Multi-polarity text segmentation using graph theory | |
Li, Jia ; Tian, Yonghong ; Huang, Tiejun ; Gao, Wen | |
2008 | |
英文摘要 | Text segmentation, or named text binarization, is usually an essential step for text information extraction from images and videos. However, most existing text segmentation methods have difficulties in extracting multi-polarity texts, where multi-polarity texts mean those texts with multiple colors or intensities in the same line. In this paper, we propose a novel algorithm for multi-polarity text segmentation based on graph theory. By representing a text image with an undirected weighted graph and partitioning it iteratively, multi-polarity text image can be effectively split into several single-polarity text images. As a result, these text images are then segmented by single-polarity text segmentation algorithms. Experiments on thousands of multi-polarity text images show that our algorithm can effectively segment multi-polarity texts. ? 2008 IEEE.; EI; 0 |
语种 | 英语 |
DOI标识 | 10.1109/ICIP.2008.4712428 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/327608] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Li, Jia,Tian, Yonghong,Huang, Tiejun,et al. Multi-polarity text segmentation using graph theory. 2008-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论