Indian Journal of Science and Technology
DOI: 10.17485/ijst/2016/v9i17/89936
Year: 2016, Volume: 9, Issue: 17, Pages: 1-6
Original Article
N. Sri Madhava Raja* and R. Vishnupriya
Department of Electronics and Instrumentation Engineering, St. Joseph’s College of Engineering, Old Mamallapuram Road, Near Sathyabhama Campus, Semmencherry, Chennai - 600 119, Tamilnadu, India; [email protected], [email protected]
*Author of Corresponding: N. Sri Madhava Raja Department of Electronics and Instrumentation Engineering, St. Joseph’s College of Engineering, Old Mamallapuram Road, Near Sathyabhama Campus, Semmencherry, Chennai - 600 119, Tamilnadu, India; [email protected]
Background/Objectives: In this paper, Cuckoo Search (CS) algorithm based image multi-thresholding is proposed for optimal segmentation of RGB image by maximizing the entropy value in Kapur’s method. Methods/Statistical Analysis: The aim of the paper is to search for an optimized threshold value for image segmentation using CS algorithm where fitness function is designed based on entropy of the image. The capability of CS assisted segmentation with Kapur’s function is established in comparison with Firefly and PSO optimization algorithms using the universal image superiority measures existing in the literature. Findings: Results of this study show that CS with Kapur’s function offers better performance measure, whereas Firefly and PSO optimization algorithms offers earlier convergence with comparatively lower CPU time. Applications/Improvements: In future, proposed method can be implemented for the medical image analysis.
Keywords: Cuckoo Search Algorithm, Image Segmentation, Kapur’s Entropy, Noise Stain, RGB Image
Subscribe now for latest articles and news.
