基于微机的自动指纹识别技术的研究-控制理论与控制工程专业论文.docx

基于微机的自动指纹识别技术的研究Abstract 基于微机的自动指纹识别技术的研究 Abstract Biometrics recognition technique，which is represented by fingerprint recognition．will be used more and more widely in many fields．Eventually it will be an indispensable part ofour daily life．Therefore，studies on the theory and application offingerprint recognition have significant meanings． Based on plenty of papers，this dissertation makes some research on common fingerprint recognition algorithms． The main points ofthis dissertation are as follows： 1．Algorithms on fingerprint preprocessing are fimt studied in unit 3 Point direction image is acquired by using discrete direction method，then block image is acquired．Fingerprint image can be filtered by a filter,which is changed by direction．Then the gray image is changed to binary image with a local self-adapted binary algorithm．In the part of thinning algorithm，，a specially designed two‘pass sequential iterative thinning algorithm helps to acquire high quality skeleton of fingerprints．After a fingerprint image thinned，we introduce an approach in which pixels on fmgerprint ridges can be traced．Based on the approach，all algorithm to remove pseudo-structures from a thinned fingerprint image is introduced．It is found that pseudo-structures can be accurately and totally removed，and the processing speed is high． 2，Algorithms on fingerprint feature extraction are studied in unit 5， Minutiae can be extracted using ridge-tracing approach． 3．In unite 5．Algorithms on fingerprint matching are studied In minutiae alignment process，we take the algorithm presented by Xiping Luo et a1．HoweveL in minutiae matching process，the algorithm presented by Jain et al is introduced． It is found that this algorithm can solve the problem of reference point pair selection with low computational COSt,and have strange robust ability to nonlinear deformation between fingerprint images． Keyword：Fingerprint recognition，preprocessing，ridge tracing， feature extraction，matching 2 基于微机的自动指纹识别技术的研究第一章序论 基