Fingerprint is known as the first material evidence in the field of criminal investigation and forensic science, and plays a very important role in combating crime and maintaining social stability. The conclusion of fingerprint identification is the key to the formation of effective evidence and the detection of criminal cases, and the quality of fingerprint image directly affects the accuracy and reliability of fingerprint identification conclusions, so accurate and objective fingerprint image quality evaluation algorithm is an indispensable tool to assist fingerprint experts in fingerprint identification. At present, the NFIQ2.0 fingerprint image quality evaluation algorithm developed by the National Institute of Standards and Technology (NIST) has attracted extensive attention from experts and scholars at home and abroad. However, the quality evaluation results of this algorithm deviate greatly from the quality evaluation results of fingerprint experts, and lack of quality evaluation for local areas of fingerprint images. Therefore, it can not meet the needs of criminal investigation and forensic science fingerprint identification tasks. In this paper, the problem of fingerprint image quality evaluation is extended to the quality space, and the quality evaluation algorithm based on expert perception is proposed by learning the quality perception strategy of fingerprint experts for the local area of ridges. The experimental results show that the overall quality evaluation results of the proposed algorithm are consistent with the quality evaluation results of fingerprint experts, and accord with the application scenarios of criminal investigation and forensic science. In addition, this paper further compared with the NFIQ2.0 algorithm on several international public fingerprint data sets, and the results show that the quality evaluation score of the proposed algorithm is more reasonable, and can effectively reduce false non-match rate (FNMR) of the fingerprint matching algorithm.
[1] Maltoni D, Maio D, Jain A K, et al. Handbook of fingerprint recognition[M]. London:Springer London, 2009. DOI:10.1007/978-1-84882-254-2.
[2] Jain A K, Ross A, Prabhakar S. An introduction to biometric recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(1):4-20. DOI:10.1109/TCSVT.2003.818349.
[3] Bolle R M, Pankanti S U, Yao Y S. System and method for determining the quality of fingerprint images:US5963656[P]. 1999-10-05.
[4] Shen L L, Kot A, Koo W M. Quality measures of fingerprint images[C]//International Conference on Audio-and Video-Based Biometric Person Authentication. Springer, Berlin, Heidelberg, 2001:266-271. DOI:10.1007/3-540-45344-X_39.
[5] Tabassi E, Wilson C L, Watson C I. Fingerprint image quality[R]. National Institute of Standards and Technology, 2004. DOI:10.6028/nist.ir.7151.
[6] ANSI. ISO/IEC 29794-1:2009:Information technology-Biometric sample quality-Part 1:Framework[EB/OL].(2009-08)[2022-01-22]. https://www.iso.org/standard/43583.html.
[7] ANSI. ISO/IEC TR 29794-4:2010:Information technology-Biometric sample quality-Part 4:Finger image data[EB/OL]. (2010-04)[2022-01-22]. https://www.iso.org/standard/50911.html.
[8] ANSI. ISO/IEC 29794-4:2017:Information technology-Biometric sample quality-Part 4:Finger image data[EB/OL]. (2017-09)[2022-01-22]. https://www.iso.org/standard/62791.html.
[9] NIST. Development of NFIQ 2.0[EB/OL]. (2014-04)[2022-01-22]. http://www.nist.gov/itl/iad/ig/development_nfiq_2.cfm.
[10] Li X, Wang R X, Li M Q, et al. A hybrid quality estimation algorithm for fingerprint images[C]//Biometric Recognition, 2016:214-223. DOI:10.1007/978-3-319-46654-5_24.
[11] Richter R, Gottschlich C, Mentch L, et al. Smudge noise for quality estimation of fingerprints and its validation[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(8):1963-1974. DOI:10.1109/TIFS.2018.2889258.
[12] Chen C H, An C S, Chen C Y. Fingerprint quality assessment based on texture and geometric features[J]. Journal of Imaging Science and Technology, 2020, 64(4):40403-1-40403-7. DOI:10.2352/j.imagingsci.technol.2020.64.4.040403.
[13] Agarwal D, Bansal A. Assessment of latent fingerprint image quality based on level 1, level 2, and texture features[C]//International Conference on Innovative Computing and Communications, 2021:489-501. DOI:10.1007/978-981-15-5113-0_38.
[14] Hendre M, Patil S, Abhyankar A. Utility of quality metrics in partial fingerprint recognition[J]. International Journal of Computing and Digital Systems, 2021, 10(1):839-849. DOI:10.12785/ijcds/100177.
[15] 中华人民共和国公安部. 指纹特征规范第5部分:指纹细节特征点标志方法:GA 774.5-2008[S]. 北京:中国标准出版社, 2008.
[16] 中华人民共和国公安部. 十指指纹图像数据复现动态链接库接口:GA 785-2008[S]. 北京:中国标准出版社, 2008.
[17] 中华人民共和国公安部. 居民身份证指纹采集和比对技术规范:GA/T 1012-2019[S]. 北京:中国标准出版社, 2012.
[18] 江璐, 赵彤, 吴敏. 基于深度卷积神经网络的指纹纹型分类算法[J]. 中国科学院大学学报, 2016, 33(6):808-814. DOI:10.7523/j.issn.2095-6134.2016.06.013.
[19] Qin J, Han C Y, Bai C C, et al. Multi-scaling detection of singular points basedon fully convolutional networks in fingerprint images[C]//Biometric Recognition, 2017:221-230. DOI:10.1007/978-3-319-69923-3_24.
[20] Li J, Feng J J, Kuo C C J. Deep convolutional neural network for latent fingerprint enhancement[J]. Signal Processing:Image Communication, 2018, 60:52-63. DOI:10.1016/j.image.2017.08.010.
[21] Liu Y H, Zhou B C, Han C Y, et al. A method for singular points detection based on faster-RCNN[J]. Applied Sciences, 2018, 8(10):1853. DOI:10.3390/app8101853.
[22] Zhou B C, Han C Y, Liu Y H, et al. Fast minutiae extractor using neural network[J]. Pattern Recognition, 2020, 103:107273. DOI:10.1016/j.patcog.2020.107273.
[23] Liu Y H, Zhou B C, Han C Y, et al. A novel method based on deep learning for aligned fingerprints matching[J]. Applied Intelligence, 2020, 50(2):397-416. DOI:10.1007/s10489-019-01530-4.
[24] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:770-778. DOI:10.1109/CVPR.2016.90.
[25] Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017:2261-2269. DOI:10.1109/CVPR.2017.243.
[26] Kingma D P, Ba J. Adam:a method for stochastic optimization[EB/OL]. arXiv:1412.6980v9[cs.LG]. (2017-01-30)[2022-01-22]. https://arxiv.org/abs/1412.6980.
[27] Gonzalez R C, Woods R E. Digital image processing[M]. 2nd ed. New Jersey:Prentice Hall, 2002.
[28] Kass M, Witkin A. Analyzing oriented patterns[J]. Computer Vision, Graphics, and Image Processing, 1987, 37(3):362-385. DOI:10.1016/0734-189X(87)90043-0.
[29] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1):62-66. DOI:10.1109/tsmc.1979.4310076.
[30] Suzuki S, be K. Topological structural analysis of digitized binary images by border following[J]. Computer Vision, Graphics, and Image Processing, 1985, 30(1):32-46. DOI:10.1016/0734-189X(85)90016-7.
[31] Maio D, Maltoni D, Cappelli R, et al. FVC2000:fingerprint verification competition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(3):402-412. DOI:10.1109/34.990140.
[32] Maio D, Maltoni D, Cappelli R, et al. FVC2002:second fingerprint verification competition[C]//2002 International Conference on Pattern Recognition. August 11-15, 2002, Quebec City, QC, Canada. IEEE, 2002:811-814. DOI:10.1109/ICPR.2002.1048144.
[33] Watson C I, Garris M D, Tabassi E, et al. User's guide to NIST biometric image software (NBIS)[R]. National Institute of Standards and Technology, 2007. DOI:10.6028/nist.ir.7392.
[34] Watson C I, Wilson C L. NIST special database 4:fingerprint database[R/OL]. National Institute of Standards and Technology (1992-03-17)[2022-01-22]. http://www.informatik.uni-ulm.de/ni/Lehre/SS03/ENIPRAKT/nist_sd4.pdf.
