场景文字识别概述

1.概述

点击打开链接

知乎链接

https://www.zhihu.com/question/20191727

2.相关论文

论文及数据集资源集合

https://www.cnblogs.com/huty/p/8516960.html

https://github.com/chongyangtao/Awesome-Scene-Text-Recognition

15年的综述

http://mclab.eic.hust.edu.cn/UpLoadFiles/Papers/FCS_TextSurvey_2015.pdf

论文 Detecting Text in Natural Image with Connectionist Text Proposal Network(CTPN)

https://arxiv.org/abs/1609.03605

论文:Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

https://arxiv.org/abs/1802.08948

介绍:http://tech.ifeng.com/a/20180301/44892454_0.shtml

3.YunOS场景文字识别

点击打开链接

4.文字识别crnn

https://github.com/bear63/sceneReco

https://blog.csdn.net/u013293750/article/details/73188934

https://github.com/TJCVRS/CRNN_Tensorflow

5.3755个汉字的识别

http://www.cnblogs.com/skyfsm/p/8443107.html

6.文字检测

CTPN https://github.com/eragonruan/text-detection-ctpn

EAST text detector  https://github.com/argman/EAST

SynthText  https://github.com/JarveeLee/SynthText_Chinese_version

B. Shi, X. Bai, S. Belongie. Detecting oriented text in natural images by linking segments. In: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17), Honolulu, Hawaii, 2017. (Spotlight) [ppt] [code]

Z. Zhang, C. Zhang, W. Shen, C. Yao, W. Liu, X. BaiMulti-oriented text detection with fully convolutional networks. In: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), Las Vegas, 2016. [code]


7.end to end 检测和识别的一体网络

Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks

M. Liao, B. Shi, X. Bai, X. Wang, W. Liu. TextBoxes: A fast text detector with a single deep neural network. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI'17), San Francisco, California, 2017.  [code]

8.印刷体识别

https://github.com/tesseract-ocr/tesseract


  • 2
    点赞
  • 6
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

AICVer

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值