中国物理B ›› 2010, Vol. 19 ›› Issue (11): 110601-113101.doi: 10.1088/1674-1056/19/11/110601

• • 上一篇    下一篇

Using three-dimensional discrete spherical Fourier descriptors based on surface curvature voxels for pollen particle recognition

谢永华1, Michael OhEigeartaigh2   

  1. (1)Institute of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China; School of Science, Waterford Institute of Technology, Waterford, Ireland; (2)School of Science, Waterford Institute of Technology, Waterford, Ireland
  • 收稿日期:2010-01-20 修回日期:2010-07-05 出版日期:2010-11-15 发布日期:2010-11-15
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant No. 60472061), the Natural Science Foundation of Jiangsu Province, China (Grant No. BK20090149), and the Natural Science Foundation of Higher Education Institutions of Jiangsu Province, China (Grant No. 08KJD520019).

Using three-dimensional discrete spherical Fourier descriptors based on surface curvature voxels for pollen particle recognition

Xie Yong-Hua(谢永华)a)b)†ger and Michael OhEigeartaighb)   

  1. a Institute of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China; b School of Science, Waterford Institute of Technology, Waterford, Ireland
  • Received:2010-01-20 Revised:2010-07-05 Online:2010-11-15 Published:2010-11-15
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant No. 60472061), the Natural Science Foundation of Jiangsu Province, China (Grant No. BK20090149), and the Natural Science Foundation of Higher Education Institutions of Jiangsu Province, China (Grant No. 08KJD520019).

摘要: This paper presents a new method for extract three-dimensional (3D) discrete spherical Fourier descriptors based on surface curvature voxels for pollen particle recognition. In order to reduce the high amount of pollen information and noise disturbance, the geometric normalized curvature voxels with the principal curvedness are first extracted to represent the intrinsic pollen volumetric data. Then the curvature voxels are decomposed into radial and angular components with spherical harmonic transform in spherical coordinates. Finally the 3D discrete Fourier transform is applied to the decomposed curvature voxels to obtain the 3D spherical Fourier descriptors for pollen recognition. Experimental results show that the presented descriptors are invariant to different pollen particle geometric transformations, such as pose change and spatial rotation, and can obtain high recognition accuracy and speed simultaneously.

Abstract: This paper presents a new method for extract three-dimensional (3D) discrete spherical Fourier descriptors based on surface curvature voxels for pollen particle recognition. In order to reduce the high amount of pollen information and noise disturbance, the geometric normalized curvature voxels with the principal curvedness are first extracted to represent the intrinsic pollen volumetric data. Then the curvature voxels are decomposed into radial and angular components with spherical harmonic transform in spherical coordinates. Finally the 3D discrete Fourier transform is applied to the decomposed curvature voxels to obtain the 3D spherical Fourier descriptors for pollen recognition. Experimental results show that the presented descriptors are invariant to different pollen particle geometric transformations, such as pose change and spatial rotation, and can obtain high recognition accuracy and speed simultaneously.

Key words: curvature voxels, spherical coordinates, three-dimensional discrete Fourier descriptors, pollen particles recognition

中图分类号:  (Fourier analysis)

  • 02.30.Nw
87.85.Ng (Biological signal processing)