Auto feature weighted c-means type clustering methods for color image segmentation

To address the limitations of existing hard c-means (HCM) and fuzzy c-means (FCM) methods, we develop four novel clustering methods: vector-weighted alternative hard c-means (VWAHCM), matrix-weighted alternative hard c-means (MWAHCM), vector-weighted alternative fuzzy c-means (VWAFCM), and matrix-weighted alternative fuzzy c-means (MWAFCM). These methods enhance clustering performance by incorporating nonEuclidean norm metrics and vector-weighted and matrix-weighted schemes without adding extra parameters. Our methods modify the traditional weight constraint from a sum to a product of weights, thereby improving robustness and accuracy. Comprehensive experiments conduct on various real-world datasets and color image segmentation tasks demonstrate the superiority of the proposed methods over traditional HCM and FCM variants. The results show significant improvements in clustering Accuracy (ACC), Normalized mutual information (NMI), Rand index (RI), and Fowlkes-Mallows index (FM). Furthermore, the proposed methods exhibit fast convergence and robust performance, proving their effectiveness in practical applications.