Intuitionistic fuzzy local information C-means algorithm for image segmentation

Abstract

Image segmentation allows us to separate an image into distinct, non-overlapping parts by utilizing specific features such as hue, texture, and shape. The technique is prevalent in different domains, including target detection, medical imaging, and pattern recognition owing to its importance in analyzing the image. The fuzzy C-means (FCM) algorithm is a popular method for image segmentation and pattern recognition. However, uncertainty and unknown noise in the data impair the effectiveness of the algorithm. Alternatively, uncertainty in real world can be addressed by the intuitionistic fuzzy set (IFS). This article presents a new approach to image representation using IFS and local information about the image. We introduce the concept of filtering into the intuitionistic fuzzy set and utilize a specially designed exponential distance for IFS. We propose the intuitionistic fuzzy local information C-means (IFLICM) algorithm. The goal of IFLICM is to increase the tolerance to noise and the maintain the details in image better than existing FCM variants. We test the performance of our algorithm on a public dataset and compare it with existing FCM methods and Double Deep-Image-Prior (Double-DIP). The experimental results demonstrate that IFLICM is highly effective in image segmentation and outperforms existing methods.