摘要
文档图像在数字图书馆、电子商务以及电子政务等工程中已获得广泛应用。如何对文档图像进行有效的转换、存储和传输.成为人们研究的焦点。将文档图像分割成不同的区域,根据不同区域的特点分别进行处理,成为一种有效的解决方案。本文在传统的块分割和图层分割方法的基础上,提出了一种优化的文档图像分割思路,对这两种方法进行了合理的综合处理,能够取得更好的效果。
In recent years, document images are widely used in OA, digital library, e-commerce, and electronic government, etc. How to efficiently convert, storage, and transmit the document image has become the focus of research. Dividing the image into difference regions, and processing them according to their characters, which is a better resolution. The paper proposes a optimal document image segmentation method based on the integration of the block segmentation and layer segmentation, which is proved a good outcome.
出处
《计算机科学》
CSCD
北大核心
2004年第4期151-153,共3页
Computer Science
