Please use this identifier to cite or link to this item:
標題: 數位信號處理器應用於指紋辨識之實作
The Implementation of Fingerprint Recognition System Using Digital Signal Processor
作者: 莊文維
Chuang, Wen-Wei
關鍵字: fingerprint recognition;指紋辨識;Gabor filter;TI TMS320C6711 DSK;Euclidean distance;FPC1010 fingerprint sensor daughter card;賈伯濾波器;TI TMS320C6711 DSK;歐基里德距離;FPC1010指紋感測子卡
出版社: 電機工程學系所
引用: [1]Richard Zunkel, “Biometrics and Border Control”, Security Technology & Design,May 1995 [2]D.Maio and D.Maltoni, “Direct gray-scale minutiae detection in fingerprints”, IEEE Trans.Pattern Anal. Machine Intell., Vol.19, pp.27-40, Jan 1997 [3]Anil K. Jain, Sharath Pankanti, Lin Hong and Ruud Bolle, “An Identity-Authentication System Using Fingerprints”, Proceedings of IEEE,Vol.85, NO.9, September 1997 [4]A. K. Hrechak and J. A. McHugh, “Automated fingerprints Recognition using structural mathing” , Patt.Recognit., Vol.23, pp.893-904, 1990 [5]Jain A. K., Hong L., and Bolle R., 1997, “On-Line Fingerprint Verification”, IEEE Trans.Pattern Anal.And Machine., Vol.19, No.4, pp.302-314 [6]Anil K.Jain ,Salil Prabhakar and Lin Hong, “A Multichannel Approach to Fingerprint Classification”, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol.21, NO.4, APRIL 1999 [7]A.Senior, “A Hidden Markov Model Fingerprint Classifier”, Proc. Asilomar Conf.Signals, Systems and Computers, pp.306-310, 1997 [8]Lin Hong ,Yifei Wan, and Anil Jain, “Fingerprint Image Enhancement : Algorithm and Performance Evaluation”, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , Vol.20, NO.8, AUGUST 1998 [9]H.C.Lee and R.E.Gaensslen, Edd., Advances in Fingerprint Technology, New York : Elsevier, 1991 [10]Kass M. and Witkin A., 1987, “Analyzing oriented pattern”, Computer Vision, Graphics and Image Processing, Vol.37, pp.362-385 [11]Prabhakar S., “Fingerprint Classification and Matching Using A Filterbank”, pp.88-102, 2001 [12]Anil K. Jain, Salil Prabhakar, Lin Hong, and Sharath Pankanti “Filterbank-Based Fingerprint Matching”, IEEE TRANS. IMAGE PROCESSING, VOL.9, NO.5, MAY 2000 [13]TAN Tai-Zhe, NING Xin-Bao, YIN Yi-Long, ZHAN Xiao-Si, CHEN Yun, “A Method for Singularity Detection in Fingerprint Image”, 2003 Journal of Software 軟件學報 Vol.14, NO.6 [14]Asker M. Bazen and Sabih H. Gerez, “Systematic Methods for the Computation of the directional Fields and Singular Points of Fingerprints”, IEEE TRANS.ON PATTERN ANALYSIS AND MACHINE IN TELLIGENCE, VOL.24, NO.7, JULY 2002 [15]Rao A. R., A Taxonomy for Texture Description and Identification, New York:Springer-Verlag, 1990 [16]李志仁, 蓋伯函數在指紋表示、強化、驗證及辨識的應用, 國立臺灣大學電機工程研究所博士論文 [17]Miao-li WEN, Yan LIANG, Quan PAN, Hong-cai ZHANG, “A Gabor Filter Based Fingerprint Enhancement Algorithm in Wavelet Domain”, IEEE Intwenational Symposium on Volume 2, 12-14 Oct. 2005 Page(s):1468 – 1471 [18]Lifeng Liu, Tianzi Jiang, Jianwei Yang, and Chaozhe Zhu, “Fingerprint Registration by Maximization of Mutual Information”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 15, NO. 5, MAY 2006 [19]Lifeng Sha, Feng Zhao, and Xiaoou Tang, “Fingerprint Matching Using Minutiae and Interpolation-based Square Tessellation Fingercode”, IEEE International Conference on Volume 2, 11-14 Sept. 2005 Page(s):II - 41-4 [20]王逸如、陳信宏, 數位信號處理的新利器TMS320C6X, 全華出版 [21]Rulph Chassaing, DSP Applications Using C and the TMS320C6X DSK, JOHN WILEY & SONS,INC.
利用生物特徵當作辨識的方法有很多,例如:指紋辨識、語音辨識及人臉辨識等等。由於指紋辨識具有唯一性、不變性及普遍性三種特性,所以指紋辨識是最為廣泛使用的技術。指紋辨識系統主要分成三個主要的步驟:影像前處理、特徵擷取和特徵比對。在前處理後,利用賈伯濾波器得到指紋特徵,在比對時,只要輸入指紋特徵與資料庫做比對,並算出差異量。我們所使用的是TI TMS320C6711 DSK(DSP Starter Kit)並且加上FPC1010指紋感測子卡,來進行指紋的擷取與比對,利用歐基里德距離來比對指紋,若小於所設定的門檻值,即為通過;若大於所設定的門檻值,則顯示比對失敗或無此人資料。

There are many biometric features that can be adopted for identification, such as fingerprints, voices and face images. Since fingerprints have the characteristics of uniqueness, stability, and universality, fingerprint recognition has become a popular biometric identification approach. There are three stages in a fingerprint recognition system: image preprocessing, feature extraction, and feature matching. After preprocessing, the feature vector of the fingerprints can be calculated by using the Gabor filters. In the matching process, we compare the input fingerprint features with those in the database and the Euclidean differences between them are used as the recognition criterion. If the smallest distance is less than a pre-selected threshold, the input will be classified into the class with the smallest distance; otherwise it will be rejected. In the experiments, we use the TI TMS320C6711 DSK(DSP Starter Kit) and the FPC1010 fingerprint daughter card to acquire and classify the fingerprints.
其他識別: U0005-1807200619160100
Appears in Collections:電機工程學系所

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.