计算机应用 ›› 2015, Vol. 35 ›› Issue (9): 2619-2623.DOI: 10.11772/j.issn.1001-9081.2015.09.2619

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于U弦长曲率的抗旋转性广义Hough变换算法

陈彬彬, 邓新蒲, 杨俊刚   

  1. 国防科学技术大学 电子科学与工程学院, 长沙 410073
  • 收稿日期:2015-04-02 修回日期:2015-06-02 出版日期:2015-09-10 发布日期:2015-09-17
  • 通讯作者: 陈彬彬(1989-),男,河南洛阳人,硕士研究生,主要研究方向:空间信息获取与处理、图像处理,borg_2013@163.com
  • 作者简介:邓新蒲(1966-),男,湖北武汉人,副教授,博士,主要研究方向:空间信息获取与处理、无源定位;杨俊刚(1984-),男,江西樟树人,讲师,博士,主要研究方向:空间信息获取与处理。
  • 基金资助:
    国家自然科学基金资助项目(61401474)。

Orientation-invariant generalized Hough transform algorithm based on U-chord curvature

CHEN Binbin, DENG Xinpu, YANG Jungang   

  1. School of Electronic Science and Engineering, National University of Defense Technology, Changsha Hunan 410073, China
  • Received:2015-04-02 Revised:2015-06-02 Online:2015-09-10 Published:2015-09-17

摘要: 针对广义Hough变换(GHT)算法匹配发生旋转图像中的目标形状时发生误匹配的问题,提出一种基于U弦长曲率的具有抗旋转性的广义Hough变换算法。首先,对模板形状采用边缘点的U弦长曲率和偏移向量等特征构建具有旋转不变性的修改的R-表;其次,以图像中边缘点的曲率作为索引,查找构建的R-表得到偏移向量等信息;最后,根据查得的信息计算图像中目标形状的可能的参考点位置进行投票。根据投票结果即可提取出图像中目标形状的位置。当图像中目标形状分别旋转0°、2°、4°、5°、6°时,提出的算法的匹配结果均在图像中目标形状位置具有非常明显的峰值。仿真结果表明,改进的广义Hough变换(I-GHT)算法具有良好的抗旋转性和抗噪性。

关键词: 广义Hough变换, 旋转不变性, U弦长曲率, 目标识别, 形态分析

Abstract: Focusing on the mismatch occurred in template matching when using Generalized Hough Transform (GHT) algorithm to extract the target shape from the rotated image, an improved orientation-invariant generalized Hough transform algorithm based on U-chord curvature was proposed. Firstly, the modified R-table with orientation-invariant performance was constructed by using features of U-chord curvature and displacement vectors of edge points of the template shape; secondly, the information such as the displacement vector was achieved by calculating the curvature of edge points as an index to lookup the constructed R-table; finally, the possible locations of reference points were calculated according to the information. The point with maximum voting was the location of the target shape of the image. When the target shape of the image is rotated by 0°, 2°, 4°, 5° and 6° individually, the sharper peaks occur in the target shape position of all the rotation images by using the proposed algorithm. The simulation results show that the Improved Generalized Hough Transform (I-GHT) algorithm has high stability in rotation and noise conditions.

Key words: Generalized Hough Transform (GHT), orientation-invariant, U-chord curvature, target recognition, shape analysis

中图分类号: