计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 149-151.doi: 10.11896/j.issn.1002-137X.2016.6A.035

• 模式识别与图像处理 • 上一篇    下一篇

基于直线曲线混合Gabor滤波器的指纹增强算法

梅园,赵波,朱之丹   

  1. 南京信息工程大学江苏省网络监控中心 南京210044江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学计算机与软件学院 南京210044,南京信息工程大学江苏省网络监控中心 南京210044江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学计算机与软件学院 南京210044,南京信息工程大学江苏省网络监控中心 南京210044江苏省大气环境与装备技术协同创新中心 南京210044南京信息工程大学计算机与软件学院 南京210044
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家科学自然基金(61206138),中国博士后基金(20110491413),南京信息工程大学“优秀本科毕业论文(设计)支持计划”重点项目资助

Fingerprint Enhancement Based on Straight-curved Line Gabor Filter

MEI Yuan, ZHAO Bo and ZHU Zhi-dan   

  • Online:2018-12-01 Published:2018-12-01

摘要: 指纹图像增强对提高自动指纹识别系统的准确性具有重要意义。针对直线Gabor滤波器在纹线弯曲程度高的区域增强效果较差和曲线Gabor滤波器增强计算复杂度较高的问题,提出了一种基于直线曲线混合Gabor滤波器的指纹增强算法。其主要过程为:基于方向场一致性特征将指纹图像划分为弯曲区域和平缓区域;对弯曲区域和平缓区域,分别采用曲线Gabor滤波器和直线Gabor滤波器进行增强。在FVC2002上的实验结果表明,该方法在取得与曲线Gabor滤波器近似增强效果的同时,增强速度提高至其1.404倍。

关键词: 指纹识别,指纹图像增强,Gabor滤波器,弯曲区域

Abstract: Fingerprint enhancement has a great significance on improvement of the accuracy of automatic fingerprint identification System(AFIS).To balance the weakness of straight-line Gabor filter in extremely curved region and the high computation complexity of curved line Gabor filter,a novel straight-curved line Gabor filter was proposed in this paper.First,orientation coherence was utilized to divide the fingerprint into curved and smooth regions.Then implemented curved-line filtering and straight-line filtering on curved and smooth regions respectively.Experiments on FVC2002 show that the proposed method achieves comparable enhancement effect and 1.404 times faster calculating speed,compared with curved-line Gabor.

Key words: Fingerprint identification,Fingerprint enhancement,Gabor filter,Curved region

[1] Peralta,Daniel,et al.Fast fingerprint identification for large databases[J].Pattern Recognition,2014,47(2):588-602
[2] Chen Fang-lin,Huang Xiao-lin,Zhou Jie.Hierarchical minutiae matching for fingerprint and palmprint identification[J].IEEE Transactions on Image Processing,2013,22(12):4964-4971
[3] Cappelli,Raffaele,Ferrara M,et al.Large-scale fingerprint identification on GPU[J].Information Sciences,2015,6:1-20
[4] O’Gorman L,Nickerson J V.An approach to fingerprint filter design[J].Pattern Recognition,1989,22(1):29-38
[5] Hong L,Wan Y,Jain AK.Fingerprint image enhancement:algorithm and performance evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,0(8):777-789
[6] 朱立新.基于偏微分方程的图像去噪和增强研究 [D].南京:南京理工大学,2007
[7] Sherlock B G,Monro D M,Millard K.Fingerprint enhancement by directional Fourier filtering[J].Vision,Image and Signal Processing,1994,141(2):87-94
[8] Chikkerur S,Cartwright A N,Govindaraju V.Fingerprint enhancement using STFT analysis[J].Pattern Recognition,2007,40(1):198-211
[9] Hsieh C T,Lai E,Wang Y C.An effective algorithm for fingerprint image enhancement based on wavelet transform[J].Pattern Recognition,2003,36(2):303-312
[10] Jirachaweng S,Areekul V.Fingerprint enhancement based on discrete cosine transform[M]//Advances in Biometrics.Sprin-ger Berlin Heidelberg,2007:96-105
[11] Hong L,Jain A K,Pankanti S,et al.Fingerprint enhancement[C]∥Proc.1st IEEE WACV.Sarasota,FL,1996:202-207
[12] Areekul V,Watchareeruetai U,Suppasriwasuseth K,et al.Separable Gabor filter realization for fast fingerprint enhancement[C]∥IEEE International Conference on Image Processing,2005(ICIP 2005).IEEE,2005,3:III-253-6
[13] 祝恩.低质量指纹图像的特征提取与识别技术的研究[D].长沙:国防科学技术大学,2005
[14] Gottschlich C.Curved-region-based ridge frequency estimationand curved Gabor filters for fingerprint image enhancement[J].IEEE Transactions on Image Processing,2012,21(4):2220-2227
[15] Mei Y,Zhao B,Zhou Y,et al.Orthogonal curved-line Gabor filter for fast fingerprint enhancement[J].Electronics Letters,2014,50(3):175-177
[16] 唐良瑞,谢晓辉,蔡安妮,等.基于 D-S 证据理论的指纹图像分割方法[J].计算机学报,2003,26(7):887-892

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!