生物辨識是近幾年來相當重要的研究課題，生物辨識使用了人體上個體之間獨一無二的特徵進行辨識，像是最為廣泛使用的指紋辨識，還有人臉、虹膜、聲紋，而最近最為風行的則是靜脈辨識。靜脈辨識利用血液中血紅蛋白和其它人體組織對近紅外線的吸收率不同，讓靜脈紋理成像進行辨識。目前的靜脈辨識有使用手背、手掌及手指的靜脈進行辨識，而其中最普遍的則是手掌和手指靜脈。因為靜脈辨識是活體辨識，所以在偽造和造假的難度上是最高的，安全性也是最高的。
本論文將以低成本的硬體設備設計指靜脈辨識系統，期望在低品質的影像上也能有較高的辨識效果。不同於一般的指靜脈辨識，本論文採用反射法進行靜脈的擷取。首先決定擷取到影像的ROI，之後使用區域性灰階尺度正規化進行對比度的強化，再使用Sobel運算子對靜脈紋理強化，最後採用SURF進行特徵的擷取和比對。

Biometrics is a very important research topic in recent years. It is uses unique body feature between different people for identification. The most widely used such as fingerprint recognition, there are other like face, iris, voice, and the most popular of biometrics is vein identification. Vein identification is uses different near-infrared absorption rate of blood hemoglobin and other body tissues, make the vein texture appear for identification. Vein recognition is currently using back, palm and finger vein, the most common is the palm and finger vein. Vein recognition is vital identification so it’s very difficult to forge and fake, and it is also most secure.
This paper will design a finger vein recognition system uses low-cost hardware, expected in the low-quality images can also have higher recognition results. Unlike the general finger vein recognition, this paper uses reflection method to capture vein image. First, decide the ROI from the capture image, then uses local gray-scale normalization for contrast enhancement, and then uses Sobel operator to enhance vein texture. Finally, use SURF for feature extraction and matching.

[1] David Mulyono and Horng ShiJinn, "A study of finger vein biometric for personal identification," International Symposium on Biometrics and Security Technologies, 2008. ISBAST 2008, pp.1-8
[2] "生物辨識技術各分類研究與發展分析", http://www.digitimes.com.tw/tw/dt/n/shwnws.asp?cnlid=13&packageid=3324&id=0000173793_P278NER583OOLF4QEUQ10
[3] Mr. M.Mohamed syed Ibrahim, Dr. Faris Salman Ai-Namiy, Dr. Marsaline Beno and Dr. L.Rajaji. "Biometric Authentication for secured Transaction using Finger Vein Technology," Chennai and Dr.MGR University Second International Conference on Sustainable Energy and Intelligent System (SEISCON 2011)
[4] N. Miura, A. Nagasaka, and T. Miyatake, "Feature extraction of fingerveinpatterns based on repeated line tracking and its application topersonal identification," Mach. Vision Appl. 15(4), 194–203 (2004).
[5] N. Miura and A. Nagasaka, "Extraction of finger-vein patterns using-maximum curvature points in image profiles, " presented atMVA2005 IAPR Conf. on Machine Vision Applications, pp. 347–350,IEICE-INST Electronics Information Communications ENG, Tokyo(2005)
[6] Jinfeng Yang and Minfu Yan, "An Improved Method for Finger-vein Image Enhancement,” Signal Processing (ICSP), pp1706-1709, Oct 2010
[7] Wenming Yang, Qing Rao and Qingmin Liao, "Personal Identification For Single Sample Using Finger Vein Location and Direction Coding," Hand-Based Biometrics (ICHB), pp.1-6, Nov 2011
[8] 李雪妍, 郭樹旭, "融合指紋和指靜脈的多模態生物識別技術的研究," 吉林大學博士學位論文
[9] Junichi Hashimoto, "Finger Vein Authentication Technology and Its Future," Symposium on VLSI Circuits, 2006. Digest of Technical Papers. 2006, Honolulu, HI , PP. 5-8 (2006).
[10] " [創新趨勢] 一「手」就搞定：靜脈辨識技術", http://blog.uns.org.tw/node/209
[11] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, ETH Zurich, "SURF: Speeded Up Robust Features," Computer Vision and Image Understanding (CVIU), Vol. 110, No. 3, pp. 346–359, 2008
[12] 鐘國亮, "影像處理與電腦視覺," 東華書局, 2006
[13] Joung-Youn Kim, Lee-Sup Kim, and Seung-Ho Hwang. "An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization," IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 11, NO. 4, APRIL 2001.
[14] H. Bay, B. Fasel, and L. van Gool, "Interactive museum guide: Fast and robust recognition of museum objects," In Proceedings of the first international workshop on mobile vision, May 2006.
[15] H. Bay, T. Tuytelaars and L. Van Gool, "SURF: Speeded up robust features," In ECCV, 2006.
[16] Lowe, D. G., "Distinctive Image Features from Scale-Invariant Key-points," International Journal of Computer Vision, 60, 2, pp. 91-110, 2004.
[17] David G. Lowe, "Distinctive image features from scale-invariant key-points," International Journal of Computer Vision, 60, 2 (2004), pp. 91-110.
[18] 王永明, 王貴錦, "圖像局部不便性及描述," 國防工業出版社
[19] Viola P, Jones M, "Rapid object detection using a boosted cascade of simple features," In IEEE Conference on Computer Vision and Pattern Recognition, 2001
[20] Simard P, Bottou L, Haffner P,et al, "Boxlets: a fast convolution algorithm for signal processing and neural networks," Advances in Neural Information Processing Systems, 1999
[21] 曾若涵, "Feature extraction and matching of finger-vein patterns based on SURF(Speeded Up Robust Features), " 2011