摘要
光学技术的发展对光学元件提出了更高的要求,检测的精度和准确性是其重要的部分,而疵病图像的配准是一个很重要的环节,因此对疵病图像的配准进行研究很有必要。针对疵病图像配准算法进行了阐述,并对基于特征点匹配的SIFT算法的原理及过程进行了介绍,用MATLAB软件进行编程,搭建实验平台获取疵病图像,并采用尺度不变特征变换(SIFT)算法对所获取的疵病图像进行配准、拼接,得到了完整的疵病图像。实验结果表明,该算法能有效地对疵病图像进行配准,为后续的疵病信息提取打下良好的基础。
With the development of optical technology,higher requirements have been put forward for optical components.The accuracy and veracity of detection is an important part of optical components.The registration of defective images is a very important link.Therefore,it is necessary to study the registration of defective images.Aiming at the defect image registration algorithm,the principle and process of SIFT algorithm based on feature point matching are introduced.The experimental platform is programmed by MATLAB software to obtain the defect image.The defect image is registered and mosaic by SIFT algorithm,and the complete defect image is obtained.The experimental results show that the algorithm can effectively register the defect image and lay a good foundation for the subsequent defect information extraction.
作者
刘璐
刘缠牢
Liu Lu;Liu Chanlao(School of Optoelectronic Engineering,Xi’an Technological University,Xi’an 710021,China)
出处
《电子测量技术》
2019年第6期94-98,共5页
Electronic Measurement Technology
关键词
疵病检测
疵病信息提取
特征点
图像配准
SIFT算法
defect detection
defect information extraction
feature points
image registration
SIFT algorithm
