SCENE TEXT DETECTION WITH EXTREMAL REGION BASED CASCADED FILTERING

CASIA OpenIR > 数字内容技术与服务研究中心 > 版权智能与文化计算

	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_版权智能与文化计算
作者单位	1.中国科学院自动化研究所 2.北京科技大学
第一作者单位	中国科学院自动化研究所
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