基于最小二乘法的印鉴缺损轮廓修补法  

Least square method based repairing method for broken seal imprint contour

作　　者：张学东[1,2] 潘晓红[1] 李端端[1] 廖开阳[1,3] 

机构地区：[1]辽宁科技大学计算机科学与工程学院,辽宁鞍山114051 [2]东北大学信息科学与工程学院,辽宁沈阳110004 [3]西安翻译学院信息工程系,陕西西安710000

出　　处：《计算机工程与设计》2009年第20期4693-4696,共4页Computer Engineering and Design

基　　金：东北大学博士后基金项目(20080313)

摘　　要：作为印章识别系统中的第一步,印鉴提取起着至关重要的作用。就印鉴的预处理问题研究了印鉴图像的提取及对提取印鉴中缺失信息的修复,首先提出印鉴提取的通用模型提取印鉴图像,然后,针对印鉴信息缺失的不同原因,分别采取了不同的修复策略:对因签名等干扰字符覆盖造成的信息缺失采用了结合背景图像和原图像二值图的方法进行修复,而对于因盖章力度不均导致的印鉴轮廓缺损,采用了最小二乘法二次拟合的方法进行了修补。实验结果表明,提出的算法能有效地得到信息完整的印鉴图像,能满足后期识别工作的要求。As the first step in seal identification system, seal imprint extraction plays a significant role. The preprocessing of seal imprint image, including seal extraction and lost information recovery, is studied, among which the lost information recovery approach is focused on. Firstly, a universal seal imprint extraction model is given, and then, the lost information recovery algorithms are presented respectively according to different causes that lead to the information lost in extracted seal image, For the lost information caused by disturbing characters covering, it is recovered by means of combining background image and foreground image, while for the lost information caused by the unequal force during stamping seals, it is recovered by mending the outer contour of the seal imprint image. It＇ s proved that with our proposed algorithm, a seal imprint is gotten with complete information effectively, which can satisfy the requirements for the succeeding verification work.

关 键 词：印鉴提取 二值化 缺失信息修复 最小二乘法 轮廓修补 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]