資訊安全是近年來最被重視的領域之一，其中又以生物特徵辨識之研究最受歡迎。生物特徵辨識技術主要是利用人體的生理特徵或是其行為模式作為身分辨識。本研究採用之生物特徵即是生理特徵之一。人體的生物特徵有以下幾種類型：脱氧核糖核酸(即DNA)、血管、手指紋路、長相、等等，其中又以指紋與靜脈特徵辨識最為快速以及精準。人體的靜脈大致在成年之後會呈現穩定的分佈，並具備單一性。由於血管位於皮膚內且必須要活體辨識，故其隱匿性與防偽性皆優於指紋辨識，使其成為生物特徵辨識領域中最好的選擇。
本研究設計出一套全新的手掌靜脈資訊擷取裝置，此裝置具有固定手掌位置之能力，提供了良好的辨識環境。硬體機構採用了Linux之嵌入式系統而在軟體辨識系統上，提出了三階段的快速特徵篩選。最後經由實驗證實，與先前論文比較，本論文之硬體機構設計與辨識比對方法都擁有低成本與高辨識率之優勢。

For the past few years, information security became one of major researches in the world; especially, for the biometric recognition researches. Biometric recognition techniques mainly use the physiological characteristics of the human body or their behaviors to do identification. The biometric used in this study is one of physiological characteristics of the human body. The biometric can be classified into several types: DNA, vein, finger print, appearance, etc. Among them, the finger print and vein recognitions are fast and accurate. The veins will be distributed fixed with unity after a human is becoming an adult. Owing to the vein being deeply under the skin and recognized lively, compared to finger print, it is hard to be visible and fake. Therefore, vein recognition technique becomes the best choice for biometric recognition.
In this study, a novel palm vein information capture device was designed, and the palm can be fixed in such a device, providing a good environment for identification. For the hardware, an embedded system which is running on Linux is provided. For the software recognition system, three-level feature descriptors were proposed to screen palm veins rapidly. Finally, the experiments show that the hardware cost can be reduced and the recognition rate of the software is quite high, compared to other existing systems.

[1] Senao International CO., LTD, “生物辨識(Biometric)系統,” http://www.senao.com.tw/proLife_Content.aspx?id=437.
[2] 國家政策網路智庫, “運用生物特徵辨識身分制度之比較研究,” http://thinktank.nat.gov.tw/lp.asp?ctNode=146&CtUnit=7&BaseDSD=11&mp=1&htx_ghtx.topcat=18982.
[3] Masaki Watanabe, Toshio Endoh, Morito Shiohara and Shigeru Sasaki, “Palm Vein Authentication Technology and Its Applications,” The Biometric Consortium Conference, pp. 1-2, September 19-21, 2005.
[4] Naoto Miura, Akio Nagasaka and Takafumi Miyatak, “Feature Extraction of Finger-vein Patterns Based on Repeated Line Tracking and Its Application to Personal Identification,” Machine Vision and Applications, pp. 194, July 20-21, 2004.
[5] Sanchit, Maurício Ramalho, Paulo Lobato Correia and Luís Ducla Soares, “Biometric Identification through Palm and Dorsal Hand Vein Patterns,” EUROCON-International Conference on Computer as a Tool, pp. 1-4, April 27-29, 2011.
[6] Jian-Gang Wang, Wei-Yun Yau and Andy Suwandy, “Feature-level Fusion of Palmprint and Palm Vein for Person Identification Based on a “Junction Point” representation,” Institute for Infocomm Research, A*STAR (Agency for Science, Technology and Research), ICIP, pp. 253-256, 2008.
[7] Hao Li, Zhenhua Guo, Shouyu Ma and Nan Luo, “A New Touchless PalmPrint Location Method Based on Contour Centroid,” Hand-Based Biometrics (ICHB), IEEE, pp. 1-5, 2011.
[8] Goh Kah Ong Michael, Tee Connie and Andrew Beng Jin Teoh, “Touch-less Palm Print Biometrics: Novel Design and Implementation,” Image and Vision Computing 26, pp. 1551-1560, 2008.
[9] Leila Mirmohamadsadeghi and Andrzej Drygajlo, “Palm Vein Recognition with Local Binary Patterns and Local Derivative Patterns,” Proceedings of the International Joint Conference on Biometrics, pp. 1-6, 2011.
[10] B.Prasanalakshmi and A.Kannammal, “Secure Cryptosystem from Palm Vein Biometrics in Smart Card,” Computer and Automation Engineering (ICCAE), 2nd International Conference, pp. 653- 657, Feb 26-28, 2010.
[11] Jing-Wein Wang and Tzu-Hsiung Chen, “Building Palm Vein Capturing System for Extraction,” 21st International Conference on Systems Engineering, pp. 311-314, 2011.
[12] Ajay Kumar and K. Venkata Prathyusha, “Personal Authentication Using Hand Vein Triangulation and Knuckle Shape,” IEEE Transactions On Image Processing, pp. 2127-2136, Sept. 2009.
[13] 鄭又誠, “Apply Bi-Features to Implement a Palm Vein Recognition System and Device Based on Gabor-Min,” Master Thesis, Dept. of Comp. Sci. and Inf. Eng., National Taiwan University of Science and Technology, 2013.
[14] Herbert Bay, Andreas Ess, Tinne Tuytelaars and Luc Van Gool, “Speeded-Up Robust Features (SURF),” Computer Vision and Image Understanding 110, pp. 346-359, 2008.
[15] J.G. Daugman, “Two-Dimensional Spectral Analysis of Cortical Receptive Field Profiles,” Vision Research, vol. 20, pp. 847-856, 1980.
[16] Woods, R.E., Gonzalez, R.C., “Real-time digital image enhancement,” Proceedings of the IEEE, vol. 69, pp.683-654, 1981.
[17] Stephen Se, David Lowe and Jim Little, “Vision-based Mobile Robot Localization and Mapping Using Scale-Invariant Features,” Int. Conf. on Robotics and Automation (ICRA), pp. 2051-2058, 2001.
[18] Herbert Bay, Tinne Tuytelaars, Luc Van Gool and ETH Zurich, “ SURF: Speeded Up Robust Features,” Computer Vision and Image Understanding (CVIU), vol. 110, no. 3, pp. 346-359, 2008.
[19] H. Bay, B. Fasel, and L. van Gool, “Interactive Museum Guide: Fast and Robust Recognition of Museum Objects,” Proceedings of the First International Workshop on Mobile Vision, May 2006.
[20] H. Bay, T. Tuytelaars and L. Van Gool, “SURF: Speeded up Robust Features,” ECCV, pp. 404-417, 2006.
[21] Huang, Hui, et al., “A New Scale Invariant Feature Detector and Modified SURF Descriptor,” Natural Computation (ICNC), 2010 Sixth International Conference on, Vol. 7. IEEE, pp.3734-3738, 2010.
[22] Simard, Patrice Y., et al. “Boxlets: A Fast Convolution Algorithm for Signal Processing and Neural Networks,” Advances in Neural Information Processing Systems, pp. 571-577, 1999.
[23] Viola P and Jones M, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” IEEE Conference on Computer Vision and Pattern Recognition, pp. I-511 - I-518, 2001.
[24] Bauer, Johannes, Niko Sunderhauf, and Peter Protzel. “Comparing Several Implementations of Two Recently Published Feature Detectors,” Proc. of the International Conference on Intelligent and Autonomous Systems, Vol. 6. Part 1, pp. 143-148, 2007.
[25] Ajay Kumar and K. Venkata Prathyusha, “Personal Authentication Using Hand Vein Triangulation and Knuckle Shape,” IEEE Transactions on Image Processing, pp. 2127-2136, Sept. 2009.
[26] Khan, M.H.-M. , “Dorsal Hand Vein Biometric Using Independent Component Analysis (ICA),” Internet Technology and Secured Transactions (ICITST), pp. 191-195, Dec 11-14, 2011.
[27] Wenming Yang, Qing Rao, Qingmin Liao, “Personal Identification for Single Sample Using Finger Vein Location and Direction Coding,” Hand-Based Biometrics (ICHB), 2011 International Conference on, pp. 17-18, Nov. 2011.
[28] Ramsoful, P., Heenaye-Mamode Khan, M., “Feature Extraction Techniques for Dorsal Hand Vein Pattern,” Innovative Computing Technology (INTECH), 2013 Third International Conference on, pp. 49–53, 2013.
[29] Mohamed, H.N., El-Alamy, E.A., Shahin, M.K., “Whole-hands Multiple-instances Finger Vein Biometric System,” Biomedical Engineering Conference (CIBEC), 2012 Cairo International, pp.68–72, 2012.
[30] Yuhang Ding, Dayan Zhuang and Kejun Wang, “A Study of Hand Vein Recognition Method,” Proceedings of the IEEE International Conference on Mechatronics & Automation Niagara Falls, Canada, pp. 2106–2110, July 2005.
[31] 江振宇, “Using SURF and CCH to Design an Effective Palm Vein Recognition Device,” Master Thesis, Dept. of Comp. Sci. and Inf. Eng., National Taiwan University of Science and Technology, 2012.
[32] Jing-Wein Wang, “Building Palm Vein Capturing System for Extraction,” Systems Engineering (ICSEng), 21st International Conference, pp. 311-314, Aug 16-18, 2011.
[33] Fletcher, Richard Ribón, et al. “Development of Mobile-based Hand Vein Biometrics for Global Health Patient Identification,” Global Humanitarian Technology Conference (GHTC), 2014 IEEE, pp. 541-547, 2014.
[34] Fan, Lin Lin, et al. “Near Infrared Finger Vein Recognition Method Based on Subspace Projection Technology,” Advanced Materials Research. Vol. 1030. pp. 2382-2385, 2014.