...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Microprocessors and microsystems >A Fast 2-D Otsu lung tissue image segmentation algorithm based on improved PSO
【24h】

A Fast 2-D Otsu lung tissue image segmentation algorithm based on improved PSO

机译：一种基于改进PSO的快速2-D OTsu肺组织图像分割算法

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

In order to reduce the time of lung tissue image segmentation, we proposed a fast 2-D Otsu lung tissue image segmentation algorithm based on improved PSO. Firstly, in the 2-D Otsu algorithm, the search scope of 2-D gray threshold is limited in a long and narrow region, which is the neighbourhood of the diagonal from the third region to the first region of the 2-D gray histogram, and the search scope and the computation are reduced, operation speed is improved. Secondly, In the PSO algorithm, the position of the particles is adjusted during iterating based on the principle of symmetric disposition, so as to avoid PSO falling into local optimal solution and improves the accuracy of threshold searching. Finally, a lung CT image with 1280x960 resolutions is segmented by our algorithm and other traditional algorithms, and a comparison is given. The segmentation threshold of our method is 85, the difference is less than 5 comparing with that of other traditional algorithms, and it shows that our method has almost the same searching precision as the traditional algorithms. The time cost is only 162ms, which is far less than the traditional algorithms, and it shows that our method improve the segmentation speed. It can be concluded that our method can not only satisfy the requirement of segmentation precision, but also meet the requirement of operation speed.
机译：为了减少肺组织图像分割的时间，我们提出了一种基于改进PSO的快速2-D Otsu肺组织图像分割算法。首先，在2-D OTSU算法中，2-D灰度阈值的搜索范围在长且窄的区域中受到限制，该区域是从第三区域到2-D灰度直方图的第一区域的对角线的邻域并且减少了搜索范围和计算，改善了操作速度。其次，在PSO算法中，基于对称配置原理在迭代期间调整粒子的位置，从而避免PSO落入局部最佳解决方案并提高阈值搜索的准确性。最后，通过我们的算法和其他传统算法对具有1280x960分辨率进行的肺CT图像，并给出了比较。我们方法的分割阈值为85，与其他传统算法的差异相比，差异小于5，并且它表明我们的方法与传统算法几乎相同的搜索精度。时间成本仅为162ms，远远低于传统算法，表明我们的方法提高了分割速度。可以得出结论，我们的方法不仅可以满足分割精度的要求，还可以满足操作速度的要求。

著录项

  • 来源
    《Microprocessors and microsystems》 |2021年第2期|103527.1-103527.8|共8页
  • 作者

    Zhao Yanqiao; Yu Xiaoyang; Wu Haibin; Zhou Yong; Sun Xiaoming; Yu Shuang; Yu Shuchun; Liu He;

  • 作者单位

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China|Harbin Univ Sci & Technol Sch Measurement & Commun Nanjing Peoples R China;

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China|Harbin Univ Sci & Technol Sch Measurement & Commun Nanjing Peoples R China;

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China|Harbin Univ Sci & Technol Sch Measurement & Commun Nanjing Peoples R China;

    Harbin Med Univ Hosp 1 Harbin Peoples R China;

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China;

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China;

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China;

    Harbin Univ Sci & Technol Higher Educ Key Lab Measuring & Control Technol & Harbin Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Threshold segmentation; Lung CT image; Two-dimensional Otsu; Improved PSO; Fast algorithm;

    机译：阈值分割;肺CT图像;二维OTSU;改进的PSO;快速算法;

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