基于自动指纹识别系统的图像增强算法研究-计算机科学与技术专业论文.docx

IMAGE IMAGE ENHANCEMENT RESEARCH BASED oN AUTOMTIC FINGERPlUNT IDENTIFICATION SYSTEM ABSTRACT In today’S complex，geographically mobile and increasingly electronically inter-connected information society,accurate personal identification is becoming more and more important and difficult．The aim and object of this paper is to improve the equality of poor fingerprint from optical sensor,especially the OVer or under inking or incomplete images． This paper mainly discusses follows： 1．Discuss and summarize the method,the principle,the main realizing method, of Automatic Fingerprint Identification System．A comprehensive preview is presented on fingerprint image preprocessing on the state of the core algorithm related t0AFIS． 2．The paper design an automatic fingerprint identification system,included test and identification module．Binarizatiort,thinning,minutia detection module ale designed using exiting method．The enhancement module is the core content．The test result has proved identification rate improved highly after image enhancement． 3．The segmentation of fingerprint alea from image background is one of the important module in image preprocessing．Based the position difference between finger and SenSOr)the huge average of four comer is used as segmentation threshold． The test result has proved that this method can segment the fingerprint image from background quickly． 4．Gabor-based fingerprint image enhanced algorithm in wavelet domain wag proposed based on the idea that the dry and wet call be looked as high—frequency disturbance．The using above estimated ridge orientation,each direction coefficient images Were enhanced based on Gabor function and further reconstruction． KEY KEY WORDS：biometric recognition，automatic fingerprint identification system，wavelet transform,Gabor function 独创性(或创新性)声明本人声明所呈交的论文是本人在导师指导下进行的研究工作及取得的 独创性(或创新性)声明 本人声明所呈交的论文是本人在导师指导下进行的研究工作及取得的 研究成果。尽我所知，除了文中特别加以标注和致谢中所罗列的内容以外， 论文中不包含其他人已经发表或撰写过的研究成果，也不包含为获得北京邮 电大学或其他教育机构的学位或证书而使用过的材料。与我一同工作的同志 对本