OCR Tutorial

Reference:

https://github.com/HCIILAB/Scene-Text-Recognition-Recommendations (Up to 2023)

https://github.com/TongkunGuan/Text-Related-Papers (Up to 2024)

1 Paper

1.1 Survey

[2021-中国图像图形学报] 自然场景文本检测与识别中的深度学习方法综述

[Paper] https://www.cjig.cn/zh/article/doi/10.11834/jig.210044/

[2020-CSUR] Text Recognition in the Wild: A Survey

[Paper] https://arxiv.org/pdf/2005.034923

[Code] https://github.com/HCIILAB/Scene-Text-Recognition

1.2 Scene Text Detection & Recognition & Spotting & Segmentation

1.2.1 Detection

[2017-AAAI] TextBoxes: A Fast Text Detector with a Single Deep Neural Network

[Paper] https://arxiv.org/abs/1611.06779

[Code] https://github.com/MhLiao/TextBoxes

[2019-CVPR] PSENet

[Paper]

[Code] https://github.com/whai362/PSENet

[2019-ICCV] PAN

[Code] https://github.com/whai362/pan_pp.pytorch

[2020-CVPR] DRRG

[Paper] https://arxiv.org/abs/2003.07493

[2020-AAAI] DBNet

[Code] https://github.com/MhLiao/DB

[2020-CVPR] ABCNet

[Code] https://arxiv.org/abs/2002.10200

[2020-IJCAI] TextFuseNet

[Paper] https://www.ijcai.org/proceedings/2020/72

[Code] https://github.com/ying09/TextFuseNet

[2021-IJCV] I3CL

[Paper] https://arxiv.org/abs/2108.01343

[Code] https://arxiv.org/abs/2108.01343

[2023-AAAI] DPText-DETR

[Paper] https://arxiv.org/abs/2207.04491

[Code] https://github.com/ymy-k/DPText-DETR

[2023-CVPR] TCM

[Paper] https://arxiv.org/abs/2302.14338

[Code] https://github.com/wenwenyu/TCM

[2024-AAAI] LRANet

[Paper] https://arxiv.org/abs/2306.15142.pdf

[Code] https://github.com/ychensu/LRANet

[2024-AAAI] SRFormer

[Paper] https://arxiv.org/abs/2308.10531

[Code] https://github.com/retsuh-bqw/SRFormer-Text-Det

[2024-ICML] Towards Unified Multi-granularity Text Detection with Interactive Attention

[Paper] https://arxiv.org/abs/2405.19765

1.2.2 Recognition

[2016-TPAMI]

[Paper] https://arxiv.org/abs/1507.05717

[2019-ICCV] What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis

[Paper] https://arxiv.org/abs/1904.01906

[Code] https://github.com/clovaai/deep-text-recognition-benchmark

[2021-CVPR] ABINet

[Paper] https://arxiv.org/abs/2103.06495

[Code] https://github.com/FangShancheng/ABINet

[2022-ECCV] ParSeq

[Paper] https://arxiv.org/abs/2207.06966

[Code] https://github.com/baudm/parseq

1.2.3 Spotting

To Be Continued...

1.3 Scene Text Generation & Editing & Removal

To Be Continued...

1.4 Scene Text Understanding (TextVQA & VIE & Pretraining & ...)

To Be Continued...

2 Framework

3 Others

ICDAR Datasets: https://rrc.cvc.uab.es/