计算机应用 ›› 2012, Vol. 32 ›› Issue (06): 1529-1531.DOI: 10.3724/SP.J.1087.2012.01529

• 图形图像技术 • 上一篇    下一篇

基于图论和均匀性测度的彩色图像分割算法

黄珊珊1,张永良1,2,肖刚1,肖健伟1,张申旭1   

  1. 1. 浙江工业大学 计算机科学与技术学院,杭州 310023
    2. 浙江省可视媒体智能处理技术研究重点实验室，杭州 310000
  • 收稿日期:2011-11-25 修回日期:2012-01-16 发布日期:2012-06-04 出版日期:2012-06-01
  • 通讯作者: 张永良
  • 作者简介:黄珊珊(1989-)，女，浙江苍南人，硕士研究生，主要研究方向：图形图像处理；〓张永良(1977-),男,浙江新昌人,副教授,博士,主要研究方向：目标跟踪与识别、生物特征识别；〓肖刚(1965-),男,浙江上虞人,教授,博士,主要研究方向：图形图像处理、制造业信息化、智能信息系统;〓肖健伟（1991-），男，上海人，主要研究方向：图形图像处理；〓张申旭（1991-），男，浙江象山人，主要研究方向：图形图像处理。
  • 基金资助:
    浙江省自然科学基金资助项目

Color image segmentation based on graph theory and uniformity measurement

HUANG Shan-shan1,ZHANG Yong-liang2,3,XIAO Gang1,XIAO Jian-wei1,ZHANG Shen-xu1   

  1. 1. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou Zhejiang 310023,China
    2. Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province, Hangzhou Zhejiang 310000,China
    3. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou Zhejiang 310023, China
  • Received:2011-11-25 Revised:2012-01-16 Online:2012-06-04 Published:2012-06-01
  • Contact: ZHANG Yong-liang

PDF

摘要： Graph-Based方法是基于图论的彩色图像分割算法中比较新颖的一种方法，且分割速度非常快。针对该算法对边缘和纹理处理效果不佳，且分割效果易受阈值影响的局限，改变了其颜色空间，结合拉普拉斯算子将带权图的边分为边缘边和非边缘边，优先处理非边缘边；再引入均匀性测度求取分割效果最佳的阈值。实验结果表明，相对于Graph-Based方法，改进的算法分割效果具有较好的准确性和适应性，更接近于人眼的感觉。

关键词: 图论, 均匀性测度, 拉普拉斯算子, 颜色空间, 图像分割

Abstract: Efficient Graph-Based algorithm is a novel image segmentation method based on graph theory and it can segment an image at an extraordinary speed. However, it is easily influenced by the threshold value and the segmentation result is imprecise when dealing with the border and texture. Here, an improved algorithm is proposed, which has three main contributions: 1) RGB color space is replaced by Lab color space; 2) Laplacian operator is used to divide the edges of weighted graph into border edges and non-border edges, and those non-border edges are given priority; 3) the optimum threshold is evaluated based on uniformity measurement. Experimental results show that the improved algorithm is more accurate and adaptive than traditional Graph-based algorithms, and segmentation results are closer to human vision property.

Key words: graph theory, uniformity measurement, Laplacian, color space, image segmentation

版权所有 © 2021 四川计算机应用杂志社有限公司
蜀ICP备 05010208 号-3　新出网证(川)字026号
技术支持：北京玛格泰克科技发展有限公司
访问总数：
今日访问：