Efficient Text Localization in Born-Digital Images by Local Contrast-Based Segmentation
Kai Chen; Yin, Fei; Liu, Chenglin
2015-08
会议名称2015 13TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR)
会议录名称International Conference on Document Analysis and Recognition (ICDAR)
会议日期2015-8
会议地点法国南锡
摘要Text localization in born-digital images is usually
performed using methods designed for scene text images. Based
on the observation that text strokes in born-digital images mostly
have complete contours and the pixels on the contours have
high contrast compared with the adjacent non-text pixels, we
propose a method to extract candidate text components using
local contrast. First, the image is segmented into smooth and
non-smooth regions. After removing non-text smooth regions, the
remaining smooth regions are merged with non-smooth regions
to form a candidate text image, which is binarized into high-value
and low-value connected components (CCs). The CCs undergo
CC filtering, line grouping and line classification to give the
text localization result. Experimental results on the born-digital
dataset of ICDAR2013 robust reading competition demonstrate
the efficiency and superiority of the proposed method.
关键词Text Localization Image Segmentation Local Contrast Connected Components Grouping
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11948
专题模式识别国家重点实验室_模式分析与学习
通讯作者Kai Chen
作者单位中科院自动化研究所
推荐引用方式
GB/T 7714
Kai Chen,Yin, Fei,Liu, Chenglin. Efficient Text Localization in Born-Digital Images by Local Contrast-Based Segmentation[C],2015.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Efficient-text-Chen.(557KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Kai Chen]的文章
[Yin, Fei]的文章
[Liu, Chenglin]的文章
百度学术
百度学术中相似的文章
[Kai Chen]的文章
[Yin, Fei]的文章
[Liu, Chenglin]的文章
必应学术
必应学术中相似的文章
[Kai Chen]的文章
[Yin, Fei]的文章
[Liu, Chenglin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Efficient-text-Chen.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。