Scene Text Detection with Novel Superpixel Based Character Candidate Extraction
Wang C(王聪)1,2; Yin F(殷飞)1; Liu CL(刘成林)1,2
2017
会议名称The 14th International Conference on Document Analysis and Recognition (ICDAR)
页码929-934
会议日期November 10-15, 2017
会议地点Kyoto, Japan
出版地Osaka, Japan
摘要
Maximally stable extremal region (MSER) is popularly used for candidate character candidate extraction in scene text detection. Its requirement of maximum stability hinders high performance on images of high variability. In this paper, we propose a novel character candidate extraction method based on superpixel segmentation and hierarchical clustering. The proposed superpixel segmentation algorithm for scene text image takes advantage of the color consistency of characters and fuses color and edge information. Based on superpixel segmentation, character candidates are extracted by single-link clustering. To improve the accuracy of non-text candidate filtering, we use a deep convolutional neural networks (DCNN) classifier and double threshold strategy for classification. Experimental results on public datasets demonstrate that the proposed superpixel based method performs better than MSER in character candidate extraction, and the proposed system achieves competitive performance compared to state-of-the-art methods.
关键词Scene Text Detection Superpixel Hierarchical Clustering
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/173211/20029
专题模式识别国家重点实验室_模式分析与学习
作者单位1.中国科学院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Wang C,Yin F,Liu CL. Scene Text Detection with Novel Superpixel Based Character Candidate Extraction[C]. Osaka, Japan,2017:929-934.
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
ICDAR2017_SCCs_final(856KB)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
[Wang C(王聪)]的文章
[Yin F(殷飞)]的文章
[Liu CL(刘成林)]的文章
百度学术
百度学术中相似的文章
[Wang C(王聪)]的文章
[Yin F(殷飞)]的文章
[Liu CL(刘成林)]的文章
必应学术
必应学术中相似的文章
[Wang C(王聪)]的文章
[Yin F(殷飞)]的文章
[Liu CL(刘成林)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ICDAR2017_SCCs_final.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。