跳到主要內容

臺灣博碩士論文加值系統

(44.210.77.73) 您好!臺灣時間:2024/02/28 05:05
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:楊長暻
研究生(外文):brianyang
論文名稱:傅立葉轉換於虹膜辨識之應用
論文名稱(外文):The application of Fourier transform in iris recognition
指導教授:許新添
指導教授(外文):Sheu,Hsin-Teng
學位類別:碩士
校院名稱:國立臺灣科技大學
系所名稱:電機工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2001
畢業學年度:89
語文別:中文
論文頁數:71
中文關鍵詞:生物辨識系統虹膜辨識機器視覺影像處理影像分割圖形識別
外文關鍵詞:biometricsirisrecognitionFourier transform
相關次數:
  • 被引用被引用:0
  • 點閱點閱:771
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
生物識別系統(biometric recognition system)目前廣泛地應用在個人身分認證上,如門禁管制、犯罪認證、金融業務、身分辨識等等,皆是屬於生物辨識系統之範圍。利用人類生理特徵進行個人身份的比對,具有較高的安全性。針對個人生理特性的辨識系統包括人臉(face)、虹膜(iris)、視網膜(retina)、指紋(fingerprint)、手紋(hand texture)、手掌形(hand geometric)、手寫簽名(signature)等等。
由文獻指出每一個人的虹膜皆具有獨特的特徵,並具有長久不變的性質,因此相當合適作為辨識的基礎,虹膜辨識的特性除了上述的性質外,最大的優點在於仿冒者不易偽造,基於上述特性,虹膜辨識確實是生物辨識中具有發展性的一門學問。於1993年,John Daugman 應用Two-Dimensional Gabor filter發展出第一套虹膜辨識系統,1994年,Wides應用Laplacian-Parymid為識別方法之辨識系統,1997年,W.W.Boles應用1-D Wavelet transform為識別方法之辨識系統,此三組系統皆已有產品上市。
本論文首先著手於研究Two-Dimensional Gabor filter與Laplacian-Parymid兩組虹膜辨識系統,此兩組系統皆是以轉換法的方法表示虹膜影像,有鑑於此,本論文提出一套建構於虹膜特徵的辨識系統。
仔細觀察虹膜影像,虹膜具有囊狀及線狀等明顯的特徵,但由於虹膜的取像受到亮度並不均勻及鏡頭對焦的距離的影響,取出特徵並不容易,因此先利用低通濾波器將雜訊去除後,應用Sobel運算子找出虹膜之特徵區域,接著利用傅立葉轉換以弧形的方式將虹膜的特徵影像編碼,最後以特徵碼的相對距離完成圖型匹配(pattern match)與判斷(decision)。
關鍵字:生物辨識系統、虹膜辨識、機器視覺、影像處理、影像分割、圖型識別。

Biometric recognition system has been in widespread use to identify a person in many applications such as access control, prison management, security application, financial services authentication, personnel management, and areas where the recognition relies on personal characteristics to achieve high safety. The biometric recognition includes facial features, iris, retina, hand texture, hand geometric, and signature.
The characteristic of iris is that it is unique and stable over time, and therefore positively distinguishing one from another. Besides, iris has physiological characteristics that can be exploited to insure that reproductions of human iris cannot be used to fool the system. Therefore, iris recognition technique is becoming a growing area in biometric recognition system since 1993.
This thesis begins to study iris recognition techniques based on 2-D Gabor filter and Laplacian Pyramid. Since an iris image contains multiple fibers, furrows, coronas, crypts, serpentine, and striations, and factors such as illumination and focusing of camera lens in iris image acquisition hinders one from making a clear picture of the characteristics of an iris, we apply low pass filter to reduce noise, followed by edge enhancement procedure before finding of an iris. Conversion of an iris image into characteristic code is achieved by utilizing Fourier transform in arc mode. Pattern match is determined by relative distance between characteristic codes. Experiments show excellent recognition rate using the iris image from six students in our lab.
Keyword: biometrics, iris, recognition, Fourier transform.

第一章 緒論1
1.1 前言1
1.2 虹膜辨識系統架構2
1.3 研究方向2
1.4 論文大綱3
第二章 虹膜影像的擷取與分割4
2.1 人眼影像的擷取4
2.2 虹膜影像分割6
2.3 實驗結果與討論10
第三章 建立於2-D Gabor Filters之虹膜辨識系統13
3.1 Two-Dimensional Gabor filters13
3.2 Doubly Dimensionless Projected Polar Coordinate System 15
3.3 虹膜碼的建立16
3.4 虹膜碼的比對與決選17
3.5 實驗結果與討論18
第四章 建立於Laplacian-Pyramid之虹膜辨識系統21
4.1 Laplacian of Gaussian21
4.2 應用Laplacian-Pyramid表是虹膜影像22
4.3 Laplacian-Pyramid之比對24
4.4 實驗結果與討論26
第五章 以虹膜特徵為基礎之虹膜辨識系統34
5.1 虹膜特徵之取出34
5.2 虹膜特徵的編碼37
5.3 虹膜特徵碼之比對40
5.4 實驗結果與討論40
第六章 結論及未來研究方向56

[1] Daugman, J.G., “High confidence visual recognition of persons by a test of statistical independence” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 11, November 1993.
[2] Daugman, J.G., “High confidence recognition of persons by rapid video of iris texture” IEE Trans. European Convention on Security and Detection, no. 408, May 1995.
[3] Daugman, J.G., “Complete discrete 2-D Gabor transforms by neural network for image analysis and compression” IEEE Trans on Acoustic, Speech, and Signal Processing. vol. 36, no. 7, July 1995.
[4] William, Gerald O., “Iris recognition technology”, IEEE AES System Magazine, April 1997.
[5] Wildes, R. P., “Iris recognition: an emerge biometric technology”, Proceedings of the IEEE, vol. 85, no.9, September 1997.
[6] Wildes, R. P., J. C. Asmuth, G. L. Green, S. C. Hsu, R. J. Kolczynski, J. R. Matey, E. McBride. “A system of automated iris recognition”, Proceedings of the IEEE 1994.
[7] Aiazzi, Bruno, Luciano Alparone, Stefano Baronti, and Giorgio Borri, “Pyramid based multiresolution adaptive filters for additive and multiplicative image noise”, IEEE Transactions on Circuits and System-Ⅱ:Analog and Digital Signal Processing, vol. 45, no. 8, August 1998.
[8] Boles, W. W., “A security system based on human iris identification” 1997 First Internation Conference on Knowledge-Base Intelligent Electronic System, pp.21-23 May 1997, Adelaide Australia.
[9] Jain, Ramesh, Rangachar Kasturi, Brian G. Schunck, Machine Vision, McGraw Hills, 1995.
[10] Gonzalez, Rafael C., Richard E. Woods, Digital Image Processing, Addison Wesley, 1966.
[11] Miller, B., “Vital Signs of Identity”, IEEE Spectrum, pp. 22-30, Feb 1994.
[12] Phillips, P. Jonathon, Alvin Martin, C. L. Wilson, Mark Przybocki, “An introduction to evaluating biometric system”, IEEE Computer, pp. 56- 63, 2000
[13] Berggren, L., “Iridology: a critical review”, Acta Ophthalmoligica, vol. 63, pp. 1-8, 1985.
[14] 繆紹綱, 數位影像處理─活用Matlab, 全華科技, 1999.
[15] 張智星, Matlab程式設計與應用, 清蔚科技, 2000.
[16] 連國珍, 數位影像處理, 儒林(1996).
[17] 余清華, Matlab精要, 全華科技, 1999.
[18] 吳成柯, 戴善榮, 程湘君, 雲立實, 數位影像處理, 儒林, 1996.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊