Image thresholding is one of the popular approaches for image segmentation. Traditional thresholding methods face challenges in finding the optimal threshold value for infrared thermal image thresholding. In this paper, we propose a new approach to fi...
Image thresholding is one of the popular approaches for image segmentation. Traditional thresholding methods face challenges in finding the optimal threshold value for infrared thermal image thresholding. In this paper, we propose a new approach to find the optimal threshold value for infrared thermal image segmentation. Creating a criterion function model using the one-dimensional histogram information of the image to get the possible object and background region separations in the image is the primary objective of the proposed method. For that, a cumulative probability distribution dependent iterative model is developed. Thereafter, a mathematical model based on sine function is utilized to extract an optimal threshold value for two-level infrared thermal image segmentation. We have experimented with our method on several infrared thermal images collected from standard image databases to describe the performance, and they are compared to the state-of-the-art methods to interpret the ability of the proposed method.