English

应用科学学报 ›› 2013, Vol. 31 ›› Issue (5): 495-502.doi: 10.3969/j.issn.0255-8297.2013.05.009

• 信号与信息处理 • 上一篇    下一篇

正交Fourier-Mellin 矩模糊不变量的构造及应用

戴修斌1， 刘天亮2， 舒华忠3， 罗立民3   

  1. 1. 南京邮电大学地理与生物信息学院，南京210046
    2. 南京邮电大学通信与信息工程学院，南京210003
    3. 东南大学计算机科学与工程学院，南京210096
  • 收稿日期:2012-07-24 修回日期:2013-03-12 出版日期:2013-09-26 发布日期:2013-03-12
  • 作者简介:戴修斌，副研究员，研究方向：图像处理和模式识别等，E-mail: daixb@njupt.edu.cn；舒华忠，教授，博导，研究方向：医学图像处理和模式识别等，E-mail: shu.list@seu.edu.cn；罗立民，教授，博导，研究方向：计算机辅助诊断和治疗以及科学可视化等，E-mail: luo.list@seu.edu.cn
  • 基金资助:

    国家自然科学基金(No. 31200747)；江苏省自然科学基金(No. BK2012437)；南京邮电大学引进人才科研启动基金(No.
    NY211030)资助

Construction and Application of Blur Invariants Based on Orthogonal Fourier-Mellin Moment

DAI Xiu-bin1, LIU Tian-liang2, SHU Hua-zhong3, LUO Li-min3   

  1. 1. College of Geographic and Biologic Information, Nanjing University of Post
    and Telecommunications, Nanjing 210046, China
    2. College of Telecommunications and Information Engineering, Nanjing University of Post
    and Telecommunications, Nanjing 210003, China
    3. School of Computer Science and Engineering, Southeast University,
    Nanjing 210096, China
  • Received:2012-07-24 Revised:2013-03-12 Online:2013-09-26 Published:2013-03-12

PDF

1129

摘要： 为了有效识别含有模糊形变的图像或特征，构造了正交Fourier-Mellin 矩模糊不变量. 通过获得形变图像和理想图像正交Fourier-Mellin矩之间的关系，推导出基于正交Fourier-Mellin矩函数的模糊不变量，然后利用该模糊不变量识别形变图像. 实验表明，在不同模糊形变和不同强度噪声作用下，正交Fourier-Mellin 矩模糊不变
量的不变性均优于其他不变量，且对模糊形变图像的正确识别率更高.

关键词: 模糊图像识别, 模糊不变量, 正交Fourier-Mellin 矩

Abstract: We propose a new set of blur invariants based on orthogonal Fourier-Mellin moments to effectively recognize blurred images. We establish the relationship between orthogonal Fourier-Mellin moments of the original and distorted images. We then use this relationship to construct blur invariants of orthogonal
Fourier-Mellin moment. The new blur invariants are used as feature descriptors to recognize blurred images. Experimental results show that，with different kind of blur degradation and different densities of noises introduced into the images，better invariance and higher recognition rates can be obtained by using the proposed invariants as compared to other blur invariants.

Key words: recognition of blurred image, blur invariant, orthogonal Fourier-Mellin moment

中图分类号: