在生物識別領域中，人類的靜脈特徵屬於新的生物辨識研究課題，為求使用方便，目前常見的靜脈辨識技術大致為手指靜脈、手掌靜脈等。靜脈辨識屬於活體辨識，由於靜脈的資訊都位於皮膚內層，有著不易仿造之優勢，為目前生物辨識較新的議題。目前許多相關研究，為求取得的靜脈影像清晰，使用的機構多數為高畫質的紅外線CCD攝影機。在本研究中，我們嘗詴採用市面上CMOS的紅外線camera為本實驗的機構。由於手掌蘊含豐富的靜脈特徵，我們以手掌靜脈辨識系統做為本次實驗的主題。 本論文提出兩種手掌靜脈特徵擷取方式，分別為Harris角點和SURF特徵極值。首先，將harris角點以CCH(Contrast context histogram，CCH)建立起角點特徵向量，利用角點特徵做初步特徵比對，篩選出第一階段的候選集。針對此候選集取出SURF特徵極值，並且以SURF特徵做第二階段比對，找出最相似者是否為受測者本人，此方式有助於整體辨識率的提升。

The biometric is very popular in recent years. The common biometrics features such as palmprint, fingerprint, iris, face. In daily life, many applications have developed based on the biometrics. In biometrics field, the vein recognitions are a novel research. Most of the vein recognitions are finger vein, palm vein and so on. The Vein information is effective only in vivo and difficult to forge because of inside the superficial skin. In order to capture clear images, many related studies which based on CCD high resolution near infrared camera. In this research, we attempted to use CMOS camera as our captured equipment. There are rich of information in Palm vein image for authentication, and it provides high accurate recognition rate. In this paper, we proposed two methods of features extraction, one is Harris corner detection and the other is SURF(Speeded up robust feature). First, we constructed feature descriptors in corner points with CCH(Contrast context histogram), and find candidate sets by comparing those feature descriptors. In those candidate sets, we extract feature points again with SURF, and they can be used to double authentication and achieve higher accuracy authentication.

[1] DIGITIMES http://www.digitimes.com.tw/tw/dt/n/shwnws.asp?CnlID=13&id=0000173793_P278NER583OOLF4QEUQ10&ct=1&OneNewsPage=2&Page=1

[2] 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, USA

[3] Naoto Miura, Akio Nagasaka, Takafumi Miyatak , ” Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification, ” Machine Vision and Applications, pp. 194–20, 21 July 2004

[4] Wang Lingyu, Graham Leedham , ” Near- and Far- Infrared Imaging for Vein Pattern Biometrics , “ IEEE International Conference on Video and Signal Based Surveillance, pp. 52-57, Nov 2006
[5] Sanchit, Mauricio Ramalho , Paulo Lobato Correia, Luis Ducla Soares, “ Biometric Identification through Palm and Dorsal Hand Vein Patterns, ” EUROCON - International Conference on Computer as a Tool (EUROCON), 2011 IEEE, pp. 1-4 , 27-29 April 2011
[6] Ajay Kumar , K. Venkata Prathyusha, “ Personal Authentication Using Hand Vein Triangulation and Knuckle Shape, ” IEEE TRANSACTIONS ON IMAGE PROCESSING, pp. 2127 – 2136 , Sept. 2009

[7] Rajendran Jeyaprakash, Jin Lee, Subir Biswas, Jae Mook Kim, ” SECURED SMART CARD USING PALM VEIN BIOMETRIC ON-CARD-PROCESS, ” International Conference on Convergence and Hybrid Information Technology 2008, pp. 548 – 551, 28-30 Aug. 2008
[8] B.Prasanalakshmi, A.Kannammal, “Secure Cryptosystem from Palm Vein Biometrics in Smart Card, ” Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on, pp. 653 – 657, 26-28 Feb. 2010
[9] Lin-Lin Huang, Akinobu Shimizu, and Hidefumi Kobatake , “ Classification-Based Face Detection Using Gabor Filter Features, “ IEEE International Conference on Automatic Face and Gesture Recognition, pp. 397 – 402, 17-19 May 2004
[10] Jinfeng Yang, Jinli Yang, Yihua Shi, “ Finger-vein segmentation based on multi-channel even-symmetric Gabor filters, “ Intelligent Computing and Intelligent Systems, 2009. ICIS 2009. IEEE International Conference on, pp. 500 - 503 , 20-22 Nov. 2009
[11] Makram Nabti , Ahmed Bouridane, “ AN EFFECTIVE IRIS RECOGNITION SYSTEM BASED ON WAVELET MAXIMA AND GABOR FILTER BANK, “ Signal Processing and Its Applications, 2007. ISSPA 2007. 9th International Symposium on, pp. 1–4, 12-15 Feb. 2007
[12] 鐘國亮, “影像處理與電腦視覺”, 東華書局, 民國九十五年三 月, 三版
[13] C. Harris and M.J. Stephens, “ A combined corner and edge detector, “ In Alvey Vision Conference, pp. 147–152, 1988
[14] Chun-Rong Huang, Chu-Song Chen , Pau-Choo Chung, “Contrast context histogram --An efficient discriminating local descriptor for object recognition and image matching, “
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, pp. 53-56, 2006
[15] DAVID G. LOWE, “ Distinctive Image Features from Scale-Invariant Keypoints, “ International Journal of Computer Visio, 2004
[16] 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
[17] 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, July 2005

[18] 張哲維, “A Scale Invariant Feature Transform Based Palm Vein Recognition System, ”, 2009
[19] 牟宗懷, “Using 2D Gabor Filters and SIFT Features to design an effective Palm vein and Palmprint Recognition device, ”, 2010
[20] Yi-Bo Zhang, “Palm Vein Extraction and Matching for Personal
Authentication, “VISUAL 2007, LNCS 4781, pp. 154-164, 2007
[21] Jing-Wein Wang , “Building Palm Vein Capturing System for Extraction, “ Systems Engineering (ICSEng), 2011 21st International Conference on, pp. 311-314, 16-18 Aug. 2011
[22] Khan, M.H.-M. , “ Dorsal hand vein biometric using Independent Component Analysis (ICA), “Internet Technology and Secured Transactions (ICITST), 2011 International Conference for, pp. 191 - 195 , 11-14 Dec. 2011