基于二次曲面拟合的亚象素图象匹配算法  

A Subpixel Image Matching Algorithm by Quadratic Surface Fitting

作　　者：侯成刚[1] 赵明涛[1] 屈梁生[1] 

机构地区：[1]西安交通大学机械工程学院

出　　处：《计量学报》1997年第3期227-231,共5页Acta Metrologica Sinica

基　　金：国家自然科学基金

摘　　要：在图象测量系统中，目标的精确定位是一个关键问题，也是应用其它图象处理技术的基础。传统的图象匹配算法只能在象素级定位，本文基于相关函数的二次曲面拟合提出了一种亚象素精度的匹配算法，它对于无噪声图象匹配的绝对误差小于００１象素。模拟实验表明，在有噪声的情况下该算法仍具有较小的偏差。Accurate object locating is a key problem in image measurement system, and it is also the basis of other image processing procedure. Conventional image matching algorithm could only be implemented at pixel accuracy. Based on the quadratic surface fitting technique, a new subpixel image matching algorithm is presented in this paper. By the proposed method the absolute error of image matching might be less than 0.01 pixel for noise-free images. Additionally, experiments show that the algorithm has a relatively small bias in the presence of noise.

关 键 词：图象测量 目标定位 图象匹配 二次曲面拟合 

分 类 号：TN919.8[电子电信—通信与信息系统] TP873[电子电信—信息与通信工程]