计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (3): 223-225.

• 工程与应用 • 上一篇    下一篇

指纹图像预处理中的关键技术研究

吴健辉1,2,许朝侠3,杨坤涛2,张国云1   

  1. 1.湖南理工学院 物理与电子信息系,湖南 岳阳 414006
    2.华中科技大学 光电子科学与工程学院,武汉 430074
    3.郑州牧业工程高等专科学校 信息工程系,郑州 450011
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-01-21 发布日期:2008-01-21
  • 通讯作者: 吴健辉

Study of essential technology for fingerprint image pre-processing

WU Jian-hui1,2,XU Chao-xia3,YANG Kun-tao2,ZHANG Guo-yun1   

  1. 1.Dept. of Physics & Electronics Information,Hunan Institute of Science & Technology,Yueyang,Hunan 414006,China
    2.School of Optoelectronics Science & Engineering,Huazhong University of Science & Technology,Wuhan 430074,China
    3.Department of Information Engineering,Zhengzhou College of Animal Husbandry Engineering,Zhengzhou 450011,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-01-21 Published:2008-01-21
  • Contact: WU Jian-hui

摘要: 指纹图像的预处理在计算机指纹自动识别系统(AFIS)中有着非常重要的作用,直接制约着系统的识别率和识别速度。指纹图像预处理通常包含图像的分割、去噪、增强、二值化和细化等。在总结现有常用预处理算法的基础上,通过实验对预处理中的三个关键算法即指纹图像的增强、二值化和细化进行了详细地研究,根据指纹图像的特点提出了一些有效的改进算法,实验结果显示这些改进的算法对指纹图像的处理效果明显,可以很好地提高指纹图像的质量,为后继处理打下良好基础。

关键词: 指纹识别, 图像增强, 二值化, 细化, 改进算法

Abstract: The pre-processing of the fingerprint image has the very important using in computer Automated Fingerprint Identification System(AFIS);it is directly restricting the system recognition rate and speed.The pre-processing of the fingerprint image commonly include algorithms about image segmenting,removed noise,enhanced,binarization and thinning.Based on the often using algorithms,the author studies the three essential technologies about image enhanced,binarization and thinning on the pre-processing method through experiment.Put forward some effective improved algorithms from the fingerprint image characteristic.The result of experiment shows these improved algorithms have the evidence effect for fingerprint image processing,which can improve the quality of fingerprint image and make the base for sequence-processing.

Key words: fingerprint recognition, image enhanced, binarization, thinning, improved algorithms