SCENE TEXT DETECTION WITH EXTREMAL REGION BASED CASCADED FILTERING
Li G(李根)1; Liu Jie(刘杰)1; Zhang Shuwu(张树武)1; Zheng Yang(郑阳)2
2016
会议名称IEEE International Conference on Image Processing (ICIP)
会议日期2016-09-25 ~ 2016-09-28
会议地点美国, 菲尼克斯
摘要
In this paper, we present a robust Extremal Region (ER) based
scene text detection system. To eliminate the vast non-text
components generated by ER operator, a three-stage cascaded
filter is proposed. In the first stage, a powerful character classifier
enhanced by recursive local search is introduced to separate
text components from noises. Then, an efficient heuristic
pruning method is designed to further clean overlapped duplicate
characters. Finally, after text line construction, a cascaded
text line classification model integrating word entropy
and sliding window based CNN is proposed to remove false
text lines. Experiments on benchmarks show that our method
achieves state-of-the-art performance.
关键词Text Detection Extremal Region Recursive Local Search Cascaded Filter
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14464
专题数字内容技术与服务研究中心_新媒体服务与管理技术
作者单位1.中国科学院自动化研究所
2.北京科技大学
推荐引用方式
GB/T 7714
Li G,Liu Jie,Zhang Shuwu,et al. SCENE TEXT DETECTION WITH EXTREMAL REGION BASED CASCADED FILTERING[C],2016.
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
SCENE TEXT DETECTION(1691KB)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
[Li G(李根)]的文章
[Liu Jie(刘杰)]的文章
[Zhang Shuwu(张树武)]的文章
百度学术
百度学术中相似的文章
[Li G(李根)]的文章
[Liu Jie(刘杰)]的文章
[Zhang Shuwu(张树武)]的文章
必应学术
必应学术中相似的文章
[Li G(李根)]的文章
[Liu Jie(刘杰)]的文章
[Zhang Shuwu(张树武)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: SCENE TEXT DETECTION WITH EXTREMAL REGION BASED CASCADED FILTERING.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。