...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Sensing and imaging >An Auto‑Segmentation Algorithm for Multi‑Label Image Based on Graph Cut
【24h】

An Auto‑Segmentation Algorithm for Multi‑Label Image Based on Graph Cut

机译：基于图割的多标签图像自动分割算法

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

The image segmentation algorithm based on graph cut guarantees arnglobally optimal solution for energy solution, which is usually with the aid of user’srninteractive operation. For the multi-label image segmentation application, the graphrncut algorithm has two drawbacks. Firstly, it has a higher computational complexityrnof segment multi-label images. Secondly, it is prone to be trapped in local minimarnwhen solves the energy formulation. For the two drawbacks, this paper presents anrnauto-segmentation algorithm based on graph cut to segment multi-label images. Thernnumber of the labels is obtained via the main colors of the image, then the mainrncolors are employed as pre-specified nodes feature, rather than select seeds withrnthe aid of prior knowledge or initialization operation by the user. The seeds can bernselected automatically without complex mathematical formulations to computerize,rnand it reduces the computational complexity successfully, and avoids falling intornlocal minima effectively. In additional, we use a fast α-expansion move algorithm tornoptimize the energy function, which can improve the speed of segmentation. Comparingrnthe proposed algorithm with the state-of-the-art segmentation methods, thernexperimental results show that the proposed algorithm has superior performance.
机译：基于图割的图像分割算法保证了能量解决方案在全局范围内的最优解，这通常是在用户交互操作的帮助下进行的。对于多标签图像分割应用，graphrncut算法有两个缺点。首先，它具有较高的计算复杂度。其次，当求解能量公式时，它容易陷入局部极小值中。针对这两个缺点，提出了一种基于图割的多标签图像自动分割算法。通过图像的主要颜色获得标签的数量，然后将主要颜色用作预定的节点特征，而不是借助用户的先验知识或初始化操作来选择种子。无需复杂的数学公式即可自动选择种子进行计算机化处理，成功降低了计算复杂度，有效避免了陷入局部极小。另外，我们使用快速的α扩展移动算法对能量函数进行优化，从而可以提高分割速度。将所提算法与最新的分割方法进行比较，实验结果表明，所提算法具有优越的性能。

著录项

  • 来源
    《Sensing and imaging》 |2018年第1期|9.1-9.14|共14页
  • 作者

    Yali Qi; Guoshan Zhang; Yeli Li;

  • 作者单位

    School of Electrical and Information Engineering, Tianjin University, 92 Weijin Road, Nankai District, Tianjin, People’s Republic of China Department of Computer Science, Beijing Institute of Graphic Communication, 1 Xinghua Avenue (Band Two), Daxing District, Beijing, People’s Republic of China;

    School of Electrical and Information Engineering, Tianjin University, 92 Weijin Road, Nankai District, Tianjin, People’s Republic of China;

    Department of Computer Science, Beijing Institute of Graphic Communication, 1 Xinghua Avenue (Band Two), Daxing District, Beijing, People’s Republic of China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Graph cut; Multi-label segmentation; α-expansion; Min-cut/maxflow;

    机译：图切;多标签细分;α-膨胀最小切割/最大流量;

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