中国物理B ›› 2014, Vol. 23 ›› Issue (6): 60701-060701.doi: 10.1088/1674-1056/23/6/060701

• GENERAL • 上一篇    下一篇

Spatial geometric constraints histogram descriptors based on curvature mesh graph for 3D pollen particles recognition

谢永华a, 徐赵飞a, Hans Burkhardtb   

  1. a School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China;
    b Department of Computer Science, Freiburg University, Freiburg 79100, Germany
  • 收稿日期:2013-08-21 修回日期:2013-11-25 出版日期:2014-06-15 发布日期:2014-06-15
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant No. 61375030), 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).

Spatial geometric constraints histogram descriptors based on curvature mesh graph for 3D pollen particles recognition

Xie Yong-Hua (谢永华)a, Xu Zhao-Fei (徐赵飞)a, Hans Burkhardtb   

  1. a School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China;
    b Department of Computer Science, Freiburg University, Freiburg 79100, Germany
  • Received:2013-08-21 Revised:2013-11-25 Online:2014-06-15 Published:2014-06-15
  • Contact: Xie Yong-Hua E-mail:yonghua@nuist.edu.cn
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant No. 61375030), 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 one novel spatial geometric constraints histogram descriptors (SGCHD) based on curvature mesh graph for automatic three-dimensional (3D) pollen particles recognition. In order to reduce high dimensionality and noise disturbance arising from the abnormal record approach under microscopy, the separated surface curvature voxels are extracted as primitive features to represent the original 3D pollen particles, which can also greatly reduce the computation time for later feature extraction process. Due to the good invariance to pollen rotation and scaling transformation, the spatial geometric constraints vectors are calculated to describe the spatial position correlations of the curvature voxels on the 3D curvature mesh graph. For exact similarity evaluation purpose, the bidirectional histogram algorithm is applied to the spatial geometric constraints vectors to obtain the statistical histogram descriptors with fixed dimensionality, which is invariant to the number and the starting position of the curvature voxels. Our experimental results compared with the traditional methods validate the argument that the presented descriptors are invariant to different pollen particles geometric transformations (such as posing change and spatial rotation), and high recognition precision and speed can be obtained simultaneously.

关键词: pollen recognition, curvature mesh graph, spatial geometric constraints, bidirectional histogram

Abstract: This paper presents one novel spatial geometric constraints histogram descriptors (SGCHD) based on curvature mesh graph for automatic three-dimensional (3D) pollen particles recognition. In order to reduce high dimensionality and noise disturbance arising from the abnormal record approach under microscopy, the separated surface curvature voxels are extracted as primitive features to represent the original 3D pollen particles, which can also greatly reduce the computation time for later feature extraction process. Due to the good invariance to pollen rotation and scaling transformation, the spatial geometric constraints vectors are calculated to describe the spatial position correlations of the curvature voxels on the 3D curvature mesh graph. For exact similarity evaluation purpose, the bidirectional histogram algorithm is applied to the spatial geometric constraints vectors to obtain the statistical histogram descriptors with fixed dimensionality, which is invariant to the number and the starting position of the curvature voxels. Our experimental results compared with the traditional methods validate the argument that the presented descriptors are invariant to different pollen particles geometric transformations (such as posing change and spatial rotation), and high recognition precision and speed can be obtained simultaneously.

Key words: pollen recognition, curvature mesh graph, spatial geometric constraints, bidirectional histogram

中图分类号:  (Computer modeling and simulation)

  • 07.05.Tp
42.30.Wb (Image reconstruction; tomography)