Multi-level image thresholding based on Kapur and Tsallis entropy using firefly algorithm
Abhay Sharma, Rekha Chaturvedi, Sandeep Kumar, Umesh Kumar Dwivedi
Abstract
Abstract Image segmentation is necessity of many application like brain tumor detection, optical character recognition, thermal energy leakage detection, Face recognition etc. multilevel thresholding is the complex task to find optimal threshold. Entropy plays an important role for efficient segmentation. We have introduced entropy-based thresholding with metaheuristic approach to find optimal threshold for gray images. Firefly Algorithm has been used with Kapur/Tsallis entropies to segment the image. All the methods have intent to find optimal threshold, based on experimental results Tsallis method offer better PSNR and SSIM values and capable of effective segmentation of images.