指紋之獨特性以及其方便採集使此一生物特徵被廣泛應用於身分識別以及保密安全上，近期可在行動裝置上看到大量應用，而辨識的準確度、執行之時間以及貯存所需的空間都會是使用者所器重之問題。以往有許多研究致力於提升指紋辨識之準確度並且降低其辨識所需之執行時間：指紋特徵點磁碟式編碼(Minutiae Disk Code(MDC))，此一編碼技術紀錄指紋特徵點(Minutia)與周圍鄰近特徵點之關係與分布情形，並使用區域與全域之比對，在完整指紋辨識上擁有良好的表現以及執行快速等優點；然而指紋特徵點(Minutia)在局部指紋辨識上會面臨資訊量不足之挑戰。汗孔暨指紋凹谷描述子(Pore-Valley Descriptor)為一針對局部指紋辨識所提出之描述子，此描述子紀錄指紋汗孔(Pore)以及周圍凹谷(Valley)之關係，能在局部指紋比對有很好的結果；然而其計算時間花費過長，而此問題也同時存在於大部分基於汗孔之方法，另一方面PVD為非定長描述子，此舉除導致PVD比對耗時過長，也讓儲存空間不便估計。
本篇論文結合指紋上汗孔(Pore)和指紋紋路凹谷(Valley)來建構成描述子進行局部指紋辨識，我們提出汗孔暨指紋紋路凹谷磁碟式編碼(Pore-Valley Disk Code (PVDC))描述子，此描述子紀錄指紋汗孔與周圍特徵資訊之間的相對關係以及分布，我們利用汗孔在指紋上的豐富數量以及指紋凹谷之偵測穩定度，將描述子的結果二值化，並改進全域比對方法，能夠有良好的效率並保持辨識能力，且可省卻儲存之空間。在高解析度指紋資料庫(HRF database)中EER能達到7.30%，且在同樣半徑下，相較於TD-Sparse wRANSAC (TDWSR) 之描述子能擁有約200倍之儲存空間壓縮率。
根據其描述子之中心的調整，也可跨不同解析度資料庫，提出的汗孔暨指紋紋路凹谷磁碟式編碼(Pore-Valley Disk Code (PVDC))描述子也改動中心特徵為指紋特徵點(Minutia)使其能夠應用到FVC2002資料庫中，且在FVC2002中能有平均98.72%之辨識率。

The uniqueness and easy collection of fingerprints make this biometric feature widely used for identity recognition and confidentiality security. Recently, a large number of applications can be seen on mobile devices, where the identification accuracy, the execution time and the storage space are all important problems which users care about. Many previous studies researched to improve the identification accuracy and to reduce the execution time. Minutiae Disk Code (MDC), which records the relationship between center minutia and neighbor minutiae. MDC use the local and global matching and can have a good performance on whole fingerprint identification and fast speed. However, using MDC in the partial fingerprints will face the lack of information. The Pore-Valley descriptor (PVD), which was proposed to focus on the partial fingerprint matching problem. The PVD method records the valley distribution around the center pore and has a good performance on matching partial fingerprints, however, the heavy computation time is a problem need to solve. The heavy computation can also discover on most previous pore-based work. Another issue is that PVD is a varying length descriptor, which not only increases the computation cost but also makes the storage difficult to estimate.
This paper combines pores and valleys information to construct the descriptor on partial fingerprint identification. We propose a Pore-Valley Disk Code (PVDC) descriptor, which records the relative relationship and distribution between center pore and neighbor valley pixels. We use the plenty number of pores in the fingerprint and the stabilize detection of the valley then binarized the results into the binary descriptor and improve the global matching method to have a great efficiency, maintain the identity ability and save the storage space. The proposed method has 160x speedup compared with the state-of-the-art pore-based Sparse Representation based Direct Pore (SRDP) method with reasonable EER in HRF DBI database. The proposed method can achieve EER 7.3% and can have an approximate 200 times of storage compression with same radius than the TD-Sparse wRANSAC (TDSWR) descriptor.
With the substitution of center features, the proposed valley-disk code structure can also cross different resolution database. Our pore-valley disk code descriptor can work on the FVC2002 database by modifying the center features from pores to minutiae. The MINU-VDC has a high distinguish ability of the 98.72% recognition rate on the FVC 2002 database.

1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Problem Description . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.3 Goal and Contribution . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.4 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2 Related Work 10
2.1 Non pore-based Matching on Partial Fingerprint . . . . . . . . . . . 11
2.2 Pore-based Matching on Partial Fingerprint . . . . . . . . . . . . . 13
3 Pore-Valley Disk Code (PVDC) Descriptor 17
3.1 Image Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . 20
3.2 Pore-Valley Disk Code (PVDC) Construction . . . . . . . . . . . . 23
3.2.1 Capture Remaining Valley Pixels . . . . . . . . . . . . . . . 24
3.2.2 Pore-valley Disk Structure . . . . . . . . . . . . . . . . . . . 26
3.2.3 Descriptor Binarization . . . . . . . . . . . . . . . . . . . . 31
4 Partial Fingerprint Matching Method 32
4.1 Local Similarity Between Two PVDCs . . . . . . . . . . . . . . . . 33
i
4.2 Geometric Consensus Examination . . . . . . . . . . . . . . . . . . 34
4.3 Retrieve Missing Correspondent Pairs . . . . . . . . . . . . . . . . . 37
4.4 Final Score Computations . . . . . . . . . . . . . . . . . . . . . . . 40
5 Performance Evaluation 42
5.1 Experimental Environment and Setting . . . . . . . . . . . . . . . . 43
5.2 Rotational Invariance Verification . . . . . . . . . . . . . . . . . . . 47
5.3 Influence of Parameters . . . . . . . . . . . . . . . . . . . . . . . . 50
5.4 Partial Fingerprint Recognition . . . . . . . . . . . . . . . . . . . . 52
5.5 Computation Time and Storage Evaluation . . . . . . . . . . . . . 55
5.6 PVDC Structure on Low Resolution Database . . . . . . . . . . . . 58
6 Conclusions and Future Work 65

[1] D. Maltoni, D. Maio, A. Jain, and S. Prabhakar, Handbook of fingerprint recognition. Springer Science & Business Media, 2009.
[2] N. Ratha and R. Bolle, Automatic fingerprint recognition systems. Springer Science & Business Media, 2007.
[3] B. inc., “A technical evaluation of fingerprint scanners,” http://www.biometrika.it/eng/wp_scfing.html, Monte Santo 21, 47100 Forli, Italy.
[4] S. Mathur, A. Vjay, J. Shah, S. Das, and A. Malla, “Methodology for partial fingerprint enrollment and authentication on mobile devices,” in Biometrics (ICB), 2016 International Conference on. IEEE, 2016, pp. 1–8.
[5] R. Cappelli, M. Ferrara, and D. Maltoni, “Minutia cylinder-code: A new representation and matching technique for fingerprint recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 12, pp. 2128–2141, 2010.
[6] D. Peralta, M. Galar, I. Triguero, O. Miguel-Hurtado, J. M. Benitez, and F. Herrera, “Minutiae filtering to improve both efficacy and efficiency of fingerprint matching algorithms,” Engineering Applications of Artificial Intelligence, vol. 32, pp. 37–53, 2014.
[7] T. T. Chu and C. T. Chiu, “A cost-effective minutiae disk code for fingerprint recognition and its implementation,” in Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, 2016, pp. 981–985.
[8] PolyU HRF Database, http://www.comp.polyu.edu.hk/biometrics/HRF/HRF.htm.
[9] Q. Zhao, D. Zhang, L. Zhang, and N. Luo, “High resolution partial fingerprint alignment using pore–valley descriptors,” Pattern Recognition, vol. 43, no. 3, pp. 1050–1061, 2010.
[10] Q. Zhao, L. Zhang, D. Zhang, and N. Luo, “Direct pore matching for fingerprint recognition,” Advances in Biometrics, pp. 597–606, 2009.
[11] F. Liu, Q. Zhao, L. Zhang, and D. Zhang, “Fingerprint pore matching based on sparse representation,” in Pattern Recognition (ICPR), 2010 20th International Conference on. IEEE, 2010, pp. 1630–1633.
[12] R. de Paula Lemes, M. P. Segundo, O. R. Bellon, and L. Silva, “Dynamic pore filtering for keypoint detection applied to newborn authentication,” in Pattern Recognition (ICPR), 2014 22nd International Conference on. IEEE, 2014, pp. 1698–1703.
[13] S. Malathi and C. Meena, “Improved partial fingerprint matching based on score level fusion using pore and sift features,” in Process Automation, Control and Computing (PACC), 2011 International Conference on. IEEE, 2011, pp.1–4.
[14] F. Liu, Q. Zhao, and D. Zhang, “A novel hierarchical fingerprint matching approach,” Pattern Recognition, vol. 44, no. 8, pp. 1604–1613, 2011.
[15] M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, vol. 24, no. 6, pp. 381–395, 1981.
[16] S. Dyre and C. Sumathi, “A SURVEY ON VARIOUS APPROACHES TO
FINGERPRINT MATCHING FOR PERSONAL VERIFICATION AND IDENTIFICATION,” Aug. 2016. [Online]. Available: https://doi.org/10.5281/zenodo.232968
[17] W. Lee, S. Cho, H. Choi, and J. Kim, “Partial fingerprint matching using minutiae and ridge shape features for small fingerprint scanners,” Expert Systems with Applications, 2017.
[18] O. Zanganeh, B. Srinivasan, and N. Bhattacharjee, “Partial fingerprint matching through region-based similarity,” in Digital lmage Computing: Techniques and Applications (DlCTA), 2014 International Conference on. IEEE, 2014, pp. 1–8.
[19] L. Nanni and A. Lumini, “Descriptors for image-based fingerprint matchers,” Expert Systems with Applications, vol. 36, no. 10, pp. 12 414–12 422, 2009.
[20] L. Nanni and A. Lumini, “Local binary patterns for a hybrid fingerprint matcher,” Pattern recognition, vol. 41, no. 11, pp.3461–3466, 2008.
[21] C. M. Brislawn, J. N. Bradley, R. J. Onyshczak, and T. Hopper, “The fbi compression standard for digitized fingerprint images,” Los Alamos National Lab., NM (United States), Tech. Rep., 1996.
[22] A. K. Jain, L. Hong, S. Pankanti, and R. Bolle, “An identity-authentication system using fingerprints,” Proceedings of the IEEE, vol. 85, no. 9, pp. 1365–1388, 1997.
[23] L. Shen and A. Kot, “A new wavelet domain feature for fingerprint recognition (< special issue> biometrics and its applications),” Biomedical fuzzy and human sciences: the official journal of the Biomedical Fuzzy Systems Association, vol. 14, no. 1, pp. 55–59, 2009.
[24] J. C. Amengual, A. Juan, J. C. Perez, F. Prat, S. Saez, and J. M. Vilar, “Realtime minutiae extraction in fingerprint images,” in 1997 Sixth International Conference on Image Processing and Its Applications, vol. 2, Jul 1997, pp.871–875 vol.2.
[25] Q. Zhao, L. Zhang, D. Zhang, N. Luo, and J. Bao, “Adaptive pore model for fingerprint pore extraction,” in Pattern Recognition, 2008. ICPR 2008. 19th International Conference on. IEEE, 2008, pp. 1–4.
[26] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma, “Robust face recognition via sparse representation,” IEEE transactions on pattern analysis and machine intelligence, vol. 31, no. 2, pp. 210–227, 2009.
[27] D. Zhang, W. Wang, Q. Huang, S. Jiang, and W. Gao, “Matching images more efficiently with local descriptors,” in Pattern Recognition, 2008. ICPR 2008. 19th International Conference on. IEEE, 2008, pp. 1–4.
[28] P. Simard, Y. LeCun, and J. S. Denker, “Efficient pattern recognition using a new transformation distance,” in Advances in neural information processing systems, 1993, pp. 50–58.
[29] M. Pamplona Segundo and R. de Paula Lemes, “Pore-based ridge reconstruction for fingerprint recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2015, pp. 128–133.
[30] R. de Paula Lemes, M. P. Segundo, O. R. Bellon, and L. Silva, “Dynamic pore filtering for keypoint detection applied to newborn authentication,” in Pattern Recognition (ICPR), 2014 22nd International Conference on. IEEE, 2014, pp. 1698–1703.
[31] J. B. Kruskal, “On the shortest spanning subtree of a graph and the traveling salesman problem,” Proceedings of the American Mathematical society, vol. 7, no. 1, pp. 48–50, 1956.
[32] S. Malathi and C. Meena, “An efficient method for partial fingerprint recognition based on local binary pattern,” in Communication Control and Computing Technologies (ICCCCT), 2010 IEEE International Conference on. IEEE, 2010, pp. 569–572.
[33] T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on pattern analysis and machine intelligence, vol. 24, no. 7, pp.971–987, 2002.
[34] R. Thai, “Fingerprint image enhancement and minutiae extraction,” The University of Western Australia, Tech. Rep., 2003.
[35] Q. Zhao, D. Zhang, L. Zhang, and N. Luo, “Adaptive fingerprint pore modeling and extraction,” Pattern Recognition, vol. 43, no. 8, pp. 2833–2844, 2010.
[36] T. Y. Jea and V. Govindaraju, “A minutia-based partial fingerprint recognition system,” Pattern Recognition, vol. 38, no. 10, pp. 1672–1684, 2005.
[37] A. M. Bazen and S. H. Gerez, “Fingerprint matching by thin-plate spline modelling of elastic deformations,” Pattern Recognition, vol. 36, no. 8, pp.1859–1867, 2003.
[38] Fingerprint Verification Competition (FVC2002), http://bias.csr.unibo.it/fvc2002/databases.asp.
[39] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, and A. K. Jain, “Fvc2002: Second fingerprint verification competition,” in Pattern recognition, 2002. Proceedings. 16th international conference on, vol. 3. IEEE, 2002, pp. 811–814.
[40] A. K. 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.
[41] V. K. Alilou, Fingerprint matching: A simple approach, [Online]. Available: https://www.mathworks.com/matlabcentral/fileexchange/44369-fingerprint-matching--a-simple-approach.