Instruments and Systems: Monitoring, Control, and Diagnostics Annotation << Back Comparison of Fuzzy Clustering Methods Used to Extract Features of Objects in an Image P.I. KARASEV, YU.YU. GROMOV, T.G. SAMKHARADZE, I.A. METELEV, A.V. RYAZANTSEV Image segmentation is the process by which an image is divided into areas with similar characteristics. Many approaches have been proposed for segmentation of color images, but the fuzzy C-means method has been widely used because it has good performance for a large class of images. However, it is not suitable for noisy images, and it takes longer to execute compared to another method such as K-means. For this reason, several methods have been proposed to address these shortcomings. Methods such as probabilistic C-means, fuzzy probabilistic C-means, Robust (outlier) fuzzy probabilistic C-means and fuzzy C-means with the Gustafson-Kessel algorithm. In this article, we compare these clustering methods used to extract features in images. Segmented images are evaluated using several quality parameters, such as the frequency of the correctly classifi ed area and the execution time. Keywords: clustering by FCM method, image segmentation. DOI: 10.25791/pribor.11.2023.1452 Pp. 14-21.