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００１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.
出处
《计量学报》
CSCD
北大核心
1997年第3期227-231,共5页
Acta Metrologica Sinica
基金
国家自然科学基金
关键词
图象测量
目标定位
图象匹配
二次曲面拟合
Image measurement
Object locating
Image matching
Subpixel image matching
Quadratic surface fitting
