Abstract In an automatic fingerprint identification system, estimating the quality of fingerprint image has significant value for segmentation, enhancement and matching processes. Besides, the quality classification of fingerprint image is of paramount significance in the applicability research of fingerprint recognition algorithm. In this paper, a method for quality classification of fingerprint image is proposed based on the support vector machine (SVM). The gradient, Gabor feature, and directional contrast are used as the quality index, and SVM is applied to achieve quality classification of fingerprint image. Meanwhile, synthetic minority over sampling technique (SMOTE) method is employed to reduce the influence of class imbalance problem. Both the theoretical analysis and the experimental results indicate the validity of the proposed method.
[1] Galton F. Finger Prints. New York, USA: Da Capo Press, 1961 [2] Lee H C, Gaensslen R E. Advances in Fingerprint Technology. New York, USA: Elsevier, 1991 [3] Yun E K, Cho S B. Adaptive Fingerprint Image Enhancement with Fingerprint Image Quality Analysis. International Vacuum Congress, 2006, 24(1): 101-110 [4] Julian F A, Chen Yi, Javier O G, et al. Incorporating Image Quality in Multi-Algorithm Fingerprint Verification // Proc of the International Conference on Biometrics. Hongkong, China, 2006: 213-220 [5] Chen Yi, Dass S C, Jain A K. Fingerprint Quality Indices for Predicting Authentication Performance // Proc of the 5th International Conference on Audio-and Video-Based Biometric Person Authentication. Hilton Rye Town, UK, 2005: 160-170 [6] Jain A K, Prabhakar S, Hong Lin, et al. Filterbank-Based Fingerprint Matching. IEEE Trans on Image Processing, 2000, 9(5): 846-859 [7] Marana A N, Jain A K. Ridge-Based Fingerprint Matching Using Hough Transform // Proc of the XVIII Brazilian Symposium on Computer Graphics and Image Processing. Natal, Brazil, 2005: 112-119 [8] Jain A K, Prabhakar S, Hong Lin. A Multichannel Approach to Fingerprint Classification. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999, 21(4): 348-359 [9] Hong Lin, Wan Yifei, Jain A. Fingerprint Image Enhancement: Algorithms and Performance Evaluation. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(8): 777-789 [10] Shen Linlin, Kot A, Koo W M. Quality Measures of Fingerprint Images // Proc of the 3rd International Conference on Audio-and Video-Based Biometric Person Authentication. Halmstad, Sweden, 2001: 266-271 [11] Ballan M, Sakarya F A, Evans B L. A Fingerprint Classification Technique Using Directional Images // Proc of the 31st Asilomar Conference on Signals, Systems & Computers. Pacific Grove, USA, 1997, Ⅰ: 101-104 [12] Jiang W C. An Adaptive Feature Extraction Algorithm for Automatic Fingerprint Recognition. Master Dissertation. Seoul, Korea: Yonsei University. School of Electrical and Electronic Engineering, 2002 [13] Ratha N, Bolle R. Fingerprint Image Quality Estimation. IBM Computer Science Research, Report RC21622, Yorktown Heights, USA: IBM T.J.Watson Research Center, 1999 [14] Qi Jinqing, Abdurrachim D, Li Dongju, et al. A Hybrid Method for Fingerprint Image Quality Calculation // Proc of the 4th IEEE Workshop on Automatic Identification Advanced Technologies. Buffalo, USA, 2005: 124-129 [15] Lee B, Moon J, Kim H. A Novel Measure of Fingerprint Image Quality Using Fourier Spectrum // Proc of the Conference on Biometric Technology for Human Identification. Orlando, USA, 2005: 105-112 [16] Boser B E, Guyon I M, Vapnik V N. A Training Algorithm for Optimal Margin Classifiers // Proc of the 5th Annual Workshop on Computational Learning Theory. Pittsburgh, USA, 1992: 144-152 [17] Cortes C, Vapnik V N. Support Vector Networks. Machine Learning, 1995, 20(3): 273-297 [18] Schlkopf B, Burges C, Vapnik V N. Extracting Support Data for a Given Task // Proc of the 1st International Conference on Knowledge Discovery & Data Mining. Québec, Canada, 1995: 262-267 [19] Vapnik V N. The Nature of Statistical Learning Theory. New York, USA: Springer Verlag, 1995 [20] Chawla N V, Bowyer K W, Hall L O, et al. SMOT: Synthetic Minority Oversampling Technique. Journal of Artificial Intelligence Research, 2002, 16: 321-257 [21] Zhou Zhihua, Liu Xuying. Training Cost-Sensitive Neural Networks with Methods Addressing the Class Imbalance Problem. IEEE Trans on Knowledge and Data Engineering, 2006, 18(1): 63-77 [22] Chawla N V, Hall L O, Bowyer K W, et al. SMOTE: Synthetic Minority Oversampling Technique. Journal of Artificial Intelligence Research, 2006, 16: 321-357 [23] Chen Xu, Yin Yilong, Wang Yanrong, et al. A Method Based on Spectral Analysis with Big Window for Fingerprint Ridge Distance Estimation. Journal of Fudan University: Natural Science, 2004, 43(5): 889-892,898 (in Chinese) (陈 旭,尹义龙,王彦荣,等.基于大窗口频谱分析的指纹纹线距离的估计方法.复旦大学学报:自然科学版, 2004, 43(5): 889-892,898) [24] Chih-Chung C, Chih-Jen L. LIBSVM: A Library for Support Vector Machines [DB/OL]. [2001-08-03]. http://www.csie.ntu.edu.tw/~cjlin/libsvm [25] Crone S F, Lessmann S, Stahlbock R. Empirical Comparison and Evaluation of Classifier Performance for Data Mining in Customer Relationship Management // Proc of the IEEE International Joint Conference on Neural Networks. Budapest, Hungary, 2004: 442-448
2009, Vol. 22 
