期刊文献+

基于迭代均值漂移滤波图像分割新算法 被引量:2

Image Segmentation Based on the Mean Shift Smoothing Filter Algorithm
下载PDF
导出
摘要 图像分割技术在系统计算机视觉领域一直扮演着重要的角色.针对传统的图像分割迭代算法由于过分重视图像分割的精确度,造成算法复杂度大大的增加.为了解决该问题,提出了一种全新的基于迭代均值漂移滤波图像分割方法.算法采用了熵作为停止准则,并使用均值移动跟踪滤波来给出递归实时的分割过程.仿真实验结果表明,提出的迭代均值漂移滤波图像分割能快速的有效的分割图像,不仅可以得到了比较高的分割精度,还大大减少了计算量,一定程度上能够改善图片分割的效率和质量. Image segmentation plays an important role in many systems of computer vision.The good performance of recognition algorithms depend on the quality of segmented image.According to the opinion of many authors the segmentation concludes when it satisfies the observer's objectives,the more effective methods being the iterative.However,a problem of these algorithms is the stopping criterion.In this work the entropy is used as stopping criterion in the segmentation process by using recursively the mean shift filtering.In such sense a new algorithm is introduced.The good performance of this algorithm is illustrated with extensive experimental results.The obtained results demonstrated that this algorithm is a straightforward extension of the filtering process.
作者 蒋菱
出处 《微电子学与计算机》 CSCD 北大核心 2011年第9期147-150,共4页 Microelectronics & Computer
关键词 图像分割 均值漂移 平滑滤波器 entropy image segmentation mean shift smoothing filter
  • 引文网络
  • 相关文献

参考文献7

二级参考文献57

共引文献91

同被引文献27

  • 1Lazaros Nalpantidis,Georgios Ch. Sirakoulis Antonios Gasteratos. A dense stereo correspondence algorithm for hardware implementation with enhanced disparity selection[C]//SETN 2008. Greece, 2008 :365-370.
  • 2Hong L,Chen G. Segment-based stereo matching using graph cuts[C]//CVPR. Washington, 2004 : 74-81.
  • 3Jian sun, Zheng Nanning, Shum Heungyeung. Stereo matching using belief propagation[J]. PAMI, 2003,25 (7) : 787-800.
  • 4Bobiek A, Intille S. Large occlusion stereo[J]. Int. J. Comput. Vis, 1999,33 (3) : 181-200.
  • 5Zhang Y, Kambhamettu C. Stereo matching with seg- mentation-based cooperation [C] // European Confer- ence on Computer Vision. Copenhagen, 2002 : 556-571.
  • 6Ke Q, Kanade T. A subspace approach to layer extrac- tion[C]//Conference on Computer Vision and Pattern Recognition. USA: Hawaii, 2001 : 255-262.
  • 7Tao H, Sawhney H S, Kumar tL A global matching framework for stereo computation[J]. ICCV, 2001 ( 1 ) : 532-539.
  • 8Daolei Wang, Kah Bin Lirn. A new segment-based ster- eo matching using graphcuts[C] //3rd IEEE Interna- tional Conference on Computer Science and Information Technology (1CCSIT). China: Chengdu, 2010 ( 5 ) : 410-416.
  • 9徐青,王敏东,李鹏,等.基于图像分割的快速立体匹配算法[J].自动化学报,2009,35(5):209-211.
  • 10Fukunaga K, Hostetler L. The estimation of the gradient of a densi- ty function, with applications in pattern reeognition[ J ]. IEEE Transactions on Information Theory,1975,21 (1) :32-40.

引证文献2

二级引证文献11

;
使用帮助 返回顶部