Chinese Image Text Recognition with BLSTM-CTC: A Segmentation-free Method
Zhai, Chuanlei; Chen ZN(陈智能); Li J(李杰); Xu B(徐波)
2016-10
会议名称The 7th Chinese Conference on Pattern Recognition(CCPR 2016)
会议日期November 5-7, 2016
会议地点Chengdu, China
摘要This paper presents BLSTM-CTC (bidirectional LSTM-Connectionist Temporal Classification), a novel scheme to tackle the Chinese image text recognition problem. Different from traditional methods that perform the recognition on the single character level, the input of BLSTM-CTC is an image text composed of a line of characters and the output is a recognized text sequence, where the recognition is carried out on the whole image text level. To train a neural network for this challenging task, we collect over 2 million news titles from which we generate over 1 million noisy image texts, covering almost the vast majority of common Chinese characters. With these training data, a RNN training procedure is conducted to learn the recognizer. We also carry out some adaptations on the neural network to make it suitable for real scenarios. Experiments on text images from 13 TV channels demonstrate the effectiveness of the proposed pipeline. The results all outperform those of a baseline system.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14521
专题数字内容技术与服务研究中心_听觉模型与认知计算
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Zhai, Chuanlei,Chen ZN,Li J,et al. Chinese Image Text Recognition with BLSTM-CTC: A Segmentation-free Method[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
Chinese Image Text R(1376KB)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
[Zhai, Chuanlei]的文章
[Chen ZN(陈智能)]的文章
[Li J(李杰)]的文章
百度学术
百度学术中相似的文章
[Zhai, Chuanlei]的文章
[Chen ZN(陈智能)]的文章
[Li J(李杰)]的文章
必应学术
必应学术中相似的文章
[Zhai, Chuanlei]的文章
[Chen ZN(陈智能)]的文章
[Li J(李杰)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Chinese Image Text Recognition with BLSTM-CTC.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。