Skip to content

smilealvin/OCR-note

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 

Repository files navigation

OCR-note

some memo for the OCR technology

一些比较好的模型

  1. 未加文字方向检测模块的模型 主要检测中文和英文以及一些符号https://github.com/YCG09/chinese_ocr
  2. 具有文字方向检测模块的模型 都是大神啊https://github.com/jiangxiluning/chinese-ocr

尚未测试过的模型

  1. C++的https://github.com/jiangxiluning/FOTS.PyTorch
  2. python的https://github.com/xieyufei1993/InceptText-Tensorflow
  3. Caffe的https://github.com/lvpengyuan/masktextspotter.caffe2#datasets
  4. https://github.com/AKSHAYUBHAT/DeepVideoAnalytics/tree/master/docs/experiments/ocr
  5. https://github.com/Belval/CRNN/tree/master/CRNN
  6. https://github.com/bear63/sceneReco
  7. 一个将densenet和crnn做了对比的项目
  8. https://github.com/diaomin/crnn-mxnet-chinese-text-recognition
  9. https://github.com/Bartzi/see
  10. https://github.com/MaybeShewill-CV/CRNN_Tensorflow
  11. https://github.com/oyxhust/CNN-LSTM-CTC-text-recognition
  12. https://github.com/xieyufei1993/InceptText-Tensorflow
  13. https://github.com/jiangxiluning/FOTS.PyTorch
  14. https://github.com/lvpengyuan/masktextspotter.caffe2

一些论文

https://github.com/tangzhenyu/Scene-Text-Understanding

一些数据集

  1. 清华的自然场景数据集
  2. 某网络数据集, 300w条字符, https://pan.baidu.com/s/1QkI7kjah8SPHwOQ40rS1Pw密码:lu7m
  3. 利用图片和文字, 合成自然场景下的文本, 40G, 800w个单词
  1. 合成简单背景的, 扭曲的文本, 项目地址
  2. ICDAR数据集
  3. 合成自然场景下的中文文本
  4. 星星比较少的合成自然场景下的中文文本模型https://github.com/wang-tf/Chinese_OCR_synthetic_data
  5. Coco数据集https://vision.cornell.edu/se3/coco-text-2/

一个网络汇总笔记

  1. https://cloud.tencent.com/developer/article/1092091
  2. http://www.cloudwalk.cn/news_detail_975.html
  3. https://yq.aliyun.com/articles/109555?t=t1

About

some memo for the OCR technology

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published