期刊文献+

对亮度不均匀性图像的活动轮廓线分割 被引量:1

Active contour segmentation for in-homogeneity images
下载PDF
导出
摘要 基于区域的活动轮廓模型的基本思想是允许轮廓线形变以获得最小化的区域能量函数,由于通常依赖于每个待分割区域的亮度均匀性,因而不能正确分割亮度不均匀性图像。同时活动轮廓模型传统的基于水平集的数值解法运算速度慢,对初始条件敏感。提出一种基于可伸缩局部区域拟合能量的活动轮廓线模型及其全局凸分割方法,以图像的局部区域内亮度不均匀性相对较弱为依据,以核函数获取图像的局部区域,通过定义局部区域内轮廓线的拟合能量函数和其轮廓线两边的局部灰度近似函数来分割亮度不均匀性图像,使轮廓线的进化不再依赖于图像的亮度均匀性,再使用SplitBregman优化方法来进行模型的数值运算。实验结果表明,该算法既能较好地分割亮度不均匀性图像,又具有比基于水平集的传统算法快速的轮廓线进化速度。 The basic idea of region-based active contour models is to make a contour to deform so as to get a minimized given region energy functional. As it tends to be effective only for the regions which are of intensity homogeneity, it often leads to erroneous seg- mentations for images of intensity in-homogeneities. In addition, the conventional level set approach of active contour models is time- consuming and depends greatly on the initialization the contour. Therefore, a new kind of active contour model is proposed, which is on the basis of local region fitting energy and its global convex segmentation method. In order to make the evolution of the contour rely less on the intensity homogeneity, this method utilizes the kernel function to extract the local region and then defines its local region fitting energy and two fitting functions which approximate the image intensities on the two sides of the contour in the local region. Finally the Split Bregman method is used to get the numerical solution of the model. Experimental results show that our approach can accurately segment images of intensity in-homogeneity and is more efficient than the traditional level set based methods.
出处 《计算机工程与设计》 CSCD 北大核心 2011年第11期3755-3758,共4页 Computer Engineering and Design
基金 国家自然科学基金项目(30900380) 广东省自然科学基金项目(N9151051501000026)
关键词 活动轮廓线 SplitBregman方法 局部区域拟合能量 亮度不均匀 active contour Split Bregrnan method local region fitting energy intensity in-homogeneity
  • 相关文献

参考文献15

  • 1Li Chunming, Kao Chiu-Yen, John C, et al.Minimization of region-scalable fitting energy for image segmentation [J]. IEEE Trans Image Processing,2008,17(10): 1940-1949.
  • 2Lankton S,Tannenbaum A.Localizing region-based active contours [J]. IEEE Transactions on Image Processing,2008,17 (11): 2029-2039.
  • 3Tony F Chan,Luminita A Vese.Active contours without edge[J]. IEEE Trans Image Process,2001,10(2):266-277.
  • 4Tony F Chan, Selim Esedogluy, Mila Nikolova. Algorithms for finding global minimizers ofdenoising and segmentation models [J]. SIAM Journal on Applied Mathematics, 2006,66 (5): 1632-1648.
  • 5Xavier Bresson,Selim Esedoglu,Pierre Vandergheynst,et al.Fast global minimization of the active contour/snake model[J].Journal of Mathematical Imaging and Vision,2007,28(2): 151-167.
  • 6Xu Ning, Ravi Bansal, Narendra Ahuja. Object segmentation using graph cuts based active contours[J].Computer vision and image understanding,2007,107(3):210-224.
  • 7Tom Goldstein, Xavier Bresson, Stanley Osher. Geometric applications of the split bregman method: segmentation and sur- face reconstruction[R].CAM Report,2009.
  • 8Tom Goldstein,Stanley Osher.The split bregman method for 11 regularized problems[R].UCLA CAM Report,2008.
  • 9Tai Xue-Cheng, Wu Chunlin. Augmented lagrangian method, dual methods and split bregman iteration for ROF model[C].Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision,2009:502-513.
  • 10Setzera S,Steidla G, Teuber T.Deblurring Poissonian images by split bregman techniques[J].Joumal of Visual Communication and Image Representation,2010,21 (3): 193-199.

同被引文献5

引证文献1

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部