中国物理B ›› 2003, Vol. 12 ›› Issue (6): 610-614.doi: 10.1088/1009-1963/12/6/307

• • 上一篇    下一篇

Cell image recognition with radial harmonic Fourier moments

任海萍1, 陈盛祖1, 吴文凯1, 平子良2, 盛云龙3, 博午日亘4   

  1. (1)Department of Nuclear Medicine, Cancer Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing 100021, China; (2)Department of Physics, Inner Mongolia Normal University, Huhhot 010022, China; (3)Department of Physics, Laval University, Quebec, GIK 7P4, Canada; (4)Mathematics Institute, Peking University, Beijing 100871, China
  • 收稿日期:2002-11-18 修回日期:2003-02-18 出版日期:2003-06-16 发布日期:2005-03-16
  • 基金资助:
    Project supported by the National Natural Science Foundation (Grant No 60262001) and by the Inner Mongolia Natural Science Foundation, China (Grant No 201301).

Cell image recognition with radial harmonic Fourier moments

Ren Hai-Ping (任海萍)a, Ping Zi-Liang (平子良)b, Bo Wu-Ri-Gen (博午日亘)c, Sheng Yun-Long (盛云龙)d, Chen Sheng-Zu (陈盛祖)a, Wu Wen-Kai (吴文凯)a   

  1. a Department of Nuclear Medicine, Cancer Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing 100021, China; b Department of Physics, Inner Mongolia Normal University, Huhhot 010022, China; c Mathematics Institute, Peking University, Beijing 100871, China; d Department of Physics, Laval University, Quebec, GIK 7P4, Canada
  • Received:2002-11-18 Revised:2003-02-18 Online:2003-06-16 Published:2005-03-16
  • Supported by:
    Project supported by the National Natural Science Foundation (Grant No 60262001) and by the Inner Mongolia Natural Science Foundation, China (Grant No 201301).

摘要: Various types of moments have been utilized to recognize image patterns in a number of applications. Multi-distortion invariant-radial harmonic Fourier moments were investigated in the recognition of cell smear images. Image recognition experiments showed that radial harmonic Fourier moments are not only highly concentrated image features but also have a good property of antidistortion and antinoise. They may be used in fast and accurate automatic cell recognition.

Abstract: Various types of moments have been utilized to recognize image patterns in a number of applications. Multi-distortion invariant-radial harmonic Fourier moments were investigated in the recognition of cell smear images. Image recognition experiments showed that radial harmonic Fourier moments are not only highly concentrated image features but also have a good property of antidistortion and antinoise. They may be used in fast and accurate automatic cell recognition.

Key words: cell recognition, moment invariant

中图分类号:  (Fourier optics)

  • 42.30.Kq
42.30.Sy (Pattern recognition) 87.17.-d (Cell processes)