Multilevel Image Thresholding Established on Fuzzy Entropy Using Differential Evolution
This study establishes a new methodology based on fuzzy partition of the image histogram and entropy for multi-level image thresholding. We propose a new methodology which is implemented in framework of the multi-step segmentation of image format. Further framework is improved to attain improved threshold value. A meta-heuristic Differential Evolution (DE) algorithm is cast-off in a direction to resolve the optimization problem, that results in a more rapid and accurate conjunction headed for the ideal situation. The accomplishment of DE can also be measured in reference to more or less widely held universal optimization procedures like Genetic Algorithms and Particle Swarm Optimization. Simulation results are equated with other entropy technique like Shannon entropy for the purpose of establishing the distinguishable difference in image.
KeywordsFuzzy entropy Multilevel image segmentation Differential evolution
- 2.Karri, C., Jena, U.: Image compression based on vector quantization using cuckoo search optimization technique. Ain Shams Eng. J. (2016). (In press)Google Scholar
- 3.Karri, C., Umaranjan, J., Prasad, P.M.K.: Hybrid Cuckoo search based evolutionary vector quantization for image compression. Artif. Intell. Comput. Vision Stud. Comput. Intell., 89–113 (2014)Google Scholar
- 16.Maryam, H., Mustapha, A., Younes, J.: A multilevel thresholding method for image segmentation based on multiobjective particle swarm optimization. In: 2017 International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), Fez, pp. 1–6 (2017)Google Scholar
- 19.Bhandari, A.K., Singh, V.K., Kumar, A., Singh, G.K.: Cuckoo search algorithm and wind driven optimization based study of satellite image segmentation for multilevel thresholding using Kapur’s entropy. Expert Syst. Appl. 41, 3538–3560 (2014). https://doi.org/10.1016/j.eswa.2013.10.059CrossRefGoogle Scholar