东北大学学报(自然科学版) ›› 2011, Vol. 32 ›› Issue (6): 854-858.DOI: -

• 论著 • 上一篇    下一篇

一种基于数学形态学的签名真伪鉴别方法

黄海龙;王宏;李微;   

  1. 东北大学机械工程与自动化学院;沈阳建筑大学管理学院;
  • 收稿日期:2013-06-19 修回日期:2013-06-19 发布日期:2013-04-04
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(61071057)

A signature identification method based on mathematical morphology

Huang, Hai-Long (1); Wang, Hong (1); Li, Wei (2)   

  1. (1) School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China; (2) College of Management, Shenyang Jianzhu University, Shenyang 110168, China
  • Received:2013-06-19 Revised:2013-06-19 Published:2013-04-04
  • Contact: Wang, H.
  • About author:-
  • Supported by:
    -

摘要: 针对离线签名鉴别可利用的信息少、鉴别难度大的问题,提出了一种基于数学形态学的签名真伪鉴别方法.该方法首先对采集的签名图像进行灰度化、二值化、滤波去噪、取反归一化等预处理,然后利用数学形态学的各种运算,结合不同大小和不同方向的结构元素提取签名中具有明显方向性特征的笔划,最后基于笔划的长短、粗细、间隔等信息对鉴别样本做出判别.实验结果表明,该方法能有效地提高鉴别的正确率,改善鉴别的实时性,对于应用新方法进行离线签名真伪鉴别是一次有益的尝试,具有一定的实用和推广价值.

关键词: 离线签名鉴别, 数学形态学, 预处理, 结构元素, 实时性

Abstract: It is much more complex and difficult for off-line signature identification attributable to the limitation of available information. To solve the problem, a signature identification method based on mathematical morphology is proposed. The signature image is gray-scaled, binarized, filtered, negated and normalized at the stage of preprocess; strokes which possess distinctive directional characteristics are extracted by using mathematical morphology and combining different scales/directions structure element; finally the judgements are made for samples in accordance with the length, thickness and distance of the strokes. Experimental results show that the proposed method can enhance the accuracy rate effectively and improve the real-time performance. It is a try beneficial to applying new methods to off-line signature identification with potential practical applications.

中图分类号: