首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于平滑滤波与最小二乘支持向量机的指纹图像识别研究
引用本文:宋召青,程子君,郑苏.基于平滑滤波与最小二乘支持向量机的指纹图像识别研究[J].海军航空工程学院学报,2010,25(2):172-176, 180.
作者姓名:宋召青  程子君  郑苏
作者单位:1. 海军航空工程学院控制工程系,山东,烟台,264001
2. 海军驻426厂军事代表室,辽宁,大连,115005
3. 海军航空工程学院研究生管理大队,山东,烟台,264001
摘    要:平滑滤波能抑制或消除噪声,获得高质量的图像。建立了完整的指纹识别系统,通过预处理、特征提取和分类识别3个过程,实现了指纹的分类识别;研究了预处理过程中的滤波增强方法,比较了邻域平均、高斯平滑和中值滤波的处理效果;在识别阶段采用最小二乘支持向量机,进行指纹识别实验,并对实验结果进行了比较。

关 键 词:平滑滤波  特征提取  最小二乘支持向量机  指纹识别

Based on Smooth Filter and Least Square Support Vector Machine
SONG Zhao-qing,CHENG Zi-jun and ZHENG Su.Based on Smooth Filter and Least Square Support Vector Machine[J].Journal of Naval Aeronautical Engineering Institute,2010,25(2):172-176, 180.
Authors:SONG Zhao-qing  CHENG Zi-jun and ZHENG Su
Institution:1. Naval Aeronautical and Astronautical University a. Department of Control Engineering; b. Graduate Students' Bridge, Yantai Shandong 264001, China; Military Representatives Office of Navy in NO. 426 Factory, Dalian Liaoning 115005 )
Abstract:Smooth filter can restrain or eliminate noise; high quality images can be got. An integrative system of fingerprint recognition was built up, and fingerprint recognition was carried out through preprocessing, characteristic extraction, classification and recognition. Methods of filters enhancement during preprocessing were studied, and the processing effect of neighbouring area average, Gauss flatness and median filter were intercompared. Fingerprint recognition experiments were carried out, and Least Square Support Vector Machine was adopted during recognition. The results were intercompared.
Keywords:smooth filter  characteristic extraction  Least Square Support Vector Machine  fingerprint recognition
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《海军航空工程学院学报》浏览原始摘要信息
点击此处可从《海军航空工程学院学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号