上海交通大学学报(自然版) ›› 2013, Vol. 47 ›› Issue (08): 1222-1226.

• 自动化技术、计算机技术 • 上一篇    下一篇

基于模型分析的指纹奇异点检测

王晓端1,刘书炘2,刘满华1   

  1.   (1.上海交通大学 电子信息与电气工程学院,上海 200240;2.漳州师范学院 教育科学与技术系,福建 漳州 363000)
     
  • 收稿日期:2012-11-21 出版日期:2013-08-29 发布日期:2013-08-29
  • 基金资助:

    教育部博士点基金资助项目(20090073120019),国家自然科学基金资助项目(61005024)

Fingerprint Singular-point Detection Based on Mathematical Model Analysis

WANG Xiaoduan1,LIU Shuxin2,LIU Manhua1
  

  1. (1. School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai 200240, China; 2. Department of Education Science and Technology, Zhangzhou Normal University, Zhangzhou 363000, Fujian, China)
  • Received:2012-11-21 Online:2013-08-29 Published:2013-08-29

摘要:

针对传统的奇异点检测方法主要基于方向场变化且容易受噪声影响,提出了一种新的基于模型分析的指纹奇异点检测方法.首先用基于离散余弦变换基函数对方向场进行建模,在计算方向场的基础上,利用常微分方程系统线性化数学模型,通过对模型参数和平衡点进行分析,检测指纹奇异点位置.实验结果表明,基于常微分方程线性化模型分析的指纹奇异点检测方法比传统的Poincare Index方法对噪声更具有较好的鲁棒性,能进一步提高奇异点检测的准确度.
 

 

关键词: 指纹, 指纹奇异点, 方向场, 离散余弦变换, 常微分方程

Abstract:

As traditional singular point detection methods are mainly based on the orientation changes which are often affected by noise, a novel method was proposed for fingerprint singular-point detection based on mathematical model analysis in this paper. First, discrete cosine transform (DCT) was used as the basis functions to build the orientation reconstruction model and compute the orientation field. Then, the ordinary differential equation and system linearization model were computed with fingerprint orientation field and the singular points detected based on the model analysis. Experimental results show that the proposed singular point detection method has high robustness to noise and can achieve a higher accuracy compared to the traditional Poincare Index method.
Key words:

Key words: fingerprint, fingerprint singular points, orientation field, discrete cosine transform(DCT), ordinary differential equation

中图分类号: