透過您的圖書館登入
IP:3.138.33.178
  • 學位論文

特徵點定位之指紋驗證系統

Feature Points Fingerprint Verification System

指導教授 : 李信興
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


生物測定學是利用生物自身的特徵來驗證使用者身份,而自身的特徵包括了聲音、人臉、指紋、虹膜…等。在這些特徵驗證方法中,指紋特徵是最常被拿來研究的方法,因為它除了有生物特徵中唯一不變的特性外,在功能及便利性上比其他驗證方法更實用。 在本篇的研究中,我們修改已有的演算法,以C++程式語言設計身份驗證系統,利用電容式或光學式指紋擷取器擷取指紋圖樣,擷取之指紋圖樣先做前置處理,再找出擷取指紋的核心點,以核心點中心把指紋圖樣劃分為許多區塊,每一個區塊大小為 。在每一個區塊中找出特徵點後,以核心點為中心,利用座標定位這些特徵點。利用這些資訊作為執行身份驗證的依據,可以改善因特徵點太過相近或是因指紋圖形不完整而造成驗證錯誤的情形。

關鍵字

生物測定學 指紋 特徵

並列摘要


Biometrics is using biological features to verify the user's own identity, and these features include voice, face, fingerprint, iris ... and so on. The fingerprint feature is the most commonly used research method in personal verification. In addition to the fingerprint keeps the same during a long period of time, the implementation of the function is more convenience and more practical than other verification methods. In this study, we modify the existing algorithms to designed a verification system using C + + programming language. We use the capacitive or optical fingerprint capture devices to capture fingerprint image. The captured fingerprint image first will do pre-processing, and then find the core point of the image. Using this core point center the image is divided into blocks, the size of each block is 7 x 7 pixels. Identify features in each block and locate all features in the image by using the core point as the reference points. Use this information as a basis for the implementation of ID verification can improve the drawback that feature points are too close together or the fingerprint image is incomplete to avoid verification errors.

並列關鍵字

Biometric Fingerprint Feature

參考文獻


參考文獻
1.李宗翰,「即時指紋辨識演算法」,輔仁大學資訊工程系碩士論文,民國九十年六月。
2.陳俊良,「有效的指紋前處理及分類」,淡江大學資工所碩士論文,民國九十年六月。
3.黃逸泓,「具影像旋轉不變性之指紋驗證系統」,清雲科技大學電機工程研究所碩士
論文,民國九十五年六月。

延伸閱讀