基于FCM和离散正则化的多目标图像分割  

A Multi-Objective Image Segmentation Method Based on FCM and Discrete Regularization

作　　者：刘晓妮[1] 卢奕南[1] 雷玲[2] 瞿子淇 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]华为技术有限公司质量部,深圳518000

出　　处：《计算机辅助设计与图形学学报》2015年第1期142-146,共5页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家教育部博士点基金(20130061110054)

摘　　要：针对机器视觉中的多目标图像分割问题,提出一种适用于多目标物体的图像分割算法.首先对图像进行图像增强预处理;然后采用基于直方图的模糊C均值聚类算法完成分类任务,实现图像的初分割,将分类后的像素作为种子集;最后利用离散正则化的半监督方法得到自动修正分类结果.实验结果表明,与已有的多目标分割算法相比,该算法分割结果更加精确.To address the problem of multi-objective image segmentation in computer vision, a multi-objectiveimage segmentation method based on fuzzy C-Means and discrete regularization is proposed in this paper.First, the method preprocesses an input image with image enhancement. Secondly, the FCM clusteringalgorithm based on histogram is used to classify the pixels in the images into the different categories andrealize the initial segmentations. Finally a discrete regularization algorithm as a semi-supervised method revisesthe classified results. The experiments demonstrate the superior performance of the proposed methodin terms of segmentation accuracy.

关 键 词：图像分割 模糊C均值聚类 离散正则化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]