摘要
对于SIFT算法即尺度不变特征变换配准方法在进行图像配准匹配率低的问题,提出了一种再SIFT算法基础上的改进的配准方法。本文主要对图像进行梯度锐化处理,使其边缘得到突出,再利用SIFT算法进行关键点提取,并对锐化后的图像进行匹配。从而完成图像配准。实验结果显示此方法比传统SIFT方法配准结果好,并且匹配率比传统SIFT算法高。
Aiming at the problem of Scale Invariant Feature Transform（SIFT）achieving low matching rate when registrating images, an image registration method based on improved SIFT is proposed.This paper mainly discusses the image gradient sharpening processing, to highlight the edge, reuse SIFT algorithm to extract key point; and match sharpened images.to complete the results show that the method of matching result is superior to SIFT higher than the traditional SIFT algorithm. image registration.The experimental method, and the matching rate is higher than the traditional SIFT algorithm.
出处
《电子设计工程》
2017年第6期185-189,共5页
Electronic Design Engineering
关键词
图像配准
SIFT
梯度锐化
关键点提取
匹配率
image registration
SIFT
gradient sharpening
key point extraction
matching ratio
