改良式多級指紋比對演算法指紋辨識晶片設計

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Thesis > Item 987654321/35657

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/35657

Title:	改良式多級指紋比對演算法指紋辨識晶片設計
Other Titles:	Fingerprint recognition chip design via the improved multi-level fingerprint verification algorithm
Authors:	蕭志豪;Hsiao, Chih-hao
Contributors:	淡江大學電機工程學系碩士班黃聰亮;Huang, Tsong-liang
Keywords:	指紋;辨識;比對;Fingerprint;Identification;Verification
Date:	2006
Issue Date:	2010-01-11 06:58:02 (UTC+8)
Abstract:	近年來，資料安全的防護與門禁管理系統的重要性越來越受到重視，傳統的密碼保密已漸漸的被淘汰，取而代之的，生物辨識技術逐漸被運用在增強系統保密性，現存的生物辨識技術主要有，虹膜、聲音、容貌、指紋，其中指紋最常為人所使用，指紋辨識的優點：方便、精確，不像虹膜辨識必須接觸眼睛容易傳染疾病；聲音容易因情緒而變調；容貌因胖瘦而有改變，且指紋具有唯一性，故指紋已被廣泛的運用在資料保全系統上。大部分的指紋辨識系統，都是先將指紋影像經過正規化、濾除雜訊、取指紋流向、流向濾波、細線化、偵測奇異點與特徵點，建檔指紋的奇異點及紋線的端點、叉點的分佈位置作為爾後比對的依據。但遇上龐大的指紋資料庫時，整體的比對效率是最常為人所詬病的，故本論文提出一種新的比對流程來增進比對單元的效率，在一連串有效的影像前處理步驟之後，我們省略細線化直接做特徵擷取，並經由其核心點附近的流向對其做快速的指紋分類建檔，在比對單元方面，會先經由其分類建檔的資料庫來比對，將會大大的改善整個比對單元的辨識效率，在演算法確立且軟體模擬成功之後，我們試著將提出的指紋影像辨識流程硬體化，利用數位訊號處理器(DSP)來實現個人身份辨識系統。 Nowadays, the importance of the information protection and the entrance guard control system have be attached importance to the people. Traditional secret maintaining methods like setting up passwords are eliminated gradually, and the biometric verification technique is to take it over. Biometric verification technique is applied on enhancing the system of maintaining secrecy gradually. Biometric verification techniques which are available now are mainly as follows : iris, voice, appearance, and fingerprint. On account of its precision and convenience, fingerprint is the most wildly-used technique; whereas iris verification may cause transmitted disease because of the contact with eyes, voice may inflect for emotion, appearance maybe changed as weight. What’s more, fingerprints possess exclusive character, therefore, fingerprints have been using on information security system generally. Most of the fingerprint verification systems would including normalization, noise filter, calculate fingerprint flow direction, flow filter, thinning, detect the positions of the singular points and minutiae, as a basis for the later verification. However, the verification efficiency of a huge recognition database is often censorable when encountering. Therefore, this thesis brings up a new verification process to promote the efficiency of verification. After a series of valid image preprocessing procedure, we detect the minutiae without Thinning, and use the flow nearing the core point to classify the fingerprints speedily. As for the verification unit, the new verification process would verify the fingerprints of its classified database first, which will improve the verification efficiency of the whole verification unit. After the confirmation of algorithm and the success of simulation, we try to realize the procedure of fingerprint image verification by hardware, using DSP to achieve personal identity verification system.
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Thesis

Files in This Item:

File	Size	Format
	0Kb	Unknown	296	View/Open

Loading...