• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Energy minimazation methods in computer vision and pattern recognition. >Global Relabeling for Continuous Optimization in Binary Image Segmentation
【24h】

Global Relabeling for Continuous Optimization in Binary Image Segmentation

机译：全局重新标记，用于二值图像分割中的连续优化

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recently, continuous optimization methods have become quite popular since they can deal with a variety of non-smooth convex problems. They are inherently parallel and therefore well suited for GPU implementations. Most of the continuous optimization approaches have in common that they are very fast in the beginning, but tend to get very slow as the solution gets close to the optimum. We therefore propose to apply global relabeling steps to speed up the convergence close to the optimum. The resulting primal-dual algorithm with global relabeling is applied to graph cut problems as well as to Total Variation (TV) based image segmentation. Numerical results show that the global relabeling steps significantly speed up convergence of the segmentation algorithm.
机译：最近，连续优化方法可以处理各种非光滑凸问题，因此变得非常流行。它们本质上是并行的，因此非常适合GPU实现。大多数连续优化方法的共同点是它们在一开始就非常快，但是随着解决方案接近最佳值，往往会变得非常慢。因此，我们建议采用全局重新标记步骤以加快收敛速度​​，使其接近最佳状态。带有全局重新标记的原始对偶算法将应用于图割问题以及基于总变化（TV）的图像分割。数值结果表明，全局重标记步骤显着加快了分割算法的收敛速度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号