首页 | 本学科首页   官方微博 | 高级检索  
     

基于知识的印鉴鉴别方法
引用本文:胡庆,杨静宇,张黔,刘克.基于知识的印鉴鉴别方法[J].自动化学报,1991,17(6):696-704.
作者姓名:胡庆  杨静宇  张黔  刘克
作者单位:1.华东工学院计算机系,南京
摘    要:计算机印鉴鉴别是一项十分困难但又具有广泛应用背景的课题,国际上至今尚无实用有 效的鉴别方法.本文从知识工程的角度出发,对印鉴鉴别中的启发式知识进行了深入的讨论. 并在此基础上引入了一套完整的基于启发式知识的印鉴鉴别方法.该方法以启发式搜索获得 配准关系,并根据启发式知识在其中提取一组结构特征,最后结合结构信息和统计模型作出判 决.实验结果表明,该方法在可靠性、适应性和实用性方面比现有方法均有明显改进,已接近 实用.

关 键 词:印鉴鉴别    启发式知识    启发式搜索    特征提取    分类器
收稿时间:1991-7-19

A Knowledge Based Seal Imprint Verification Approach
Hu Qing,Yang Jingyu,Zhang Qian,Liu Ke.A Knowledge Based Seal Imprint Verification Approach[J].Acta Automatica Sinica,1991,17(6):696-704.
Authors:Hu Qing  Yang Jingyu  Zhang Qian  Liu Ke
Affiliation:1.Dept.of Computer Science,East China Institute of Technology,Nanjing
Abstract:To verify seal imprint by computer is a difficult practical problem. There is no efficient and practical approach up to date. According to the ideas of knowledge engineering and concepts of tne heuristic knowledge in the seal imprint verification, an effective and practical approach has been presented in this paper. In the approach, heuristic search scheme is used to calculate the registration relation, several effective features are extracted based on heuristic knowledge, and final decision is made in a statistical classification model with structural information. Extensive experiments show that this approach is superior in reliability, adaptability and practability to many existing approaches.
Keywords:Seal imprint verification  combined classification model  heuristic searcb in geometry space  feature extraction  K-L transformation  
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
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