计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 116-117.doi: 10.11896/j.issn.1002-137X.2016.6A.027

• 模式识别与图像处理 • 上一篇    下一篇

利用傅里叶变换边缘曲线法进行W型轮廓的快速匹配

王洋,张琴   

  1. 西安交通大学软件学院 西安710049,西安交通大学软件学院 西安710049
  • 出版日期:2018-12-01 发布日期:2018-12-01

Using Contour Edge Curve’s Fourier Transform Method to Faster Match W-Shaped Pattern

WANG Yang and ZHANG Qin   

  • Online:2018-12-01 Published:2018-12-01

摘要: W型轮廓标靶是一种用于汽车四轮定位的定位标靶,在一幅定位图像中能够快速地检索出与其一致的目标轮廓非常重要。传统的Hu矩、成对几何直方图算法运算速度慢,鲁棒性差。而一些适用于商标图像检索的傅里叶描述子却可以很好地适用于快速轮廓匹配,但是由于在一幅图像中进行目标轮廓的检索引入了过多的轮廓干扰,因此利用形状图像的傅里叶变换提取出轮廓的频谱特征,通过检查目标轮廓对模板轮廓频谱特征的干扰性大小来进行轮廓的相似性度量,并进行算法简化,从而达到轮廓快速匹配的目的。并且其抗干扰能力强,轮廓查找效率高。这说明利用傅里叶变换边缘曲线法进行轮廓形状匹配具有很好的适用性。

关键词: 图像,傅里叶描述子,轮廓匹配

Abstract: The “W” pattern target is a kind of four-wheel alignment’s calibration target.It is very important to search the right contour in a positioning image quickly.The Hu moment and the pair-wise geometric histograms algorithm are traditional methods,and they are low in speed and poor in robustness.Some Fourier descriptor for trademark image retrieval can be well applied to quick contour matching.But searching a target contour in an image may introduce too much interference of many contours.In this paper,we used the Fourier transform to extract the contour’s spectrum characteristics,then measured the similarity by examining the disruptive of target contour to the template contour,and simplified the algorithm to achieve the goal of fast matching.Its anti-interference ability is strong,and searching efficiency is high.This suggests that the method of Fourier transform of edge curve to match contour has good applicability.

Key words: Image,Fourier descriptor,Contour matching

[1] 丁险峰,吴洪,张宏江,等.形状匹配综述[J].自动化学报,2001,27(5):678-693
[2] 张京明,张宇晗,等.基于不变矩和灰度匹配的汽车跟踪算法[J].农业装备与车辆工程,2015,53(6):13-15
[3] Li L.Building an accurate 3D model of a circular feature for robot vision[J].Opto-Electronics Review,2012,0(2):120-125
[4] Chu Jun,Zheng An,Lu Guo,et al.Chessboard corner detection under Image physical coordinate[J].Optics and Laser Technology,2013,48:599-605
[5] 朱科钤,卢章平.基于极坐标和傅里叶描述子的二值商标图像检索[J].农业机械学报,2006,37(11):100-121
[6] 范春年,傅德胜.一种改进的二维傅里叶描述子在基于形状的图像检索中的应用[J].武汉理工大学学报(交通科学与工程版),2004,28(2):266-269
[7] 罗磊.基于轮廓的形状匹配方法研究[D].长沙:国防科技大学,2008
[8] Kim H K,Kim J D.Region-based shape descriptor invariant to rotation scale and translation[J].Signal Processing:Image Communication,2000,16(1/2):87-93

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!