指紋辨識(Fingerprint recognition)是近期最為廣泛運用的生物辨識技術，且由於固態式指紋感測器的出現，片段指紋(Partial fingerprint)的有限資訊為傳統匹配演算法帶來新的挑戰。隨著可得到的細節特徵減少，基於細節特徵之匹配演算法的正確率顯著地降低。
本論文專注在基於細節(Minutiae)特徵的片段指紋匹配方法之研發。由於從相同手指經過不同次按壓之指紋所萃取出的細節特徵會有偏差之問題，為了改善對齊的偏差，本論文提出先利用初始的匹配結果來萃取新的幾何轉換關係，並且參考匹配點數的變化，作為適應性對齊的依據，透過對齊誤差的改善，有機會進一步增加匹配點數。此外，由於假的指紋匹配點數較少，匹配在指紋邊緣的結果有可能導致錯誤的匹配。為了獲得高可靠的匹配結果，傳統的做法是參考最高匹配點數之結果，基於最高的匹配點數，本論文提出加入覆蓋面積做為參考之改善方法，當在不同的對齊位置上出現相同的匹配點數時，會優先選取具有較大覆蓋面積之匹配結果。最後，本論文對於辨識效能的要求，提出情況式評分方法，針對較不可靠的情況做原始分數的調整，所提出的方法參考覆蓋面積、匹配點數和原始分數來給予不同權重，進而調整其原始分數。基於FVC2000 DB1_B資料庫之實驗結果顯示，本論文所提出之方法可達5.63%的相等錯誤率，當錯誤匹配率為零時，可達到17.39%的錯誤未辨識率，且僅有2.53%的真正樣本受到影響，在樹梅派Raspberry Pi 2環境下的運算時間僅需0.27秒。

Fingerprint recognition is the most widely used biological recognition technology recently. The advent of solid-state fingerprint sensors also poses new challenges to traditional fingerprint matching algorithms due to limited amount of information that can be extracted from given partial fingerprints. For instance, the accuracy of minutiae-based matching algorithms drop dramatically as the number of available minutiae decreases.
In this thesis, we mainly focus on the development of efficient partial fingerprint matching schemes for minutiae-based applications. Since the features of extracted minutiae from different impressions of the same finger might deviate from each other, the initial matching result is used to estimate the geometrical transformation for further alignment. That is, the proposed method takes the set of matched points as a reference to determine a more suitable point for adaptive refinement; thus the number of matched minutiae might be increased accordingly. Moreover, the number of matched minutiae is relatively small for imposter cases, some of the false matching is caused by matching near the boundary of fingerprint. To improve the reliability of the matching results, both the maximum number of matched points and the size of overlapping area are taken into account for evaluating the final score. For those cases consisting of the maximum number of matched points, the one with the largest overlapping area is considered as the most reliable result and is chosen for scoring. Finally, a conditional scoring method is also presented to refine the score according to the information such as the size of overlapping area, the number of matched points and the original score.
The proposed matching schemes has been tested on FVC2000’s DB1_B database. Experiment results show that the proposed can achieve an equal error rate of 5.63%, and ZeroFMR of 17.39% with only 2.53% degradation on the genuine samples. The execution time is about 0.27 seconds on average using the Raspberry Pi 2 platform.

[1] D. Maltoni, Handbook of fingerprint recognition. London: Springer, 2009.
[2] Lin Hong, Yifei Wan and A. Jain, "Fingerprint image enhancement: algorithm and
performance evaluation", IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 20, no. 8, pp. 777-789, 1998..
[3] A. Ravishankar Rao, A taxonomy for texture description and identification. New York:
Springer-Verlag, 1990. A. Rao, A Taxonomy for Texture Description and Identification.
New York, NY: Springer-Verlag, 1990.
[4] M. Kass and A. Witkin, "Analyzing oriented patterns", Computer Vision, Graphics,
and Image Processing, vol. 37, no. 3, pp. 362-385, 1987.
[5] L. Lam, S. Lee and C. Suen, "Thinning methodologies-a comprehensive survey", IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 9, pp. 869-
885, 1992.
[6] V. Espinosa-Duro, "Mathematical Morphology Approaches for Fingerprint
Thinning", The 36th Annual 2002 International Carnahan Conference on Security
Technology, pp. 43-45
[7] M. Ahmed and R. Ward, "A rotation invariant rule-based thinning algorithm for
character recognition", IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 24, no. 12, pp. 1672-1678, 2002.
[8] P. M. Patil, S. R. Suralkar, F. B. Sheikh. "Rotation Invariant Thinning Algorithm to
Detect Ridge Bifurcations for Fingerprint Identification", Proceedings of the ICTAI'05,
2005, pp634- 641.
[9] X. You, B. Fang, V. Y. Y. Tang, and J. Huang, “ Multiscale approach for thinning ridges
of fingerprint”, in Proc. Second Iberian Conference on Pattern Recognition and Image
Analysis, volume LNCS 3523, 2005, pp. 505–512.
[10] A. Jain, Lin Hong, S. Pankanti and R. Bolle, "An identity-authentication system using
fingerprints", Proceedings of the IEEE, vol. 85, no. 9, pp. 1365-1388, 1997.
[11] M. Garris, User's guide to NIST fingerprint image software (NFIS). Gaithersburg, MD:
U.S. Dept. of Commerce, Technology Administration, National Institute of Standards
57
and Technology, 2001.
[12] Sainath Maddala,Josef Ström Bartůněk and Mikael Nilsson, "Implementation and
Evaluation of NIST Biometric Image Software for Fingerprint Reorganization", IEEE,
2010.
[13] D. Peralta, M. Galar, I. Triguero, D. Paternain, S. García, E. Barrenechea, J. Benítez,
H. Bustince and F. Herrera, "A survey on fingerprint minutiae-based local matching
for verification and identification: Taxonomy and experimental evaluation",
Information Sciences, vol. 315, pp. 67-87, 2015.
[14] S. Huvanandana, Changick Kim and Jenq-Neng Hwang, "Reliable and fast fingerprint
identification for security applications", Proc. Int. Conf. Image Processing, vol.2, Sept.
10-13, 2000, pp. 503-506.
[15] Y. He , J. Tian , R. Qun and X. Yang, "Maximum-likelihood deformation analysis of
different-sized fingerprints", Proc. 4th Int. Conf. Audio- and Video-Based Biometric
Person Authentication, pp. 421-428, 200
[16] T. Jea and V. Govindaraju, "A minutia-based partial fingerprint recognition system",
Pattern Recognition, vol. 38, no. 10, pp. 1672-1684, 2005.
[17] A. Bazen and S. Gerez, "Fingerprint matching by thin-plate spline modelling of elastic
deformations", Pattern Recognition, vol. 36, no. 8, pp. 1859-1867, 2003.
[18] A. Jain and F. Farrokhnia, "Unsupervised texture segmentation using Gabor filters",
Pattern Recognition, vol. 24, no. 12, pp. 1167-1186, 1991.
[19] A. Jain, Lin Hong, S. Pankanti and R. Bolle, "An identity-authentication system using
fingerprints", Proceedings of the IEEE, vol. 85, no. 9, pp. 1365-1388, 1997.
[20] American National Standards Institute. American national standard for information
systems, data format for the interchange of fingerprint information, 1993. Doc#
ANSI/NIST-CSL 1-1993
[21] S. Meagher and A. Hicklin, “Extended Fingerprint Feature Set,” Proc. ANSI/NIST ITL
1-2000 Standard Update Workshop, 2005.
[22] B. Kim and D. Park, "Adaptive image normalisation based on block processing for
enhancement of fingerprint image", Electron. Lett., vol. 38, no. 14, p. 696, 2002..
58
[23] Z. Shi and V. Govindaraju. "Fingerprint image enhancement based on skin profile
approximation". In Pattern Recognition, 2006. ICPR 2006. 18th International
Conference on, volume 3, pages 714–717, 2006.
[24] Mil'shtein, S.; Pillai, A.; Shendye, A.; Liessner, C.; Baier, M.; "Fingerprint
Recognition Algorithms for Partial and Full Fingerprints", The IEEE Conference on
Technologies for Homeland Security, pp. 449-452, May 2008.
[25] H. Lee and R. Gaensslen, Advances in fingerprint technology. Boca Raton, Fla.: CRC
Press, 2001.
[26] A. Moenssens, Fingerprint techniques. Philadelphia: Chilton Book Co, 1971.
[27] S. Pankanti, S. Prabhakar and A. Jain, "On the individuality of fingerprints", IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 8, pp. 1010-
1025, 2002.
[28] J.D. Stosz and L.A. Alyea, “Automated System for Fingerprint Authentication Using
Pores and Ridge Structure,” Proc. SPIE Conf. Automatic Systems for the Identification
and Inspection of Humans, vol. 2277, pp. 210-223, 1994.
[29] D. Ashbaugh, Quantitative-qualitative friction ridge analysis. Boca Raton, Fla.: CRC
Press, 1999.
[30] J. Thornton, “Latent Fingerprints, Setting Standards in the Comparison and
Identification,” Proc. 84th Ann. Training Conf. Calif. State Division of IAI, May 2000.
[31] S. Tarar and E. Kumar, "Fingerprint Mosaicing Algorithm to Improve the Performance
of Fingerprint Matching System", Computer Science and Information Technology,
Horizon Research Publication Corporation, vol. 2, no. 3, pp. 142-151, 2014
[32] K. Choi, H. Choi, S. Lee and J. Kim, "Fingerprint Image Mosaicking by Recursive
Ridge Mapping", IEEE Trans. Syst., Man, Cybern. B, vol. 37, no. 5, pp. 1191-1203,
2007.
[33] A. Jain, Y. Chen and M. Demirkus, "Pores and Ridges: High-Resolution Fingerprint
Matching Using Level 3 Features", IEEE Transactions on Pattern Analysis and
Machine Intelligence, vol. 29, no. 1, pp. 15-27, 2007.
[34] G. Fang, S. Srihari, H. Srinivasan, and P. Phatak, “Use of Ridge Points in Partial
Fingerprint Matching,” Proc. SPIE: Biometric Technology for Human Identification
59
IV, Apr. 2007.
[35] Roli Bansal, Priti Sehgal and Punam Bedi, "Minutiae Extraction from Fingerprint
Images - a Review", Proc. International Journal of Computer Science Issues (IJSCI)
[36] A. Jain, Lin Hong and R. Bolle, "On-line fingerprint verification", IEEE Transactions
on Pattern Analysis and Machine Intelligence, vol. 19, no. 4, pp. 302-314, 1997.
[37] D. Maio, D. Maltoni, R. Cappelli, J. Wayman and A. Jain, "FVC2000: fingerprint
verification competition", IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 24, no. 3, pp. 402-412, 2002.
[38] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, and A. K. Jain, "FVC2002:
Fingerprint verification competition ", Proc. Int. Conf. Pattern Recognition (ICPR),
pp. 744-747, 2002