摘要
自然场景中的文字提取技术成为了近几年计算机视觉领域的热门研究课题。本文对自然场景文本信息提取的关键技术进行了研究,全面总结了文本信息提取的研究现状,对文本检测定位和识别算法设计进行了有益的探索和研究,并对主流算法进行了分类和对比,最后总结了场景图像中文本信息提取存在的主要问题和评测方法。
The scene text extraction technology has become more and more important and is being applied to more and more new scenarios. This paper mainly gives a research on the key technologies of extracting text from natural scene images. This thesis explored and researched some key technologies and design of algorithm for text location and text recognition, and a comparison study is conduct- ed on categorized algorithm. Finally evaluation methods are exhibited and most difficulties and future direction are concluded.
出处
《黑龙江科技信息》
2015年第36期131-133,共3页
Heilongjiang Science and Technology Information
基金
安徽省自然科学研究基金项目(1408085MF127)
关键词
自然场景图像
文本信息提取
文本定位
文本识别
Natural Scene Image
Text Information Extraction
Text Location
Text Recognition