臺灣博碩士論文加值系統

　　生物特徵識別（Biometric identification）是目前熱門研究的主題之一，其中有一部份運用手部的特徵像是指紋（Fingerprint）、手的幾何（Hand geometry）、掌紋（Palmprint）與掌背血管（Vein of Palm-dorsum）等。其中，掌紋的特徵由主線（Principal lines）、皺褶（Wrinkes）與脊（ridges）所組成，而人類的整根手指上的紋路與手掌上的紋路亦有近似的三項特徵結構，即主線、皺褶、脊。因此，本論文嘗試取出手掌影像中的小指、無名指、中指和食指共四根手指上中央部位的長方形手指紋路（Finger Crease Patterns）當作興趣區域（Regions of Interest, ROI），再以小波轉換（Wavelet transformation）來取得小波能量特徵（Wavelet Energy Features, WEF），最後藉由倒傳遞類神經網路（Back propagation neural network, BPNN）來作比對。

Biometric identification is one of the popular research fields recently. Some of those use the features of hands like fingerprint, hand geometry, palmprint and vein of palm-dorsum. Palmprint has several features, which include principal lines, wrinkles and ridges. Also, the whole stick of finger is full of the similar structure of features (i.e. principal lines, wrinkles and ridges). In this dissertation, a new approach is introduced. In the image of the palm, we try to use Finger Crease Patterns on the central area of four fingers (little finger, ring finger, middle finger and forefinger) as regions of Interest (ROI). Next we computed the wavelet energy feature (WEF) through the use of wavelet transform. Finally, the back propagation neural network (BPNN) is applied for verification.

目錄
目錄 VII
圖表目錄 IX
1 第一章 緒論 1
1.1 研究動機 1
1.2 相關文獻 3
1.2.1手的幾何 3
1.2.2掌紋 5
1.2.3手指紋路 6
1.2.4多重模式 7
2 第二章 小波理論及倒傳遞類神經網路 9
2.1 小波理論 9
2.1.1 一維Haar小波轉換 9
2.1.2 二維Haar小波轉換 12
2.1.3 以濾波器的觀點來看小波轉換 13
2.2 倒傳遞類神經網路[20] 14
2.2.1倒傳遞演算法[20] 15
3 第三章 研究方法 18
3.1 前處理階段 18
3.1.1 影像二值化 19
3.1.2 侵蝕與擴張 21
3.1.3 邊緣描繪 23
3.1.4 手指端點定位 26
3.1.4.1 利用視窗結構定位手指端點 26
3.1.4.2 利用手掌輪廓與定點的距離分佈定位手指端點 28
3.1.5 擷取手指影像 34
3.1.6 手指節定位 36
3.1.7擷取手指內部的ROI影像 42
3.2 WEF特徵擷取階段 43
4 第四章 實驗設計與結果 45
4.1 實驗設計 45
4.2 WEF辨識結果 47
4.3 WEF的不同階數及頻帶辨識結果 48
4.4 不同的手指組合辨識結果 50
4.5 利用倒傳遞類神經網路辨識結果 51
4.6 其它相關文獻參考 52
5 第五章 結論與展望 53
6 參考文獻 54

6參考文獻
[1]E. Fix and J. L. Hodges, “Discriminatory analysis: Nonparametric discrimination: Consistency properties,” Tech. Rep. Project 21-49-004, Report Number 4, USAF School of Aviation Medicine, Randolf Field, Texas, 1951.
[2]C. C. Han, H. L. Cheng, K. C. Fan and C. L. Lin ,"Personal authentication using palmprint features," Pattern Recognition, vol. 36, pp. 371-381, 2003.
[3]A. K. Jain, A. Ross and S. Pankanti, “A Prototype Hand Geometry-based Verification System,” in Proceedings of the 2nd International Conference on Audio- and Video-based Personal Authentication (AVBPA), Washington D.C., Mar. 1999.
[4]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, pp.15-22, 1998.
[5]A. Kumar, D. C. M. Wong, H. C. Shen and A. K. Jain, “Personal Verification Using Palmprint and Hand Geometry Biometric,” in Proceedings of the 4th International Conference on AVBPA, Guildford, U. K., Jun. 2003.
[6]C. L. Lin, “Biometric Verification Using Palmprints and Vein-patterns of Palm-dorsum”, Ph. D. Dissertation, NCU, Taiwan, ROC, Nov. 2003.
[7]G. Lawton, “Biometrics: A New Era in Security,” IEEE Computer, vol. 31, pp. 16-18, Aug. 1998.
[8]H.M.El-Bolok, M.I.El-Adawy, M.E.AbouEl-Wafa and R.I.Mubarak, “Person Identification Through Hand Geometry Measurements,” Journal of Engineering Sciences, Assiut University, vol. 32, No. 4, pp. 1661-1672, Sep. 2004.
[9]N. Pavešić, S. Ribarić and D. Ribarić, "Personal authentication using hand-geometry and palmprint features: the state of the art," presented at the workshop Biometrics - Challenges arising from theory to practice (BCTP), at the conference International conference on pattern recognition (ICPR) 2004.
[10]O. Rioul, M.Vetterli, “Wavelets and signal processing,” IEEE Signal Processing Magazine, vol. 8, no. 4, pp. 14-38, Oct. 1991.
[11]A. Ross, A. Jain and J. Z. Qian, “Information Fusion in Biometrics,” in Proceedings of 3rd International Conference on AVBPA, Guildford, U. K., Jun. 2001.
[12]E. J. Stollnitz, T. D. DeRose, D. H. Salesin, “Wavelets for Computer Graphics: A Primer Part1,” IEEE Computer Graphics and Applications, vol. 15, no. 3, pp. 76-84, May. 1995.
[13]X. Q. Wu, K. Q. Wang, D. Zhang: “Wavelet based palmprint recognition”, in Proceedings of the 1st International Conference on Machine Learning and Cybernetics, Beijing, 4-5, Nov. 2002.
[14]J. You, W. Li and D. Zhang: “Hierarchical palmprint identification via multiple feature extraction,” Pattern Recognition, vol. 35, pp. 847-859, Apr. 2002.
[15]D. Zhang and W. Shu, "Two Novel Characteristics in Palmprint Verification: Datum Point Invariance and Line Feature Matching," Pattern Recognition, vol. 32, pp.691-702, 1999.
[16]J. H. McClellan, R. W. Schafer and M. A. Yoder, Signal Processing First. Prentice-Hall, 2003.
[17]M. Sonka, V. Hlavac and R. Boyle, Image Processing, Analysis, and Machine Vision. PWS Publisher, 1999.
[18]N. Efford, Digital Image Processing: A Practical Introduction using Java. Addison-Wesley Publisher, 2000.
[19]International Biometric Group. (n.d.). [Online]. Biometrics Reports and Research. Available:http://www.biometricgroup.com/reports/public/reports_and_research.htm Jul. 14,2005 [date accessed].
[20]蘇木春、張孝德: ”機器學習:類神經網路、模糊系統以及基因演算法則 二版”, 全華科技圖書 民88。