首页 | 官方网站   微博 | 高级检索  
     

基于谱聚类的多闭值图像分割方法
引用本文:邹小林,陈伟福,冯国灿,刘志勇,汤鑫.基于谱聚类的多闭值图像分割方法[J].计算机科学,2012,39(3):246-248.
作者姓名:邹小林  陈伟福  冯国灿  刘志勇  汤鑫
作者单位:(中山大学数学与计算科学学院 广州 510275);(肇庆学院数学与信息科学学院 肇庆 526061); (广东省计算科学重点实验室 广州 5102750);(深圳职业技术学院工业中心 深圳 518055)
基金项目:国家自然科学基金项目(60975083,U0835005)资助
摘    要:阈值法是图像分割的一种重要方法,在图像处理与目标识别中广为应用。因此,如何确定阈值是图像分割的关键。提出了一种新的图像阈值分割方法,即通过采用新的相似度函数的谱聚类算法(Dcut)确定图像阈值。采用基于灰度级的权值矩阵代替常用的基于图像像素级的权值矩阵描述图像像素的关系,因而算法需要的存储空间及实现的复杂性与其它基于图的图像分割方法相比大大减少。实验表明,该方法分割图像的时间少,且能够单阈值和多阈值分割图像,与现有的阈值分割方法相比,其具有更为优越的分割性能。

关 键 词:图像阈值分割  多阈值  谱聚类  Dcut

Image Segmentation of Multilevel Thresholding Based on Spectral Clustering
ZOU Xiao-lin,CHEN Wei-fu,FENG Guo-can,LIU Zhi-yong,TANG Xin.Image Segmentation of Multilevel Thresholding Based on Spectral Clustering[J].Computer Science,2012,39(3):246-248.
Authors:ZOU Xiao-lin  CHEN Wei-fu  FENG Guo-can  LIU Zhi-yong  TANG Xin
Affiliation:1,3(School of Mathematics and Computational Sciences,Sun Yat-sen University,Guangzhou 510275,China)1(School of Mathematics and Information Sciences,Zhaoqing University,Zhaoqing 526061,China)2(Guangdong Province Key Laboratory of Computational Science,Guangzhou 510275,China)3(Industry Centre,Shenzhen Polytechnic,Shenzhen 518055,China)4
Abstract:The thresholding is an important form of image segmentation and is used in many applications that involve image processing and object recognition. hhus, it is crucial to how to acquire a threshold of image segmentation. A novelmultilevel thresholding algorithm was presented in order to improve image segmentation performance at lower computational cost. hhe proposed algorithm determines the thresholdings by spectral clustering algorithm called Dcut that uses a new similarity function. hhe weight matrices used in evaluating the graph cuts arc based on the gray levels of an image, rather than the commonly used image pixels. For most images, the number of gray levels is much smaller than the number of pixels. Therefore, proposed algorithm occupies much smaller storage space and requires much lower com- putational costs and implementation complexity than other graph-based image segmentation algorithms. A large number of examples were presented to show the superior performance by using the proposed multilevel thrcsholding algorithm compared to existing thresholding algorithms.
Keywords:Image thresholding segmentation  Multilevel thresholding  Spectral clustering  Dcut
本文献已被 CNKI 等数据库收录!
点击此处可从《计算机科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号