一种基于ORB特征的印鉴快速配准算法

A Fast Seal Registration Algorithm Based on ORB Features

印鉴配准是印鉴缺陷检测算法的关键步骤。论文针对圆形印鉴,提出一种基于ORB特征的印鉴快速配准方法。该方法首先计算印鉴的圆心与半径,将印鉴变换到同一尺度范围下;再提取印鉴的ORB特征点进行匹配;然后使用RANSAC算法消除误匹配特征点;最后以印鉴圆心为基准,采用投票策略计算两枚印鉴的相对偏转角度。实验结果表明,该配准方法具有较高的准确性与鲁棒性,能够克服印鉴存在缺陷问题产生的影响,实现快速配准。

eal registration is a key step in the seal defect detection algorithm. This paper proposes a fast circular seal registration method based on ORB feature points. The method first calculates the center and radius of the seal and transforms the seal into the same scale. Then,it extracts ORB feature points of the seal and matches the feature points. And then RANSAC algorithm is used to eliminate the mismatch feature points. Finally,taking the center of the seal as the reference point,voting strategy is used to calculate the relative deflection angles of the two seals. The experimental results show that the proposed registration method has high accuracy and robustness,and can overcome the defect of the seal,and achieve fast registration.