摘要
文章利用双层PDF的原理,以及信息技术及图像处理技术,构建了一种高效、准确、可靠的古籍的数字化系统模型,在古籍原版图像上实现全文检索、全文定位,解决了一直以来困扰研究者对古籍数字化产品进行利用的可靠性问题。
In this paper, 1 use double PDF theory, information technology and Image processing technology to build a new kind of ancient literature full-text digital model, this model is efficient, Accurate and reliable, use this model we can positioning retrieved result in the original image of the ancient books, resolve the reliability problems of the use of digital product of ancient books which has long eluded researchers.
出处
《语言研究》
CSSCI
北大核心
2014年第1期124-126,共3页
Studies in Language and Linguistics
关键词
古籍数字化
OCR识别
双层PDF
图像定位
Digitization of ancient books
OCR recognition
Double PDF
Localization of image