›› 2012, Vol. 25 ›› Issue (10): 11-.

• 论文 • 上一篇    下一篇

基于特征序列匹配函数的快速图像匹配

郑兴明   

  1. (南京航空航天大学 计算机科学与技术学院,江苏 南京 210016)
  • 出版日期:2012-10-15 发布日期:2012-11-29
  • 作者简介:郑兴明(1988—),男,硕士研究生,AIAA会员。研究方向:图像处理,计算机视觉和模式识别。
  • 基金资助:

    中央高校基本科研业务费专项资金资助项目(No.kfjj20110241);南京航空航天大学研究生创新基地开放基金资助项目(20110241)

Fast Image Matching Based on Sub-Image Content Matching Function

 ZHENG Xin-Ming   

  1. (School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China)
  • Online:2012-10-15 Published:2012-11-29

摘要:

为解决在导弹制导、目标搜寻等领域中图像快速匹配的问题,提出一种基于图像局部特征序列的匹配函数,以加快图像匹配速度。该算法将匹配图像和查找图像分为若干相同大小的子图片,并计算它们的局部特征,形成一个带有特征的序列,利用提出的特征序列匹配函数,计算两种图像内容的特征序列下的匹配情况,该匹配函数能够利用匹配图像本身的特征信息提高图像匹配的查找速度。由于匹配图像特征序列之间存在关联,在匹配失效的情况下,不用再从查找图像的特征序列起始点重新进行查找匹配,而是根据匹配函数,计算出新的匹配点,从新的匹配点进行匹配,加快图像匹配的速度。

关键词: 匹配函数, 图像匹配, 尺度不变特征

Abstract:

In order to solve the image matching problems in the field of missile guidance,target search and other fields,a fast image matching method-the matching function method based on the sub-image features is proposed to accelerate the speed of matching.The matching image and the search image are divided into a number of sub-images of the same size and their scale invariant features are calculated.These features form a sequence.The failure function produces the matching results by calculating the characteristic sequences of the two images.It takes advantage of the characteristic sequences of the image itself to improve the search speed of image matching.Due to the association of the image characteristic sequences,the algorithm does not restart its application from the original characteristics sequence,but according to the lapse function,producing a new position to matching.

Key words: matching function;Image matching;SIFT

中图分类号: 

  • TP391.41