首页 | 本学科首页   官方微博 | 高级检索  
     

基于组合特征的集装箱箱号识别法
引用本文:郭喜凤,安博文,辉林如.基于组合特征的集装箱箱号识别法[J].计算机与现代化,2011(9):78-81,85.
作者姓名:郭喜凤  安博文  辉林如
作者单位:上海海事大学信息工程学院,上海,200135
基金项目:上海海事大学校基金资助项目(20100138)
摘    要:为准确、高效地识别集装箱箱号,提出一种基于组合特征实现箱号识别的方法。对分割好的字符二值图像预处理后提取孔洞特征、凹凸特征、跳变特征、笔画特征等,利用树形分类器进行分类识别,并结合箱号自身的校验规则进行验证、识别。该方法不需要对字符图像做复杂的细化处理,提高了运算速度,避免了细化造成的字符畸变。实验结果表明,该方法平均箱号正确识别率可以达到93%,每箱号(11个字符)平均识别时间为0.065s。

关 键 词:箱号识别  图像预处理  特征提取  树形分类器

Recognition Method of Container Code Based on Combined Features
GUO Xi-feng,AN Bo-wen,HUI Lin-ru.Recognition Method of Container Code Based on Combined Features[J].Computer and Modernization,2011(9):78-81,85.
Authors:GUO Xi-feng  AN Bo-wen  HUI Lin-ru
Affiliation:GUO Xi-feng,AN Bo-wen,HUI Lin-ru(College of Information Engineering,Shanghai Maritime University,Shanghai 200135,China)
Abstract:In order to recognize container code precisely and effectively,a recognition method of container code based on combined features is proposed.After preprocessing the segmented binary image of single character,the character features including hole,concave-convex,leap,stroke,etc.are extracted.Then the tree-like classifier is used to classify and recognize the container code,and combine the validation rules to verify the results.The method doesn't need complex thinning procedure on the character image,improves ...
Keywords:container code recognition  image preprocessing  feature extraction  tree-like classifier  
本文献已被 CNKI 维普 万方数据 等数据库收录!
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