Neural Network Based Over-Segmentation for Scene Text Recognition

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Neural Network Based Over-Segmentation for Scene Text Recognition
	He X(贺欣); Wu YC(吴一超); Chen K(陈凯); Yin F(殷飞); Liu CL(刘成林); He X(贺欣)
	2015
会议名称	Asian Conference on Pattern Recognition
会议录名称	Asian Conference on Pattern Recognition
会议日期	2015-11
会议地点	吉隆坡
摘要	Over-segmentation is often used in text recognition to generate candidate characters. In this paper, we propose a neural network-based over-segmentation method for cropped scene text recognition. On binarized text line image, a segmentation window slides over each connected component, and a neural network is used to classify whether the window locates a segmentation point or not. We evaluate several feature representations for window classification and combine sliding window-based segmentation with shape-based splitting. Experimentalresults on two benchmark datasets demonstrate the superiority and effectiveness of our method in respect of segmentation point detection and word recognition.
关键词	场景文字识别过切分
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11764
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	He X(贺欣)
作者单位	中国科学院自动化研究所
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	He X,Wu YC,Chen K,et al. Neural Network Based Over-Segmentation for Scene Text Recognition[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
Neural Network Based（444KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载