Image multithresholding based on Kapur/Tsallis entropy and firefly algorithm

Abstract

Background/Objectives: In this paper, Firefly Algorithm (FA) based multilevel thresholding is proposed to segment the gray scale image by maximizing the entropy value. Methods/Statistical analysis: Better segmentation method gives appropriate threshold values to enhance the region of interest in the digital image. The entropy based methods, such as Kapur's and Tsallis functions are chosen in this paper to segment the image. This work is implemented using the gray scale images obtained from Berkeley segmentation dataset. The FA assisted segmentation with entropy function is confirmed using the universal image superiority measures existing in the literature. Findings: Results of this simulation work show that Tsallis function offers better performance measure values, whereas the Kapur's approach offers earlier convergence with comparatively lower CPU time. Applications/Improvements: Proposed method can be tested using other recent heuristic methods existing in the literature.