近年來，生物辨識的議題備受矚目，不同的生物辨識在生活中也有不同的應用。指靜脈辨識為非接觸式的體內識別，偽造的可能性低，除了這項優點外，方便使用和穩定性高也是靜脈辨識的優點，因此越來越多人對指靜脈辨識有興趣，相關議題也越來越多。目前許多銀行陸陸續續提出靜脈辨識，除了存提款便利性提高，也更加安全，然而靜脈系統的辨識速度、辨識率、EER都受到大家的矚目。
然而靜脈的特徵擷取，與影像處理技術有關，在影像濾波裡多小波擁有許多優勢，可以同時滿足正交性、對稱性、短支撐等良好特性，本篇論文利用GHM多小波進行靜脈圖像的濾波，GHM多小波是基於多分辨率分析，多分辨率分析是利用數據融合和小波變換進行圖像邊緣檢測，此特性能讓指靜脈影像得到壓縮與去雜訊的優點，除此之外，多小波結合多尺度的小波，計算速度上又能增快許多。
儘管目前在手指靜脈驗證有進展，但是在指靜脈辨識系統的效能上還有進步空間。首先，利用GHM濾波將指靜脈的特徵擷取，GHM多小波濾波能使靜脈的特徵便明顯，且運算速度快。第二步將濾波完的指靜脈進行機器學習(Machine Learning)，找出此人的靜脈圖。本文提出LFR(Learning-based Finger-vein recognition)演算法，運用GHM多小波融合機器學習來提高靜脈的辨識率和降低EER，並且用幾組資料庫證實LFR演算法擁有非常好的辨識效能。

In recent years, the issue of biometrics has attracted attention. Different biometrics have different applications in life. Because finger vein recognition is non-contact in vivo recognition, the possibility of counterfeiting is low, and it is very convenient to use and has high stability. More and more people are interested in finger vein identification, and there are more and more topics related to vein identification. At present, many banks continue to propose vein identification on a continuous basis, which makes deposits and withdrawals more convenient and safer. However, the identification speed, recognition rate, and EER of the intravenous system have received attention from everyone.
However, the feature extraction of veins is related to image processing technology. multiwavelet has many advantages in the image filtering. It can satisfy good characteristics such as orthogonality, symmetry, and short support. This paper uses GHM multiwavelet filter to perform vein images. GHM multiwavelet is based on multi-resolution analysis. Multi-resolution analysis is the use of data fusion and wavelet transform for image edge detection. This feature can make the finger vein image compression and denoising advantages. In addition, multiwavelet combined with multi-scale wavelets can speed up computation.
Although there is progress in finger vein verifications, performance is still room for improvement in finger vein identification system. First, use GHM filtering to extract the characteristics of the finger vein. GHM multiwavelet filter can make the characteristics of the vein obvious, and the operation speed is fast. The second step is to perform machine learning on the filtered finger vein. This step can find out the person's vein map. This paper proposes the LFR (Learning-based Finger-vein recognition) algorithm and uses GHM multiwavelet fusion machine learning to improve the recognition rate of veins and reduce EER.

[1] A. K. Jain, A. Ross, and S. Prabhakar, “An introduction to biometric recognition,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 420, Jan. 2004.
[2] S. Tirunagari, N. Poh, D. Windridge, A. Iorliam, N. Suki, and A. T. Ho, “Detection of face spoofing using visual dynamics,” IEEE Trans. Inf. Forensics Security, vol. 10, no. 4, pp. 762–777, Apr. 2015.
[3] G. L. Marcialis et al., “First international fingerprint liveness detection competition–LivDet 2009,” in Proc. ICIAP, 2009, pp. 12–23.
[4] C. Sousedik and C. Busch, “Presentation attack detection methods for fingerprint recognition systems: A survey,” IET Biometrics, vol. 3, no. 4, pp. 219–233, 2014.
[5] Z. Liu, Y. Yin, H.Wang, S. Song, and Q. Li, “Finger vein recognition with manifold learning,” J. Netw. Comput. Appl., vol. 33, no. 3, pp. 275-282, May 2010.
[6] J. Wu and S. Ye, “Driver identification using finger-vein patterns with Radon transform and neural network,” Expert Syst. Appl., vol. 36, no. 3, pp. 5793-5799, Apr. 2009.
[7] V. Strela, P. Heller, G. Strang, P. Topiwala, and C. Heil, “The application of multiwavelet filterbanks to image processing,” IEEE Transactions on Image Processing, 8(4), pp.548-563.
[8] R. Raghavendra, K. Raja, S. Venkatesh, C. Busch: "Transferable Deep Convolutional Neural Network Features for Fingervein Presentation Attack Detection", in Proceedings of 5th International Workshop on Biometrics and Forensics (IWBF 2017), Coventry, UK, April 4-5, (2017)
[9] Kang Ryoung Park, “Finger Vein Recognition By Combining Global And Local Features Based On SVM ,” Computing and Informatics, Vol. 30, 2011.
[10] Song Xie, Liyong Fang, Ziqian Wang, Zhaochun Ma and Jingyuan Li, “Review of personal identification based on near infrared vein imaging of finger,” 2017 2nd International Conference on Image, Vision and Computing (ICIVC).
[11] Surbiryala J, Raghavendra R, Busch C, “Finger vein indexing based on binary features,” ClII Colour and Visual Computing Symposium. IEEE, 2015.
[12] Raghavendra R, Surbiryala J, Busch C, “An efficient finger vein indexing scheme based on unsupervised c1ustering,” ClII IEEE International Conference on Identity, Security and Behavior Analysis. IEEE, 2015:1-8.
[13] Kejun Wang, Hui Ma, Oluwatoyin P. Popoola and Jingyu Liu (2011).Finger vein recognition, Biometrics, Dr.Jucheng Yang (Ed.), InTech, Available from: http://www.intechopen.com/books/biometrics/finger-vein-recognition
[14] V. Ramya, P. Vijaya Kumar, B. Palaniappan, “A Novel Design Of Finger Vein Recognition For Personal Authentication And Vehicle Security”, Journal of Theoretical and Applied Information Technology, Vol. 65 No.1, 2014.
[15] Asmaa Q. Shareef, Loay E. George, Roaa E. Fadel, “Computing Finger Vein Recognition Using Haar Wavelet Transform”, in International Journal of Computer Science and Mobile Computing, 4(3), pp. 1-7, March 2015.
[16] Fotios Tagkalakis, Dimitrios Vlachakis, Vasileios Megalooikonomou, Athanassios Skodras, “A Novel Approach To Finger Vein Authentication ”, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp.659-662, 2017.
[17] Lumei Dong, Gongping Yang, Yilong Yin, Fei Liu, and Xiaoming Xi. Finger Vein Verification Based on a Personalized Best Patches Map. IJCB2014.
[18] Fengxu Guan, Kejun Wang, Hongwei Mo, Hui Ma, Jingyu Liu, “Research of Finger Vein Recognition based on fusion of Wavelet Moment and Horizontal and Vertical 2DPCA”, Image and Signal Processing, 2009.
[19] Devarasan Ezhilmaran, Rose Bindu Joseph, “Finger vein biometric system with type-2 fuzzy enhancement and minutiae matching”, IEEE Region 10 Symposium (TENSYMP), 2017.
[20] Huafeng Qin, Mounim A. El-Yacoubi, “Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification”, IEEE Transactions on Information Forensics and Security, Aug. 2017.
[21] Haiying Liu, Lu Yang, Gongping Yang, Yilong Yin, “Discriminative Binary Descriptor for Finger Vein Recognition”, IEEE Access, December 2017.
[22] Available at: https://read01.com/zh-tw/QAMOJm.html#.WxeTy58zZPY [Accessed 6 Jun. 2018].
[23] Available at: http://www.zgdlsy.cn/news/hynews/hynews3.html?cv=1
[24] J. Geronimo, Hardin D., and Massopust P., “Fractal functions and wavelet expansions based on several scaling functions,” J. Approx. Theory, Vol. 78, pp. 373–401, 1994.
[25] P., and Heil C., “The application of multiwavelet filter banks to image processing,” IEEE Transactions on Image Processing, Vol. 8, No. 4, pp. 548-563 April 1999.
[26] G. Strang and V. Strela, “Short wavelets and matrix dilation equations," IEEE Trans. on SP, vol. 43, pp. 108-115, 1995.
[27] Limited Phase Only Correlation and Width Centroid Contour Distance for finger based biometrics,” Expert Systems with Applications, Volume 41, Issue 7, 1 June 2014, Pages 3367-3382, ISSN 0957-4174.
[28] Wenming Yang, Xiang Yu, Qingmin Liao, “Personal authentication using finger vein pattern and finger-dorsa texture fusion,” Proceedings of the 17th ACM international conference on Multimedia. ACM, 2009: 905-908.
[29] Ajay Kumar and Yingbo Zhou, “Human Identification using Finger Images”, IEEE Trans. Image Processing, vol. 21, pp. 2228-2244, April 2012.
[30] N. Miura, A. Nagasaka, and T. Miyatake, “Extraction of finger-vein patterns using maximum curvature points in image profiles,” IEICE Trans. on Inf. Systems, vol. 90, no. 8, pp. 1185–1194, 2007.
[31] A. Kumar and Y. Zhou, “Human identification using finger images,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 2228–2244, Apr. 2012.
[32] A. Ross, and A. K. Jain, “Human recognition using biometrics: an overview,” in Annales des Telecommunications, vol. 62, no. 1-2, pp.11–35, 2007.