2021/02/18 by Sara Inés Rizo Rodríguez, Rodriguez, Sara Ines Rizo, Francisco de A.T. de Carvalho +1
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Face and Expression Recognition #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2102.09529
openalex publication_date 2021/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The clustering methods have been used in a variety of fields such as image\nprocessing, data mining, pattern recognition, and statistical analysis.\nGenerally, the clustering algorithms consider all variables equally relevant or\nnot correlated for the clustering task. Nevertheless, in real situations, some\nvariables can be correlated or may be more or less relevant or even irrelevant\nfor this task. This paper proposes partitioning fuzzy clustering algorithms\nbased on Euclidean, City-block and Mahalanobis distances and entropy\nregularization. These methods are an iterative three steps algorithms which\nprovide a fuzzy partition, a representative for each fuzzy cluster, and the\nrelevance weight of the variables or their correlation by minimizing a suitable\nobjective function. Several experiments on synthetic and real datasets,\nincluding its application to noisy image texture segmentation, demonstrate the\nusefulness of these adaptive clustering methods.\n