配准方法在签名鉴定系统中的研究  

Study of Matching Method in Signature Verification System

作　　者：姜宏亮[1] 刘嘉敏[1] 马广焜[1] 

机构地区：[1]沈阳工业大学信息科学与工程学院,辽宁沈阳110023

出　　处：《计算机与现代化》2008年第8期57-59,共3页Computer and Modernization

摘　　要：在笔迹鉴定系统中,针对字体点云与字体图像的配准问题,本文给出了一个简单有效的解决方法,避免了大量繁琐复杂的计算。对字体点云与字体图像进行特殊角点的快速搜索,然后利用计算得到的参数进行角度旋转、尺度伸缩、平移等操作把字体点云匹配到相应的字体图像上。用该方法对相关样本进行大量实验,平均配准率达到了97.4%,取得满意的效果并基本符合笔迹鉴定系统的研发要求。对于图像配准在此类问题的解决方法上提供了值得借鉴的成功经验。In order to solve the problem of how to match dot cloud of Chinese characters corresponding to relative Chinese characters image in the signature verification system, this paper gives an available and convenient method avoiding the massive, tedious and complex computations. Through the fast search of the special comer in the dot cloud Of character and the character image, relative parameter can be calculated. After the operation of rotation, scaling stretching and translation etc the cloud character can be matched to the character image. Using the matching method to do experiments with a large amount of samples, the average matching ratio touched to 97.4% and the result satisfied the need of further researches in the signature verification system, It provided a success experience to solve such problem about image matching.

关 键 词：图像配准 签名鉴定系统 点云 细线化 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]