计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (7): 86-88.

• 学术探讨 • 上一篇    下一篇

基于一种快速鲁棒特征描述子的图像匹配

吴 铮,孙 立,夏一民,汪亚明   

  1. 浙江理工大学 信息与电子学院,杭州 310018
  • 收稿日期:2007-06-21 修回日期:2007-09-10 出版日期:2008-03-01 发布日期:2008-03-01
  • 通讯作者: 吴 铮

Image correspondence based speed feature descriptor

WU Zheng,SUN Li,XIA Yi-min,WANG Ya-ming   

  1. College of Informatics and Electronics,Zhejiang Sci-Tech University,Hangzhou 310018,China
  • Received:2007-06-21 Revised:2007-09-10 Online:2008-03-01 Published:2008-03-01
  • Contact: WU Zheng

摘要: 基于一种快速鲁棒特征描述子进行图像特征点之间的匹配。此方法基于积分图像,使用快速Hessian检测子来提取图像特征点。对每个特征点,通过计算Haar小波,来寻找它的主方向。然后构造窗口区域,以主方向和与主方向垂直的方向上的小波和来描述特征点。最后以特征描述向量的距离为标准寻找不同图像之间的特征匹配。

Abstract: This paper proposes a method about image correspondence based on a speed robust feature descriptor.This relies on integral images and Fast-Hessian detector to extract interest points.For each feature point,the dominant orientation is assigned by computing Haar-wavelet responses.Based on these orientations constructing a window around the feature point,the feature points are decrypted by the sum of Haar-wavelet responses on the domination orientation and the verticality.Image correspondences are made based on distance between these descriptors.