检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]北京化工大学理学院,北京100029 [2]中国专利技术开发公司,北京100080
出 处:《计算机工程与设计》2014年第9期3029-3033,共5页Computer Engineering and Design
基 金:教育部中央高校基本科研业务费基金项目(ZZ1129)
摘 要:针对印鉴识别任务中有效印文的提取以及伪造印鉴的识别这两个难点问题,建立在监督分类体系下的印鉴识别系统。利用有效印文与背景的颜色统计差异以及真伪印鉴间的几何统计差异分别解决上述难点。在构建的包含3000个印鉴的印鉴数据库上进行实验,实验结果表明,该方法对于有效印文的提取准确率可达到(95.27±3.73%),对于伪造印鉴的识别准确率可达到97.62%,具有可行性和有效性。To solve two challenging problems of the seal imprint identification including the valid seal prints extraction and the forged seal identification, a new seal identification system was designed under a supervised classification framework. Based on the statistical color difference between seal prints and the background, and the geometric difference between the real and the forged seal, a novel seal extraction method and a novel forged seal identification method were proposed respectively. Results of the experiment performed on a challenging real seals database show that the proposed method obtains the good performance in terms of the valid seal prints extraction (95.27 ±3.73%)and the forged seal identification (97.62 %).
关 键 词:印鉴识别 有监督分类 特征匹配 几何一致性 局部图像特征
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38