Applications (CCCA).