End-to-End Chinese Image Text Recognition with Attention Model
Fenfen Sheng1,2
2017
会议名称International Conference on Neural Information Processing
会议日期November 14-18, 2017
会议地点Guangzhou, China
摘要This paper presents an attention-based model for end-to-end
Chinese image text recognition. The proposed model includes an encoder
and a decoder. For each input text image, the encoder part firstly combines deep convolutional layers with bidirectional Recurrent Neural Network to generate an ordered, high-level feature sequence, which could
avoid the complicated text segmentation pre-processing. Then in the
decoder, a recurrent network with attention mechanism is developed to
generate text line output, enabling the model to selectively exploit image
features from the encoder correspondingly. The whole segmentationfree model allows end-to-end training within a standard backpropagation algorithm. Extensive experiments demonstrate significant performance improvements comparing to baseline systems. Furthermore, qualitative analysis reveals that the proposed model could learn the alignment
between input and output in accordance with the intuition.

关键词Chinese Images Text Recognition · End-to-end · Attention · Segmentation-free
学科领域Computer Vision
DOI10.1007/978-3-319-70090-8_19
引用统计
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19661
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1.Institute of AutomationChinese Academy of SciencesBeijingChina
2.University of Chinese Academy of SciencesBeijingChina
推荐引用方式
GB/T 7714
Fenfen Sheng. End-to-End Chinese Image Text Recognition with Attention Model[C],2017.
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
End-to-End Chinese I(1100KB)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
[Fenfen Sheng]的文章
百度学术
百度学术中相似的文章
[Fenfen Sheng]的文章
必应学术
必应学术中相似的文章
[Fenfen Sheng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: End-to-End Chinese Image Text Recognition with Attention Model.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。