计算机与现代化

• 图像处理 • 上一篇    下一篇

基于稀疏特征点的零件图像拼接方法

  

  1. (1.西南科技大学计算机科学与技术学院,四川绵阳621010;2.四川天一学院信息工程系,四川绵竹618200)
  • 收稿日期:2018-07-07 出版日期:2019-02-25 发布日期:2019-02-26
  • 作者简介:张勤(1987-),女,四川眉山人,助教,硕士研究生,研究方向:图像拼接,E-mail: 624046263@qq.com; 贾渊(1973-),男,四川营山人,教授,博士,研究方向:图像处理,E-mail: 114997152@qq.com。
  • 基金资助:
    国家自然科学基金面上项目(61672438); 龙山学术人才科研支持计划项目(17LZXJ09)

A Part Image Mosaic Method Based on Sparse Feature Points

  1. (1. School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, China;
    2. Department of Information Engineering, Sichuan Tianyi College, Mianzhu 618200, China)
  • Received:2018-07-07 Online:2019-02-25 Published:2019-02-26

摘要: 针对纹理弱、特征稀少且存在大量相似性区域的零件图像拼接,一般基于特征点的图像拼接方法效果较差,本文提出一种改进方法。该方法首先依据FAST特征点检测方法提取特征点,再筛选出用于匹配的候选点集;其次,利用模板区域采样灰度特征,通过设置旋转角度和缩放比例搜索域结合结构相似性(SSIM)方法完成点匹配;最后,通过点匹配结果求出旋转、缩放和平移参量,利用3σ原则去除异常值得到最终结果。实验结果表明,在角度搜索域为[-45°,+45°],缩放搜索域为[0.5,1.5]的条件下,本文方法能够得到较准确的旋转、缩放、平移参量及拼接效果。

关键词: 图像拼接, FAST特征点, 特征点匹配, 结构相似性

Abstract: Aiming at the poor results that many image mosaic methods based on the feature points are used to parts image with weak texture, few features and many similar regions, an improved method is proposed. Firstly, the feature points are extracted by the FAST method, and the candidate points sets for matching are generated from them. Secondly, the gray feature values are sampled by template region, and the points matching results are obtained via setting the rotation angle and scaling search regions with the structural similarity index measurement (SSIM) method. Finally, the rotation, scaling, translation parameters are worked out by the points matching results. The last results of the parameters are gained through 3σ principle removing abnormal values. The experiment results show that the new method could get good rotation, scaling, translation parameters and mosaic image when angle search region is[-45°,+45°] and scaling search region is[0.5,1.5].

Key words:  image mosaic, FAST feature points, feature points matching, structural similarity index measurement (SSIM)

中图分类号: