期刊文献+

基于全局最小二乘拟合的直线抽取算法

A Global Least Squares Based Method for Extracting Straight Lines
下载PDF
导出
摘要 提出了基于全局最小二乘拟合的应用于二维图像的直线抽取算法.类似于一维数据曲线拟合的方法,通过引入叉分的手段,克服了二维图像数据非单值函数的困难(图像的y坐标作为x坐标的函数),实现了用最小二乘算法来全局地描述、提取二维图像中的直线.并提供了数值实验验证. Based on global least squares fitting, an algorithm of extracting straight lines on the two-dimensional picture is proposed. Similar to curve fitting on the one-dimensional data, the difficulty has overcome that the function of two-dimensional picture is multi-valued ( the y coordinate as the x coordinate), with the help of forked method; and it realizes the global description and extraction of the straight lines in the two-dimensional picture using the least squares algorithm. The experiment shows that this algorithm is effective.
出处 《集美大学学报(自然科学版)》 CAS 2008年第3期255-260,共6页 Journal of Jimei University:Natural Science
基金 国家自然科学基金资助项目(60772164) 福建省自然科学基金资助项目(A0540005)
关键词 直线抽取 直线拟合 非单值的 叉分 extracting straight lines straight line fitting multi-valued forking
  • 相关文献

参考文献8

  • 1BEVERIDGE J R, RISEMANISEMAN E M. How easy is matching 2D line models using local search [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19(6) : 564-579.
  • 2IQBAL Q, GGARWAL J K. Retrieval by classification of images containing large manmade objects using perceptual grouping [J]. Pattern Recognition Journal, 2002, 5(7) : 1463-1479.
  • 3LUO A, TAO W. A new multilevel line-based stereo-vision algorithm based on fuzzy techniques [C] //Proc of the 13th International Conference on Pattern Recognition. Vol.1. Vienna Austria: IEEE, 1996: 383-387.
  • 4CHO PRA R. An architecture for exploiting qualitative, scene-specific context in high-level computer vision. [ D ]. N. Y. : State University of New York, 1997.
  • 5BURNS J B, HANSON A R. Extracting straight lines [ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(4) : 425-455.
  • 6KAHN P, KITCHEN L. A fast line finder for vision-guided robot navigation [ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(11) : 1098-1102.
  • 7王亮,卜佳俊.参数控制的边缘直线提取算法[J].计算机工程,2004,30(1):148-149. 被引量:1
  • 8卜佳俊,王亮,陈纯.一种可参数化的快速直线提取算法[J].浙江大学学报(工学版),2003,37(4):410-414. 被引量:3

二级参考文献11

  • 1[1]Burns J B, Hanson A R, Riseman E M. Extracting Straight Lines. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(4): 425-455
  • 2[2]Kahn P, Kitchen L, Riseman E M. A Fast Line Finder for Vision- guided Robot Navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12 (11): 1098-1102
  • 3[3]Beveridge J R, Riseman E M. How Easy is Matching 2D Line Models Using Local Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(6): 564-579
  • 4BURNS J B, HANSON A R, RISEMAN E M. Extracting straight lines [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(4):425-455.
  • 5KAHN P, KITCHEN L, RISEMAN E M. A fast line finder for vision-guided robot navigation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(11): 1098--1102.
  • 6BEVERIDGE J R, RISEMAN E M. How easy is matching 2D line models using local search[J].IEEE Transactions on Pattern Analysis and Machine Inteiligence, 1997, 19(6): 564--579.
  • 7IQBAL Q, AGGARWAL J K. Retrieval by classification of images containing large manmade objects using perceptual grouping [J]. Pattern Recognition Journal,2002, 35(7): 1463--1479.
  • 8LUO A, TAO W, BURKHARDT H. A new multilevel line-based stereo vision algorithm based on fuzzy techniques[A]. Proe of the 13th international Conference on Pattern Recognition vol. 1 [C]. Vienna Austria:IEEE, 1996. 383-- 387.
  • 9CHOPRA R. An architecture for exploiting qualitative,scene-specific context in high level computer vision[d]. Buffalo, NY, USA: State University of New,York,1997.
  • 10DAUMUELLER K.Extracting lines with a reconfigurable mesh parallel processor [R]. Amherst, MA:Department of Computer Science, University of Massachusetts, 1994.

共引文献2

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