隨著電子資訊的蓬勃發展,科技的安全議題受到相當的重視。生物辨識 (Biometrics)近年被廣泛的使用在各個領域,其中指靜脈辨識使用手指靜脈紋路作 為辨識依據,相較於其他方法,靜脈紋路具有良好的唯一性、活體辨識、不易改 變及偽造,因此開始被廣泛使用並成為重要的研究議題之一。本論文利用指靜脈 形成拓樸之結構與影像品質量尺量測指靜脈影像的相似度,並結合高效能平行計 算圖形處理器(Graphic Process Unit, GPU)對骨架匹配過程進行加速。實驗結果顯 示出此系統平均錯誤率(EER)為 0.94%,與 CPU 相比之下,加速了 12.75 倍的比 對時間。

With the evolution of consumer electronics technologies, personal private information stored in the consumer electronics devices is becoming increasingly valuable. To protect private information, biometrics technology is subsequently equipped into the consumer electronics devices. Finger-vein is one of the biometric features which gaining popularity for identification recently. In this thesis, we proposed a twofold finger-vein authentication. The first task of identification process in our system using skeleton topologies to determine the similarities and differences between finger-vein patterns. Yet, some extreme cases with ambiguous features cannot be successfully classified. Hence, the image quality assessment (IQA) is employed as the second stage of the system. Furthermore, to overcome the computational requirement of the algorithm, the GPU is adopted in our system. The many-core computing framework provided by GPU offers an opportunity to enhance the skeleton matching process. The experimental results show the proposed method achieves 0.94% equal error rate and reach a speed-up up to 12.75 times than CPU.

[1] P. Corcoran and A. Cucos, “Techniques for securing multimedia content in consumer electronic appliances using biometric signatures, ” IEEE Transactions on Consumer Electronics, vol 51, no. 2, pp. 545-551, May 2005.
[2] A. K. Jain, S. Pankanti, S. Prabhakar, H. Lin, and A. Ross, “Biometrics: a grand challenge,” Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 2, pp. 935-942, 2004.
[3] R. Cappelli, M. Ferrara, and D. Maltoni, “Minutia cylinder-code: A new representation and matching technique for fingerprint recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 12, pp. 2128–2141, Dec. 2010.
[4] Shen W, Surette M and Khanna R, “Evaluation of automated biometrics-based identification and verification systems,” In: Special issue on automated biometric systems. Proc IEEE 85(9):1463–1478, 1997.
[5] D. Maltoni, D. Maio, A. Jain, and S. Prabhakar, “Handbook of Fingerprint Recognition,” New York, NY, USA: Springer-Verlag, 2009.fp, 1997.
[6] Chen X, Flynn PJ, Bower KW, “Visible-light and infrared face recognition, ” In: Proceedings of the workshop on multimodal user authentication, pp 48–55, 2003.
[7] Jianxu Chen, Feng Shen, Danny Ziyi Chen and Patrick J. Flynn, “Iris Recognition Based on Human-Interpretable Features,” IEEE Trans. Inf. Forensics Security, vol. 11, no. 7, pp. 1476–1485, Ju. 2016.
[8] H. Proenca, “Iris recognition: On the segmentation of degraded images acquired in the visible wavelength,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(8):1502–1516, 2010.
[9] Venayagamoorthy GK, Moonasar V, Sandrasegaran K, ” Voice recognition using neural networks,” In: Proceedings of the IEEE South African symposium on communication and signal processing (COMSIG 98), pp 29–32, 1998.
[10] Wenxin Li, J. You, and D. Zhang, ” Texture-based palmprint retrieval using a layered search scheme for personal identification,” Multimedia, IEEE Transactions on, 7(5):891–898, 2005.
[11] D. Zhang, Wai-Kin Kong, J. You, and M. Wong, ” Online palmprint identification,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, 25(9):1041–1050, 2003.
[12] Z. Liu, Y. Yin, H. Wang, S. Song, and Q. Li, “Finger vein recognition with manifold learning”, Journal of Network and Computer Applications, vol.33, no.3, pp. 275-282, 2010.
[13] Jian-Da Wu and Chiung-Tsiung Liu, ”Finger-vein pattern identification using {SVM} and neural network technique,” Expert Systems with Applications, 38(11):14284 – 14289, 2011
[14] Jian-Da Wu and Siou-Huan Ye, ” Driver identification using finger-vein patterns with radon transform and neural network,” Expert Systems with Applications, 36(3, Part 2):5793 – 5799, 2009.
[15] Y. Deng, C. Kenney, M. S. Moore, and B. S. Manjunath, "Peer group filtering and perceptual color quantization", Proc. IEEE Int. Symp. Circuits Syst., vol. 4, pp. 21-24, 1999
[16] L. Lam, S. Lee, and C. Suen, “Thinning methodologies-a comprehensive survey,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 14, no. 9, pp. 869–885, 1992.
[17] A. Kumar and K. Prathyusha, “Personal authentication using hand vein triangula- tion and knuckle shape,” Image Processing, IEEE Transactions on, vol. 18, no. 9, pp. 2127–2136, 2009.
[18] Zhou Wang, Eero P. Simoncelli, and Alan C. Bovik, “Multi-scale structural similarity for image quality assessment,” In in Proc. IEEE Asilomar Conf. on Signals, Systems, and Computers, (Asilomar, pages 1398–1402, 2003).
[19] NVIDIA (2015, September) CUDA C Programming Guide. <http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html>.
[20] Y. Yin, L. Liu, and X. Sun, “Sdumla-hmt: A multimodal biometric database.,” in CCBR (Z. Sun, J.-H. Lai, X. Chen, and T. Tan, eds.), vol. 7098 of Lecture Notes in Computer Science, pp. 260–268, Springer, 2011.
[21] NVIDIA (2015, September) CUDA C Best Practices Guide. <http://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html>.
[22] Aled C. Weaver, “Biometric Authentication,” University of Virginia, February 2006.
[23] Technical Document About FAR, FRR and EER Version 1.0, SYRIS Technology Corp., 2004.
[24] NVIDIA (2014, February) Maxwell Compatibility Guide for CDUA Applications < https://developer.nvidia.com/maxwell-compute-architecture>
[25] N. Miura, A. Nagasaka, and T. Miyatake, “Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification,” Mach. Vision Appl., vol. 15, pp. 194–203, Oct. 2004.
[26] N. Miura, A. Nagasaka, and T. Miyatake, “Extraction of finger-vein patterns using maximum curvature points in image profiles,” IEICE - Trans. Inf. Syst., vol. E90-D, pp. 1185–1194, Aug. 2007.
[27] A. Masmoudi, R. Trabelsi, M. Krid, and D. Masmoudi, “Implementation of a fin- gervein recognition system based on improved gaussian matched filter,” MAGNT Research Report, vol. 2, no. 4, pp. 251–260, 2014.
[28] T. Ong, J. Teng, K. Muthu, and A. Teoh, “Multi-instance finger vein recognition using minutiae matching,” in Image and Signal Processing (CISP), 2013 6th Inter- national Congress on, vol. 03, pp. 1730–1735, Dec 2013.
[29] D. Wang , J. Li, and G. Memik, “User identification based on finger- vein patterns for consumer electronics devices”, IEEE Transactions on Consumer Electronics, vol. 56, no. 2, pp. 799-804, 2010.
[30] N. Damera-Venkata, T. D. Kite, W. S. Geisler, B. L. Evans and A. C. Bovik, "Image quality assessment based on a degradation model", IEEE Trans. Image Process., vol. 9, no. 4, pp. 636-650, 2000.
[31] D. M. Chandler and S. S. Hemami, "VSNR: A wavelet-based visual signal-to-noise ratio for natural images", IEEE Trans. Image Process, vol. 16, no. 9, pp. 2284-2298, 2007
[32] Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” Image Processing, IEEE Transactions on, vol. 13, no. 4, pp. 600–612, 2004.