近年來科技的迅速發展，使得人們的生活越來越便利，相對於言，資訊安全議題則越來越受到大家的重視，身分識別系統逐漸被應用在各種相關環境中。生物特徵辨識是近年來火熱的話題，利用生物特徵的唯一性來做身分識別系統，已成為資訊領域研究方向之一。
由於掌靜脈辨識具有活體資訊之特性，且人體靜脈資訊於成年後其結構已穩定分布，因此非常適合應用在生物特徵辨識系統上。然而，之前的掌靜脈辨識系統的擷取影像方式是擺放在固定機構上面，容易受到使用者擺放位置而影響辨識率。本論文是採取非接觸式的方式擷取掌靜脈影像，其困難度遠比固定式機構還要大，因此如何有效地減少使用者造成的手掌位移、遠近、旋轉而造成之影響將會是決定此辨識系統效能之關鍵。
本論文將辨識系統劃分為兩階段運作，透過第一階段二值化影像之方式，去計算感興趣區域的位置，接著將感興趣區域的影像放入深度學習的模組訓練，完成訓練後，再用準備好的測試集測試，取得最終辨識結果。

The rapid development of science and technology in recent years has made people live more and more convenient. Relatively, people pay much attention on information security and identity recognition systems are gradually applied in various related environments. Biometrics is a hot research topic in recent years. Therefore, using the uniqueness of biometrics as an identity recognition system has gradually become one of the research directions in the field of computer science.
Since palm vein has the characteristics of living body information and the structure of human vein information is stable after grown up, palm vein is suitable for biometric identification system. However, the image capturing method of the previous palm vein recognition system is placed on a fixed mechanism, which is very easily influenced by the displacement of user's palm position. In this thesis, we use a contactless method to capture the palm vein images. It is more difficult than the fixed mechanism. How to effectively reduce the impact of the palm displacement, distance changing, and rotation caused by the user will be the key factors to determine the performance of this recognition system.
In this thesis, the identification system is divided into two stages. In the first stage, the captured palm vein image is binaried and the region of interest is obtained. Then in the second stage, the image of the region of interest is put into the deep learning network for training. Finally, a prepared test dataset is used to do testing and the best recognition results are obtained.

[1] Z. X. Geng and Y. Q. Qiao, "An Improved Illumination Invariant SURF Image Feature Descriptor," 2017 International Conference on Virtual Reality and Visualization (ICVRV), Zhengzhou, China, 2017, pp. 389-390.
[2] V. Gurunathan, T. Sathiyapriya and R. Sudhakar, "Multimodal biometric recognition system using SURF algorithm," 2016 10th International Conference on Intelligent Systems and Control (ISCO), Coimbatore, 2016, pp. 1-5.
[3] L. Zhu, "Finger knuckle print recognition based on SURF algorithm," 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), Shanghai, 2011, pp. 1879-1883.
[4] Zhang, Y.-B., Li, Q., You, J., et al., "Palm vein extraction and matching for personal authentication," Int. Conf. on Advances in Visual Information Systems, Shanghai, China, June 2007, pp. 154–164.
[5] Greitans, M., Pudzs, M., Fuksis, R., "Palm vein biometrics based on infrared imaging and complex matched filtering," Proc. of the 12th ACM Workshop on Multimedia and Security, Roma, Italy, September 2010, pp. 101–106.
[6] Kabacinski, R., Kowalski, M., "Vein pattern database and benchmark results," Electron. Lett., 2011, 47, (20), pp. 1127–1128.
[7] Dandawate, Y.H., Inamdar, S.R., "Fusion based multimodal biometric cryptosystem," 2015 Int. Conf. on Industrial Instrumentation and Control (ICIC), Wellesely Road, Shivaji Nagar, Pune, Maharashtra, India, May 2015, pp. 1484–1489.
[8] Gohk, O., Andrew, T., "Design and implementation of a contactless palm vein recognition system," Proc. of the 2010 Symp. on Information and Communication Technology, Hanoi, Vietnam, August 2010, pp. 92–99.
[9] P. Tome and S. Marcel, "Palm Vein Database and Experimental Framework for Reproducible Research," 2015 International Conference of the Biometrics Special Interest Group (BIOSIG), Darmstadt, 2015, pp. 1-7.
[10] P. Cancian, G. W. Di Donato, V. Rana and M. D. Santambrogio, "An embedded Gabor-based palm vein recognition system," 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Orlando, FL, 2017, pp. 405-408.
[11] X. Yan, F. Deng and W. Kang, "Palm Vein Recognition Based on Multi-algorithm and Score-Level Fusion," 2014 Seventh International Symposium on Computational Intelligence and Design, Hangzhou, 2014, pp. 441-444.
[12] Jen-Chun Lee, "A novel biometric system based on palm vein image, " Pattern Recognition Letters, Volume 33, Issue 12, 2012, Pages 1520-1528.
[13] R. Movchan and Z. Shen, "Adaptive thresholding hosvd algorithm with iterative regularization for image denoising," 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 2017, pp. 2991-2995.
[14] D. Liu and J. Yu, "Otsu Method and K-means," 2009 Ninth International Conference on Hybrid Intelligent Systems, Shenyang, 2009, pp. 344-349.
[15] S. M. Pizer, R. E. Johnston, J. P. Ericksen, B. C. Yankaskas and K. E. Muller, "Contrast-limited adaptive histogram equalization: speed and effectiveness," [1990] Proceedings of the First Conference on Visualization in Biomedical Computing, Atlanta, GA, USA, 1990, pp. 337-345.
[16] Karel Zuiderveld, "Contrast Limited Adaptive Histogram Equalization, " Graphics Gems IV(1994) , pp. 474-485.
[17] A. Mishra, M. Gupta and P. Sharma, "Enhancement of Underwater Images using Improved CLAHE," 2018 International Conference on Advanced Computation and Telecommunication (ICACAT), Bhopal, India, 2018, pp. 1-6.
[18] M. Mohan, L. P. T and L. S. Nair, "Fuzzy c-means Segmentation on Enhanced Mammograms Using CLAHE and Fourth Order Complex Diffusion," 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 2020, pp. 647-651.
[19] Satoshi Suzuki, KeiichiA be, "Topological structural analysis of digitized binary images by border following," Computer Vision, Graphics, and Image Processing, Volume 30, Issue 1, 1985, Pages 32-46.
[20] Lie Kang, Sheng Zhong and Fang Wang, "A new contour tracing method in a binary image," 2011 International Conference on Multimedia Technology, Hangzhou, 2011, pp. 6183-6186.
[21] Jayaram, M., Fleyeh, H. (2016), "Convex Hulls in Image Processing: A Scoping Review, " American Journal of Intelligent Systems, 6(2): pp. 48-58.
[22] Ren Lisheng, Wang Lizhong, "Analysis of image matching algorithm for corner detection based on curvature scale space, " Application of Electronic Technique, 2016, 42(12)：pp. 112-114，118.
[23] "直方圖均化維基百科", https://zh.wikipedia.org/zh-tw/%E7%9B%B4%E6%96%B9%E5%9B%BE%E5%9D%87%E8%A1%A1%E5%8C%96
[24] "Adaptive histogram equalization Wikipedia", https://en.wikipedia.org/wiki/Adaptive_histogram_equalization
[25] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 770-778.
[26] M. Yusoh, A. Phon-on and K. Khongkraphan, "Estimating Motion Blur Parameters with Gradient Descent Method," 2018 22nd International Computer Science and Engineering Conference (ICSEC), Chiang Mai, Thailand, 2018, pp. 1-4.
[27] A. Bouillard and P. Jacquet, "Quasi Black Hole Effect of Gradient Descent in Large Dimension: Consequence on Neural Network Learning," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019, pp. 8365-8369.
[28] G. Cong and O. Bhardwaj, "A Hierarchical, Bulk-Synchronous Stochastic Gradient Descent Algorithm for Deep-Learning Applications on GPU Clusters," 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, 2017, pp. 818-821.
[29] R. G. J. Wijnhoven and P. H. N. de With, "Fast Training of Object Detection Using Stochastic Gradient Descent," 2010 20th International Conference on Pattern Recognition, Istanbul, 2010, pp. 424-427.
[30] R. R. Tobias et al., "Faster R-CNN Model With Momentum Optimizer for RBC and WBC Variants Classification," 2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech), Kyoto, Japan, 2020, pp. 235-239.
[31] W. Xiong et al., "Convolutional Neural Network Based Atmospheric Turbulence Compensation for Optical Orbital Angular Momentum Multiplexing," in Journal of Lightwave Technology, vol. 38, no. 7, pp. 1712-1721, 1 April1, 2020.
[32] N. Zhang, D. Lei and J. F. Zhao, "An Improved Adagrad Gradient Descent Optimization Algorithm," 2018 Chinese Automation Congress (CAC), Xi'an, China, 2018, pp. 2359-2362.
[33] Diederik P. Kingma, Jimmy Ba, "Adam: A Method for Stochastic Optimization," 3rd International Conference for Learning Representations, San Diego, 2015
[34] "熵維基百科", https://zh.wikipedia.org/wiki/%E7%86%B5
[35] "相對熵維基百科", https://zh.wikipedia.org/zh-tw/%E7%9B%B8%E5%AF%B9%E7%86%B5
[36] "交叉熵維基百科", https://zh.wikipedia.org/zh-tw/%E4%BA%A4%E5%8F%89%E7%86%B5
[37] The Chinese Academy of Sciences, Automation Institute , "CASIA Palmprint Database, " http://biometrics.idealtest.org/.
[38] The Hong Kong Polytechnic University , "PolyU Multispectral Palmprint Database, " https://www4.comp.polyu.edu.hk/~biometrics/MultispectralPalmprint/MSP.htm