基于深度学习的浏览器OCR插件设计与实现  

Design and Implementation of an OCR Browser Extension Based on Deep Learning

作　　者：廖晓彬 Liao Xiaobin(Department of Computer Science, Beijing Forestry University, Beijing 100083, China)

机构地区：[1]北京林业大学计算机科学与技术系,北京100083

出　　处：《信息与电脑》2018年第10期108-109,112,共3页Information & Computer

摘　　要：浏览器是用户日常接触网络的信息重要入口,用户对于网页上的文字识别也有广泛需求,因此,开发一款OCR文字识别的浏览器插件,将极大提高用户的工作效率。笔者介绍了基于深度学习OCR文字识别的技术原理,设计了并实现了一款基于深度学习的浏览器OCR插件。The browser is an important entrance for users to contact the network daily. The user also has a wide demand for word recognition on the webpage. Therefore, developing a browser extension for OCR character recognition will greatly improve the user＇s work efficiency. The author introduces the technical principle of OCR based on deep learning, and designs and implements an OCR browser extension based on deep learning.

关 键 词：深度学习 OCR 浏览器插件 

分 类 号：TP311.52[自动化与计算机技术—计算机软件与理论]