Adaptive Kernel-Based Fuzzy C-Means Clustering with Spatial Constraints for Image Segmentation

作者：Hu, Guang^*; Du, Zhenbin

来源：International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33(1): 1954003.

DOI：10.1142/S021800141954003X

• Spatial information constraint
• adaptive weighted coefficient
• KFCM clustering
• image segmentation

In order to resolve the disadvantages of fuzzy C-means (FCM) clustering algorithm for image segmentation, an improved Kernel-based fuzzy C-means (KFCM) clustering algorithm is proposed. First, the reason why the kernel function is introduced is researched on the basis of the classical KFCM clustering. Then, using spatial neighborhood constraint property of image pixels, an adaptive weighted coefficient is introduced into KFCM to control the influence of the neighborhood pixels to the central pixel automatically. At last, a judging rule for partition fuzzy clustering numbers is proposed that can decide the best clustering partition numbers and provide an optimization foundation for clustering algorithm. An adaptive kernel-based fuzzy C-means clustering with spatial constraints (AKFCMS) model for image segmentation approach is proposed in order to improve the efficiency of image segmentation. Various experiment results show that the proposed approach can get the spatial information features of an image accurately and is robust to realize image segmentation.

• 出版日期2019-1
• 单位烟台大学