通用OCR开发工具的设计  

Design of the Genral OCR Development Tools

作　　者：王浩军[1] 赵南元[1] 邓钢轶[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《计算机工程与应用》2002年第21期133-136,共4页Computer Engineering and Applications

摘　　要：提出了一个通用OCR开发工具的设想,用于各种文字的OCR软件的开发,它能够在使用者的干预下自动完成识别器的设计,大大减少文字识别软件开发的工作量。系统以决策树作为基本的判别器,并用多个决策树组成多方案识别系统。提出设计树和分类器设计器的概念,分别用于决策树设计过程的控制和决策树节点中的分类器的设计。最后实现一个实验系统,验证了该文的设想和设计方案的可行性。This paper brings out the idea of General OCR Software Development Tools,which can be used to develop OCR Software for all kinds of Scripts.Because it can automatically design the classifier with the assistance of the de-signer,total workload of the development of a recognition system will be reduced remarkably.The paper selects decision tree as the basic classifier and several decision trees can be used together to implement multiple classifier integration.The idea of designing tree and classifier designer are proposed to control the design process of decision tree and de-sign the classifier of the node of decision tree.An experimental system has been accomplished,which demonstrates the effectiveness of our design method.

关 键 词：通用OCR开发工具 设计 文字识别 决策树 设计树 自动设计 光学文字识别 计算机 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]