指紋是每個人與生俱來獨一無二的特徵。在生物辨識的領域中，指紋最常被用來做辨識身分的工具。近年來，學界和業界也相繼投入指紋辨識系統，很明顯的，大多數的指紋辨識系統都需依賴電腦強大的運算能力，以達到及時處理指紋影像及辨識的功能。雖然有高準確度的辨識結果，但需要電腦做大量的計算仍是一項值得改善與突破的要點。有鑒於此，本論文發找出一套具有高辨識率且節省資源的指紋辨識演算法，此演算法可以運用於各項需要安全考量的電子系統、個人身分辨識及保全系統等等。本論文研究指紋辨識處理流程以提高效能進而改善可被硬體設計的實現度，並且提出一套新的指紋比對方法：三角比對法，此方法比以往的比對法更可以容忍位移、旋轉及變形等問題。實驗證明，此套演算法能達到高效能的指紋辨識。

A fingerprint is one of the unique features that everyone born with. In the biometrics technologies, fingerprint recognition is considered the most general one. Many experts from both academia and industries have been engaged in the research of fingerprint recognition recently. It is not difficult to find out that most of the fingerprint recognition systems provided by industries still rely significantly on calculation of PC to process real-time fingerprint images as well as recognition ability. Though it provides results with high accuracy, the fact that it takes great amount of calculation through the computers is the disadvantage that needs to be improved. This paper addressed a novel fingerprint reorganization algorithm which indeed provides high performance, which is able to function in terms of any security electronic systems, personal identification and home security system, etc. In an experiment for the progress of the possible practicability of the hardware design, we study for improving the efficiency of all the calculations in the fingerprint processing. Also, we provide a new fingerprint matching method based on Delaunay Triangle, which is able to admit a certain degree of deformation, translation and rotation. As the result shows, this system is proved to be working well through simulation and experiment.

[1] Anil K. Jain, Lin Hong, Sharath Pankanti, “Biometrics: Promising frontiers for emerging identification market”, February, 2000.
[2] E.R. Henry, Classification and Uses of Finger Prints, London: Routledge , 1900.
[3] Sharath Pankanti, Salil Prabhakar, Anil K. Jain, “On the Individuality of Fingerprints”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.24, pp. 1010-1025, 2002.
[4] Raffaele Cappelli, Alessandra Lumini, Dario Maio, and Davide Maltoni, “ Fingerprint Classification by Directional Image Partitioning”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.21, pp. 402-421, 1999.
[5] R.M. Stock, C.W. Swonger, “Development and evaluation of a reader of fingerprint minutiae”, Technical Report CAL No. XM-2478-X-1, pp. 13-17, 1969.
[6] Wu Chaohong, Shi Zhixin, Govindaraju Venu, “Fingerprint image enhancement method using directional median filter”, In: Proceedings of the SPIE, Vol.5404, pp. 66-75, 2004.
[7] Lin Hong, Anil Jain, Sharathcha Pankanti, and Ruud Bolle, “Fingerprint enhancement”, In: Proceedings of the 3rd IEEE workshop on applications of computer vision, Sarasota, pp. 202–207, 1996.
[8] Abdullah Çavuşoğlu, Salih Görgünoğlu, “A fast fingerprint image enhancement algorithm using a parabolic mask”, Computers & Electrical Engineering, Vol.34, pp. 250-256, 2008.
[9] T.Y. Zhang, C.Y. Suen, “A fast parallel algorithm for thinning digital patterns”, Communications of the ACM, Vol.27, pp. 236-239, 1984.
[10] Davide Maltoni, Dario Maio, Anil K. Jain, Handbook of Fingerprint Recognition, Springer, pp.171, 2003.
[11] George Bebis, Taisa Deaconu, Michael Georgiopoulos “Fingerprint Identification Using Delaunay Triangulation”, IEEE International Conference on Intelligence, Information, and Systems, Maryland, 1999.
[12] Tamer Uz, George Bebis, Ali Erol, Salil Prabhakar, “Minutiae-based template synthesis and matching for fingerprint authentication”, Computer Vision and Image Understanding archive, Vol.113, pp. 979-992, 2009.
[13] Ning Liu, Yilong Yin, Hongwei Zhang, “A Fingerprint Matching Algorithm Based On Delaunay Triangulation Net”, The Fifth International Conference on Computer and Information Technology, pp. 591-595, 2005.