臺灣博碩士論文加值系統

由於近十年間，人們對於安全問題的重視，使得以生物辨識為基礎之身份辨識技術的重要性迅速成長。而於多種生物辨識技術中，本論文將深入探討以B樣條曲線為基礎的掌形生物辨識系統。實作一套具有良好辨識率的生份辨識系統，並建立一組適用於系統的手掌影像資料庫，進行實驗檢測。系統架構，包含四個模組：有影像擷取、影像處理、特徵萃取與分類辨識模組。首先，輸入自數位相機擷取之手掌影像，接著由影像前處理模組，利用影像處裡演算法，自手掌影像擷取出所需之掌形影像。特徵萃取模組，以B樣條曲線（B-Spline curves）擬合4根手指(不包含姆指)，將B樣條曲線之控制點（control points）及曲率加上掌形的幾何特徵，作為生物辨識用的特徵資訊。最後，分類辨識模組，利用生物特徵資訊，進行使用著的註冊及辨識的動作。
以實驗室自建的資料庫，總共有100個自願者的手掌影像，共600掌影像，對系統進行測試。本研究利用控制點、曲率及指寬作為特徵，以等錯率（equal error rate）作為標準辨識成功率分別95.55%（128bytes）、85.7%（32bytes）及96.84%（96bytes），最後我們組合此三種特徵，以控制點加指寬作為特徵其辨識成功率可達97.84%（224bytes）。本論文會針對實驗結果進行分析比較，來驗證本系統所提的相關理論，以供後續研究作為參考。

With an increasing emphasis on security, personal authentication based on biometrics has been receiving extensive attention over the past decade. Among many different biometric technologies, this thesis examines hand-shape technique for personal identification and develops a good performance recognition system based on human hand features. It is implemented and tested on VIP-CCL Lab. Hand image database. The proposed system includes four modules: image acquisition, image pre-processing, feature extraction, and recognition modules. First, the system captures a hand image using digital camera, then uses some image processing algorithms to localize the hand-geometry from the hand image via image pre-processing module. In the feature extraction module, we use 4 B-Spline curves to fit with fingers (except thumb) from a single hand image for a single person. Then we store these control points and curvatures of the B-Spline curves as well as other geometry measurements (the width of fingers) of the hand as the features of that person into the database. Finally, the system applies these features for matching in recognition module.
Experimental results show that the system has an encouraging performance on the VIP-CC Lab. Database (including 600 images from 100 classes). The proposed system uses the control points 、the curvatures and the width of fingers to generate the features, we attain the recognition rates up to 95.55%(128bytes)、85.7%(32bytes)and 96.84%(96bytes) (according to equal error rate, EER), respectively. This thesis analyzes the experimented results and verifies the related inferences of the proposed system for providing useful information for further research.

目錄
誌謝 i
論文摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 ix
符號說明 x
第一章 緒論 1
1.1 研究動機 1
1.2 掌形辨識技術之發展與研究 3
1.3 研究目標與方向 4
1.4 論文大綱與組織 5
第二章 基礎影像處理技術 6
2.1 影像強化 6
2.1.1 基本灰階轉換 6
2.1.2 空間域濾波技術 8
2.2 形態學影像處理 10
2.3 邊緣偵測 14
2.4 臨界值法 20
第三章 B樣條原理 22
3.1 B樣條曲線特性 22
3.1.1 B樣條曲線方程與遞推定義 22
3.1.2 B樣條局部性質與特性 25
3.1.3 重節點對B樣條基函數與曲線的影響 27
3.2 B樣條曲線類型 28
3.3 B樣條曲線擬合 31
3.3.1 反算B樣條曲線控制點 31
3.3.2 數據點參數化 31
第四章 基於B樣條曲線之掌形辨識 34
4.1 系統架構 34
4.2 影像擷取模組 35
4.3 影像前處理模組 37
4.4 三次非均勻B樣條曲線 43
4.5 特徵萃取 47
4.6 分類辨識模組 51
第五章 實驗結果 52
5.1 實驗環境 52
5.2 系統效能評估 52
5.3 非均勻三次B樣條曲線之控制點 54
5.4 非均勻三次B樣條曲線之曲率 55
5.5 實驗結果分析與討論 56
第六章 結論與建議 62
6.1 結論 62
6.2 建議研究方向 62
參考文獻 64

參考文獻
[1]J. D. Woodward, “Biometrics: privacy’s foe or privacy’s friend ?”, Proc. of the IEEE, vol. 85, No. 9, pp. 1480-1492, 1997.
[2]S. Nanavati, M. Thieme and R. Nanavati, Biometrics: Identity Verification in a Networked World, John Wiley & Sons, 2002.
[3]“http://www.biometricgroup.com/,” Homepage of International Biometric Group.
[4]A. K. Jain and N. Duta, “Deformable matching of hand shapes for user verification,” ICIP 99 Image Processing, 1999.
[5]R. Sanchez-Reillo, C. Sanchez-Avila and A. Gonzalez-Marcos, “Biometric identification through hand geometry measurements,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, No. 10, pp. 1168-1171, Oct 2000.
[6]R. Sanchez-Reillo, “Hand geometry pattern recognition through gaussian mixture modeling,” Pattern Recognition, vol. 2, pp. 937-940, 2000.
[7]C. C. Han, P. C. Chang and C. C. Hsu, “Personal identification using hand geometry and palm-print,” Proc. of Fourth Asian Conference on Computer Vision(ACCV), pp. 747-752, 2000.
[8]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd Edition, Prentice-Hall, New Jersey, 2002.
[9]G. Amayeh, G. Bebis, A. Erol and M. Nicolescu, “Peg-free hand shape verification using high order zerhike moment,” IEEE Conf. on computer Vision and Pattern Recognition Workshop, pp. 40-40, 2006.
[10]J. R. Parker, Algorithms for Image Processing and Computer Vision, John Wiley & Sons, 1996.
[11]張智星，Matlab程式設計，清蔚科技，新竹市，民國93年。
[12]謬紹剛，數位影像處理-活用Matlab，全華科技圖書，台北市，民國88年。
[13]劉震昌，數位影像處理，新加坡商湯姆生亞洲私人有限公司台灣分公司，台北市，民國94年。
[14]鍾國亮，影像處理與電腦視覺，東華書局，台北市，民國91年。
[15]J. Canny, “A computational approach to edge detection,” IEEE Trans. on Pattern Analysis. and Machine Intelligence., vol. 8, No. 6, pp. 679-698, 1986.
[16]江樂山，以小波轉換與統計矩陣為基礎的掌紋與掌形生物辨識，國立暨南國際大學，碩士論文，民國94年。
[17]“http://www.ibiblio.org/e-notes/Splines/Intro.htm, ”An Interactive Introduction to Splines.
[18]T. Toe and T. V. To, “Curve matching by using B-spline curves,” WSCG International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, pp. 173-176, 2004.
[19]Y. L. Ma, F. Pollick and W. T. Hewitt, “Using B-spline curves for hand recognition,” Proc. of IEEE, International Conference on Pattern Recognition (ICPR), vol. 3, pp. 274-277, 2004.
[20]E. Yörük, E. Konukoglu, B. Sankur and J. Darbon, “Shape-based hand recognition,” IEEE Trans. on Image Process, vol. 15, No. 7, Jul. 2006.
[21]D.-M. Sun and Z.-D. Qiu, “Automated hand shape verification using HMM,” Proc. of IEEE, International Conference on Signal Processing (ICSP), vol. 3 pp. 2274-2277, 2004.
[22]W. Xiong, K. A. Toh, W. Y. Yau and X. Jiang, “Model-guided deformable hand shape recognition without positioning aids,” Pattern Recognition, vol. 38, pp.1651-1664, 2005.
[23]S. Mallat and S. Zhong, “Characterization of signals from multiscale edge,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.14, No. 7, pp. 710-732, Jul. 1992.
[24]Y. Y. Tang, et al., Wavelet Theory and Its Application to Pattern Recognition, World Scientific, Singapore, 2000.
[25]S. Theodoridis and K. Koutroumbas, Pattern Recognition, 3nd Edition, Academic Press, London, 2006.
[26]R. O. Duda, P. E. Hart and D. G. Stork, Pattern Classification, 2nd Edition, A Wiley-Interscience Publication, 2001.
[27]R. Goldenthal and M. Bercovier, “Spline curve approximation and design by optimal control over the knots using genetic algorithms,” International Congress on Evolutionary Methods for Design, Optimization and Control with Applications to Industrial Problems, 2003.
[28]F. L. Kitson, “An algorithm for curve and surface fitting using B-splines,” Proc. of IEEE,International Conference on Acoustics, Speech, and Processing (ICASSP), vol. 2, pp. 1207-1210, 1989.
[29]G. Chen and Y. H. H. Yang, “Edge detection by Regularized Cubic B-Spline Fitting,” IEEE Trans. on System, Man and Cybernetics, vol. 25, pp. 636-643, 1995.
[30]劉景隆，斷層影像之B-Spline參數曲線與曲面重建研究，國立中央大學，碩士論文，民國92年。
[31]吳新逸，空間中具曲率連續的B-Spline封閉曲線建構，國立成功大學，碩士論文，民國93年。
[32]施法中，計算機輔助幾何設計與非均勻有理B樣條，新華科技，北京，1994。
[33]C. De Boor, A practical guide to splines, Berlin: Spring, 1978.