基于MODI的文档图像处理的研究  

Research of Document Image Processing Based on MODI

作　　者：顾李晶 赵霁[1] 

机构地区：[1]东南大学自动化学院,江苏南京210018

出　　处：《自动化技术与应用》2013年第11期45-47,66,共4页Techniques of Automation and Applications

摘　　要：识别文档图像中的文字,有助于人们管理和使用信息。MODI作为Microsoft Office内建的免费文字识别组件,使开发人员可以方便地,以较低的成本处理文档图像。本文通过研究MODI组件的OCR模块的特点和二次开发,以及与其他商业OCR软件的对比,验证了MODI在文档图像处理方面具有较高的可靠性和应用价值。Document image processing helps people to manage and use information by identifying the text in the document image.MODI,as a free and built-in character recognition components in Microsoft Office,makes developers more convenient and lower the cost of processing the document image.In this paper,from the research of features and secondary development of optical character recognition module in the MODI components,as well as comparison with other commercial optical character recognition software,it verifies that the MODI has higher reliability,and a higher value in document image processing.

关 键 词：文档图像 MODI OCR 

分 类 号：TP391.413[自动化与计算机技术—计算机应用技术]