郑州大学学报（理学版）2018，Vol.50Issue(2)：75-80,6.DOI:10.13705/j.issn.1671-6841.2017094
彩色图像分割的FCM预分类核极限学习机方法
FCM Pre-classification Kernel Extreme Learning Machine Algorithm of Color Image Segmentation
摘要
Abstract
Based on the study of clustering algorithm and extreme learning machine, a kernel extreme learning machine(KELM)with fuzzy C mean clustering algorithm(FCM)pre-classification and its ap-plication in color image segmentation were implemented.Firstly,FCM pre-classification training samples were adopted by the algorithm.Then,the image features were extracted from the color image as attributes of training samples of KELM.Finally,the color images were segmented by the trained classifier.It was demonstrated that the segmentation speed and accuracy of color image segmentation algorithm were better than that of FCM pre classification BP artificial neural network and FCM pre classification support vector machine.The algorithm was proved to be an efficient color image segmentation algorithm.关键词
图像分割/聚类算法/核极限学习机Key words
image segmentation/clustering algorithm/Kernel extreme learning machine分类
信息技术与安全科学引用本文复制引用
王杰,刘向晴..彩色图像分割的FCM预分类核极限学习机方法[J].郑州大学学报（理学版）,2018,50(2):75-80,6.基金项目
国家自然科学基金项目(61473266). （61473266）
