「掌紋」在中國相學中，運用地相當廣泛，能夠分析命理、預卜吉凶與判斷性格；在中醫學中，「掌紋」更是「望診」的重要訊息取得途徑之一。近年來，隨著資訊科技的發展，人們越來越依賴網路，使得資訊安全問題備受重視，身份辨識因此成為重要的研究議題。傳統上，人們使用鑰匙、密碼與磁卡等作為身份登入的機制，不過這些的方式都伴隨著遺忘與遺失的風險。為了追求更加人性化與便利性的發展，學者們將目標轉移到人類與生俱來的特徵上，我們稱之為生物特徵。生物特徵具有獨特性、普遍性、便利性以及難以仿造的特性，因此成為熱門的研究主題，而手掌即為其中之一。人類的手掌包含有掌紋、手指紋及手掌幾何等特徵，所隱含的資訊相當豐富，且手掌影像在硬體設備上取得容易。因此本研究透過觀察手掌的特徵，對於掌部特徵做整體的分析與考量，並建立一套既實用又便利的掌紋辨識系統。
本系統透過接觸式與非接觸式兩種輸入平台取得手掌影像，並將手掌特徵分為掌紋、手指紋及手掌幾何等三個部分作探討。掌紋系統經由局部二元化圖樣，萃取具方向性的掌紋特徵；手指紋系統以史托克維爾轉換，建立手指紋理的特徵模型；手掌幾何特徵之辨識系統，即利用手指長、寬、長寬比例、手指面積以及手掌面積等作為特徵參數，接著經過影像模型的特徵比對，得到最後的辨識結果。本系統在CPU時脈為1.6 GHz的AMD Phenom II core 4 P920之個人電腦與Windows7作業系統環境下，以掃描機與數位相機作為輸入裝置，對實驗室13人，左右手掌各取11張影像，經模型比對後，正確辨識率分別可達100%與99.24%。而透過IIT、COEP與HK PolyU所提供的掌紋資料庫，分別各有230、163及500人，其辨識率分別可達到84.35%、92.02%與99.80%。

“Palm-print” possesses a wide range of applications in Chinese chirology. It can construe numerology, foretell divination and determine character of a person. “Palm-print” is also one of the most important information sources for visual examination in traditional Chinese medicine. In the recent years, the advancement of information technology makes people rely heavily on the internet. However, convenience is also accompanied by unavoidable security problems. In order to alleviate this issue, user identification research becomes a global spotlight. In the common life, keys, passwords and magnetic cards are used as login mechanisms, these methods usually tie up with great missing risk. To solve this problem, scientists move focus to the inherent features of human beings and build a much more secure and convenient system by the use of biometric features. These kinds of features are unique, universal, portable, and hard to counterfeit. Biometrics then becomes a popular research topic. Since human palm contains abundant information in palm-print, fingerprint and hand geometry, and its image can be easily acquired using commodity hardware, it is our objective to analyze the properties of the whole palm, and design a practical and convenient palm-print recognition system.
This system uses both scanner and digital camera for contact and non-contact palm image acquisition respectively. A strategy based on palm-print, fingerprint textures and hand geometry is then designed to recognize the correct person. Local binary patterns and Stockwell transform are utilized for the palm-print and fingerprint feature extraction separately. Finger lengths, widths, the ratios between lengths and widths of fingers, fingers and palms areas are used as hand geometry characteristic parameters. Finally, the system compares the feature models of images, and concludes the ultimate user. Under the 1.6 GHz of AMD Phenom II core 4 P920 PC and Windows 7 environment, correct rates of 100% and 99.24% can be obtained using scanner and camera images respectively for a database of 13 Laboratory users. For each user, eleven palm images are captured for the left and the right hand separately. In addition, the system is tested on IIT database of 230 users, COEP database of 163 users and HK PolyU database of 500 users, correct recognition rates of 84.35%, 92.02% and 99.80% can also be achieved respectively.

論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
目錄 v
圖次 viii
表次 xii
第一章 緒論 1
1.1研究動機 1
1.2研究目的與方法 4
1.3論文章節概要 4
第二章 手掌特徵介紹 5
2.1掌形特徵 6
2.2掌紋特徵 8
2.3手指紋特徵 11
第三章 相關文獻 13
3.1掌形辨識 13
3.2掌紋辨識 14
3.3手指紋辨識 16
第四章 影像辨識系統之流程與架構 19
4.1影像辨識系統之流程 19
4.2影像之前置處理 20
4.2.1影像二值化 21
4.2.2去除影像雜訊 24
4.2.3手指之谷點定位 27
4.2.4左右手掌之分類 31
4.2.5擷取手指影像 32
4.2.6擷取手掌紋影像 39
4.2.7手掌紋與手指紋之對比強化 40
4.3手掌的幾何特徵 45
4.3.1幾何特徵萃取 46
4.3.2絕對值距離 47
4.4史托克維爾轉換 48
4.4.1時頻分析 48
4.4.2手指紋特徵萃取 54
4.4.3餘弦相似度 55
4.5局部二元化圖樣 56
4.5.1掌紋特徵萃取 56
4.5.2卡方距離 59
第五章 辨識系統之實作成果與效能評析 60
5.1軟硬體設備與開發平台 60
5.2影像模型建立 61
5.3權重分析 62
5.4系統辨識效能 63
第六章 結論與未來展望 74
參考文獻 75

[1] 張嵐霆(民101年4月12日)。日本國內ATM首度採用無卡式手掌靜脈辨識。iThome。取自http://www.ithome.com.tw/node/73148
[2] A+醫學百科。掌紋醫學。取自http://cht.a-hospital.com/w/掌纹医学#.UyEyTvmSySo
[3] 互動百科（民101年6月9日）。西洋手相學中的幾種手型。取自http://xiangxue.h.baike.com/article-361897.html
[4] 玅開命運。『手相學』掌指形狀。取自http://www.fateopen.com/news/fn.php?d_id=232
[5] 內政部警政署刑事警察局。指紋科學小百科。取自http://www.cib.gov.tw/Science/EncyclopediaDetail/228
[6] 劉靜怡、陳顯武、周桂田、廖福特、吳豪人（民95）。運用生物特徵辨識身分制度之比較研究。臺北市：行政院研究發展考核委員會。
[7] 王晨霞（民99）。王晨霞掌紋診病健康密碼。新北市：源樺。
[8] Lori Reid（民92）。手相學習百科（章敏譯）。臺北市：貓頭鷹。
[9] 黃恆堉（民95）。初學手相，這本最好用。臺北市：知青頻道。
[10] 宮澤美智（民100）。學手相沒這麼難啦！（郭玉梅譯）。臺北市：三悅文化。
[11] 周威仲（民86）。現代手相學-命運的圖像解碼。臺北市：方智。
[12] 王晨霞（民92）。掌紋醫學入門。臺北市：商周。
[13] 劉家村（民94）。生物特徵辨識-手指紋路辨識（碩士論文）。國立中央大學，桃園縣。
[14] Gonzalez Woods（民98）。數位影像處理（繆紹綱譯）。臺北縣：台灣培生教育。
[15] 鍾國亮（民101）。影像處理與電腦視覺。臺北市：東華。
[16] A. McAndrew, J.-H. Wang and C.-S Tseng（民100）。數位影像處理（劉震昌譯）。臺北市：高立圖書。
[17] John Neter（民94）。應用線性迴歸模型(第4版)（陳至安譯）。臺北市：華泰文化。
[18] 管中閔（民93）。統計學：觀念與方法。臺北市：華泰文化。
[19] Anil K. Jain and Nicolae Duta, “Deformable Matching of Hand Shapes for Verification,” IEEE International Conference on Image Processing, pp. 857-861, 1999.
[20] Anil K. Jain, Arun Ross and Sharath Pankanti, “A Prototype Hand Geometry Based Verification System,” Audio and Video-Based Biometric Person Authentication, pp. 166-171, 1999.
[21] Lei Zhang, Zhenhua Guo, Zhou Wang and David Zhang, “Palmprint Verification using Complex Wavelet Transform,” IEEE International Conference on Image Processing, Vol. 2, pp. 417-420, 2007.
[22] Jiwen Lu, Erhu Zhang, Xiaobin Kang, Yanxue Xue and Yajun Chen, “Palmprint Recognition Using Wavelet Decomposition and 2D Principal Component Analysis,” IEEE International Conference on Communications, Circuits and Systems, Vol. 3, pp. 2133-2136, 2006.
[23] Jinyu Guo, Yuqin Liu and Weiqi Yuan, “Palmprint Recognition Based on Phase Congruency and Two-Dimensional Principal Component Aanlysis,” Congress on Image and Signal Processing, Vol. 3, pp. 1527-1530, 2011.
[24] Jifeng Dai and Jie Zhou, “Multifeature-Based High-Resolution Palmprint Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, No. 5, pp. 945-957, 2011.
[25] Yanuar Adhinagara, B. W. Tjokorda Agung and Dayawati Retno Novi, “Implementation of Multimodal Biometrics Recognition System Combined Palm print and Palm Geometry Features,” IEEE International Conference on Electrical Engineering and Informatics, pp. 1-5, 2011.
[26] D. G. Joshi, Y. V. Rao, S. Kar, Valli Kumar and R. Kumar, “Computer Vision Based Approach to Personal Identification Using Finger Crease Pattern,” Pattern Recognition, Vol. 31, No. 1, pp. 15-22, 1998.
[27] Le-qing Zhu and San-yuan Zhang, “Multimodal Biometric Identification System Based on Finger Geometry, Knuckle Print and Palm Print,” Pattern Recognition Letters, Vol. 31, No. 12, pp. 1641-1649, 2010.
[28] Y.Linde, A.Buzo and R.M.Gray, “An Algorithm for Vector Quantizer Design,” IEEE Transactions on Communications, Vol. 28, No. 1, pp. 84-95, 1980.
[29] R. G. Stockwell, L. Mansinha and R. P. Lowe, “Localization of the Complex Spectrum: The S Transform,” IEEE Transactions on Signal Processing, Vol. 44, No. 4, pp. 998-1001, 1996.
[30] J. B. Allen, “Short Term Spectral Analysis, Synthesis, and Modification by Discrete Fourier Transform,” IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. 25, No. 3, pp. 235-238, 1977.
[31] G. S. Badrinath and Phalguni Gupta, “Stockwell Transform Based Palmprint Recognition,” Applied Soft Computing, Vol. 11, No. 7, pp. 4267-4281, 2011.
[32] Timo Ojala, Matti Pietikainen and T. Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 7, pp. 971-987, 2002.
[33] Vu Thi Lan Huong, Dong-Chul Park, Dong-Min Woo and Yunsik Lee, “Centroid Neural Network with Chi Square Distance Measure for Texture Classification,” Proceedings of International Joint Conference on Neural Networks, pp. 1310-1315, 2009.
[34] Timo Ahonen, Abdenour Hadid and Matti Pietikäinen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 12, pp. 2037-2041, 2006.
[35] Zhenhua Guo, Lei Zhang, David Zhang and Xuanqin Mou, “Hierarchical Multiscale LBP for Face and Palmprint Recognition,” IEEE International Conference on Image Processing, pp. 4521-4524, 2010.
[36] Ajay Kumar and Yingbo Zhou, “Human Identification Using Finger Images,” IEEE Transactions on Image Processing, Vol. 21, No. 4, pp. 2228-2244, 2012.
[37] Wei Li, Bob Zhang, Lei Zhang and Jingqi Yan, “Principal Line-Based Alignment Refinement for Palmprint Recognition,” IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, Vol. 42, No. 6, pp. 1491-1499, 2012.
[38] Yang Zhao, Wei Jia, RongXiang Hu, Jie Gui, “Palmprint Identification Using LBP and Different Representations,” IEEE International Conference on Hand-Based Biometrics, pp. 1-5, 2011.
[39] Ajay Kumar, “Incorporating Cohort Information for Reliable Palmprint Authentication,” IEEE Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 583-590, 2008.
[40] David Zhang, Zhenhua Guo, Guangming Lu, Lei Zhang and Wangmeng Zuo, “An Online System of Multi-spectral Palmprint Verification,” IEEE Transactions on Instrumentation and Measurement, Vol. 59, No. 2, pp. 480-490, 2010.
[41] Dong Han, Zhenhua Guo and David Zhang, “Multispectral Palmprint Recognition using wavelet-based Image Fusion,” IEEE International Conference on Signal Processing, pp. 2074-2077, 2008.
[42] David Zhang, Wai-kin Kong, Jane You and Michael Wong, “On-line palmprint identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 9, pp. 1041-1050, 2003.
[43] Zhenhua Guo, David Zhang, Lei Zhang, Wangmeng Zuo and Guangming Lu “Empirical Study of Light Source Selection for Palmprint Recognition”, Pattern Recognition Letters, pp. 120-126, 2010.
[44] The IIT Delhi Touchless Palmprint Database Version 1.0: http://www.comp.polyu.edu.hk/~csajaykr/IITD/Database_Palm.htm
[45] The COEP Palm Print Database: http://www.coep.org.in/index.php?pid=367
[46] The PolyU Multispectral Palmprint Database: http://www4.comp.polyu.edu.hk/~biometrics/MultispectralPalmprint/MSP.htm