Image thresholding based on swarm intelligence technique for image segmentation

Image thresholding is a critical task of image segmentation. Selection of the optimal value of the threshold is the most important task for image thresholding. The better the value of threshold better is the quality of segmentation. In this paper, recent swarm intelligence technique (fireworks algorithm) has been used for image thresholding. Fireworks algorithm is used to maximize two functions, namely Kapur and Otsu. Results show that quality of segmentation is better in case of Firewok-Otsu than Firework-Kapur. Comparison of results has been done on the basis of PSNR value.