Modified differential evolution algorithm for contrast and brightness enhancement of satellite images |
| |
| Affiliation: | 1. Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, Italy;2. Technical University of Munich, Germany;3. Comsats Institute of Information Technology, Islamabad, Pakistan;1. Department of Electronics and Communication Engineering, National Institute of Technology Patna, Patna, Bihar, India;2. Department of Electronics and Communication Engineering, Muzaffarpur Institute of Technology, Muzaffarpur, Bihar, India;1. School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China;2. School of Mathematics and Computing Science, Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation, Guilin University of Electronic Technology, Guilin, China;3. Guangxi Colleges and Universities Key Laboratory of Intelligent Processing of Computer Images and Graphics, Guilin University of Electronic Technology, Guilin, China;4. Guangxi Experiment Center of Information Science, Guilin, China;1. Division of Science and Engineering, University of Quintana Roo, Quintana Roo, Mexico;2. Faculty of Mechanical and Electrical Engineering, Autonomous University of Nuevo Leon, Nuevo Leon, Mexico;3. Department of System Operation, Taiwan Power Company, Taipei, Taiwan |
| |
| Abstract: | Satellite images normally possess relatively narrow brightness value ranges necessitating the requirement for contrast stretching, preserving the relevant details before further image analysis. Image enhancement algorithms focus on improving the human image perception. More specifically, contrast and brightness enhancement is considered as a key processing step prior to any further image analysis like segmentation, feature extraction, etc. Metaheuristic optimization algorithms are used effectively for the past few decades, for solving such complex image processing problems. In this paper, a modified differential Modified Differential Evolution (MDE) algorithm for contrast and brightness enhancement of satellite images is proposed. The proposed algorithm is developed with exploration phase by differential evolution algorithm and exploitation phase by cuckoo search algorithm. The proposed algorithm is used to maximize a defined fitness function so as to enhance the entropy, standard deviation and edge details of an image by adjusting a set of parameters to remodel a global transformation function subjective to each of the image being processed. The performance of the proposed algorithm is compared with ten recent state-of-the-art enhancement algorithms. Experimental results demonstrate the efficiency and robustness of the proposed algorithm in enhancing satellite images and natural scenes effectively. Objective evaluation of the compared methods was done using several full-reference and no-reference performance metrics. Qualitative and quantitative evaluation results proves that the proposed MDE algorithm outperforms others to a greater extend. |
| |
| Keywords: | Image enhancement Metaheuristics Differential evolution algorithm Cuckoo search algorithm Satellite images |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
