Compact Fuzzy BLS Driven Semi-Supervised Multi-Objective Evolutionary Adaptive Multiple-Kernel Fuzzy Clustering for Color Image Segmentation

Multi-objective evolutionary algorithms (MOEAs)-based fuzzy clustering have been successfully applied to image segmentation problems. However, these MOEAs require a lot of expensive fitness function evaluations. In order to make full use of image prior information and multi-kernel advantages as well as further improve the segmentation performance and time efficiency for image segmentation, a compact fuzzy broad learning system (CFBLS) surrogate-assisted semi-supervised multi-objective evolutionary adaptive multiple-kernel fuzzy clustering (CFBLS-S
²
AMKFC) algorithm is proposed in this paper. The main contributions of CFBLS-S
²
2AMKFC are described as follows: first, a semi-supervised adaptive multiple-kernel weights fuzzy clustering fitness function is constructed to obtain satisfactory segmentation results; second, using CFBLS model predict the real objective function values in the MOEAS framework, thus reducing the time complexity of the algorithm, and third, constructing a semi-supervised multi-kernel clustering validity index to select the optimal solution from the final nondominated solution set. Experiment results on Berkeley images demonstrate that the proposed algorithm CFBLS-S
²
AMKFC has good segmentation accuracy and low time cost.