OCR资源|论文，代码，数据集

请点击上方“AI公园”，关注公众号

---

本文选自github

作者：ZumingHuang

编译：ronghuaiyang

github上另外一位同学整理的OCR的资源分享，也很全面，按照论文主题，年份进行了分类，非常好！

github地址： https://github.com/ZumingHuang

这个仓库包括了收集的OCR方面一些资源（有论文有些有代码有数据集）。

内容

按论文的主题排列

文字检测

2018

Single Shot Scene Text RetrievalLluıs Gomez, Andres Mafla, Marcal Rusinol, Dimosthenis KaratzasLicense Plate Detection and Recognition in Unconstrained ScenariosSergio Montazzolli Silva, Claudio Rosito Jung

Using Object Information for Spotting TextShitala Prasad, Adams Wai Kin Kong

Accurate Scene Text Detection through Border Semantics Awareness and BootstrappingChuhui Xue, Shijian Lu, Fangneng Zhan

Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in ScenesFangneng Zhan, Shijian Lu, Chuhui Xue

TextSnake: A Flexible Representation for Detecting Text of Arbitrary ShapesShangbang Long, Jiaqiang Ruan, Wenjie Zhang, Xin He, Wenhao Wu, Cong Yao

Shape Robust Text Detection with Progressive Scale Expansion NetworkXiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang代码：https://github.com/whai362/PSENet

Boosting up Scene Text Detectors with Guided CNNXiaoyu Yue, Zhanghui Kuang, Zhaoyang Zhang, Zhenfang Chen, Pan He, Yu Qiao, Wei Zhang

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text DetectionQiangpeng Yang, Mengli Cheng, Wenmeng Zhou, Yan Chen, Minghui Qiu, Wei Lin

Geometry-Aware Scene Text Detection With Instance Transformation NetworkFangfang Wang, Liming Zhao, Xi Li, Xinchao Wang, Dacheng Tao

Learning Markov Clustering Networks for Scene Text DetectionZichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, Wang Ling Goh

Rotation-Sensitive Regression for Oriented Scene Text DetectionMinghui Liao, Zhen Zhu, Baoguang Shi, Gui-song Xia, Xiang Bai

Multi-Oriented Scene Text Detection via Corner Localization and Region SegmentationPengyuan Lyu, Cong Yao, Wenhao Wu, Shuicheng Yan, Xiang Bai

PixelLink: Detecting Scene Text via Instance SegmentationDan Deng, Haifeng Liu, Xuelong Li, Deng Cai

Sliding Line Point Regression for Shape Robust Scene Text DetectionYixing Zhu, Jun Du

TextBoxes++: A Single-Shot Oriented Scene Text DetectorMinghui Liao, Baoguang Shi, Xiang Bai

2017

Detecting Curve Text in the Wild: New Dataset and New SolutionLiu Yuliang, Jin Lianwen, Zhang Shuaitao, Zhang Sheng

Deep Direct Regression for Multi-Oriented Scene Text DetectionWenhao He, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu

WeText: Scene Text Detection under Weak SupervisionShangxuan Tian, Shijian Lu, and Chongshou Li

Single Shot Text Detector with Regional AttentionPan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, Xiaolin Li

Self-organized Text Detection with Minimal Post-processing via Border LearningYue Wu, Prem Natarajan

WordSup: Exploiting Word Annotations for Character based Text DetectionHan Hu, Chengquan Zhang, Yuxuan Luo, Yuzhuo Wang, Junyu Han, Errui Ding

Deep Matching Prior Network: Toward Tighter Multi-oriented Text DetectionYuliang Liu, Lianwen Jin

Detecting Oriented Text in Natural Images by Linking SegmentsBaoguang Shi, Xiang Bai, Serge Belongie

EAST: An Efficient and Accurate Scene Text DetectorXinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, and Jiajun Liang

Unambiguous Text Localization and Retrieval for Cluttered ScenesXuejian Rong, Chucai Yi, Yingli Tian

R2CNN: Rotational Region CNN for Orientation Robust Scene Text DetectionYingying Jiang, Xiangyu Zhu, Xiaobing Wang, Shuli Yang, Wei Li, Hua Wang, Pei Fu, Zhenbo Luo

Cascaded Segmentation-Detection Networks for Word-Level Text SpottingSiyang Qin, Roberto Manduchi

Improving Text Proposal for Scene Images with Fully Convolutional NetworksDena Bazazian, Raul Gomez, Anguelos Nicolaou, Lluis Gomez, Dimosthenis Karatzas, Andrew D. Bagdanov

TextBoxes: A Fast Text Detector with a Single Deep Neural NetworkMinghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu

Detection and Recognition of Text Embedded in Online Images via Neural Context ModelsChulmoo Kang, Gunhee Kim, Suk I. Yoo

Arbitrary-Oriented Scene Text Detection via Rotation ProposalsJianqi Ma, Weiyuan Shao, Hao Ye, Li Wang, Hong Wang, Yingbin Zheng, Xiangyang Xue

TextProposals: A text-specific selective search algorithm for word spotting in the wildLluis Gomez, Dimosthenis Karatzas代码：https://github.com/lluisgomez/TextProposals

2016

Detecting Text in Natural Image with Connectionist Text Proposal NetworkZhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao

Synthetic Data for Text Localisation in Natural ImagesAnkush Gupta, Andrea Vedaldi, Andrew Zisserman

Multi-Oriented Text Detection with Fully Convolutional NetworksZheng Zhang, Chengquan Zhang, Wei Shen, Cong Yao, Wenyu Liu, Xiang Bai

Canny Text Detector: Fast and Robust Scene Text Localization AlgorithmHojin Cho, Myungchul Sung, Bongjin Jun

Scene Text Detection via Holistic, Multi-Channel PredictionCong Yao, Xiang Bai, Nong Sang, Xinyu Zhou, Shuchang Zhou, Zhimin Cao

DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural ImagesZhuoyao Zhong, Lianwen Jin, Shuye Zhang, Ziyong Feng

Accurate Text Localization in Natural Image with Cascaded Convolutional Text NetworkTong He, Weilin Huang, Yu Qiao, Jian Yao

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural ImagesAndreas Veit, Tomas Matera, Lukas Neumann, Jiri Matas, Serge Belongie

Reading Text in the Wild with Convolutional Neural NetworksMax Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman

Text-Attentional Convolutional Neural Network for Scene Text DetectionTong He, Weilin Huang, Yu Qiao, Jian Yao

TextCatcher: a method to detect curved and challenging text in natural scenesJonathan Fabrizio, Myriam Robert-Seidowsky, Severine Dubuisson, Stefania Calarasanu, Raphael Boissel

Context Modeling for Semantic Text Matching and Scene Text DetectionWenyi Huang

2015

Text Flow: A Unified Text Detection System in Natural Scene ImagesShangxuan Tian, Yifeng Pan, Chang Huang, Shijian Lu, Kai Yu, Chew Lim Tan

FASText: Efficient unconstrained scene text detectorMichal Busta, Lukas Neumann, Jiri Matas

Object Proposals for Text Extraction in the WildLluis Gomez, Dimosthenis Karatzas

Real-Time Lexicon-Free Scene Text Localization and RecognitionLukas Neumann, Jiri Matas

2014

Deep Features for Text SpottingMax Jaderberg, Andrea Vedaldi, Andrew Zisserman

Robust Scene Text Detection with Convolution Neural Network Induced MSER TreesWeilin Huang, Yu Qiao, Xiaoou Tang

Robust Text Detection in Natural Scene ImagesXu-Cheng Yin, Xuwang Yin, Kaizhu Huang, Hong-Wei Hao

2013

PhotoOCR: Reading Text in Uncontrolled ConditionsAlessandro Bissacco, Mark Cummins, Yuval Netzer, Hartmut Neven

2012

Real-Time Scene Text Localization and RecognitionLukas Neumann, Jiri Matas

2010

Detecting Text in Natural Scenes with Stroke Width TransformBoris Epshtein, Eyal Ofek, Yonatan Wexler

文字识别

2018

Synthetically Supervised Feature Learning for Scene Text RecognitionYang Liu, Zhaowen Wang, Hailin Jin, Ian Wassell

Single Shot Scene Text RetrievalLluıs Gomez, Andres Mafla, Marcal Rusinol, Dimosthenis Karatzas

License Plate Detection and Recognition in Unconstrained ScenariosSergio Montazzolli Silva, Claudio Rosito Jung

Towards Human-Level License Plate RecognitionJiafan Zhuang, Saihui Hou, Zilei Wang, Zheng-Jun Zha

Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in ScenesFangneng Zhan, Shijian Lu, Chuhui Xue

SCAN: Sliding Convolutional Attention Network for Scene Text RecognitionYi-Chao Wu, Fei Yin, Xu-Yao Zhang, Li Liu, Cheng-Lin Liu

Edit Probability for Scene Text RecognitionFan Bai, Zhanzhan Cheng, Yi Niu, Shiliang Pu, Shuigeng Zhou

AON: Towards Arbitrarily-Oriented Text RecognitionZhanzhan Cheng, Yangliu Xu, Fan Bai, Yi Niu, Shiliang Pu, Shuigeng Zhou

SqueezedText: A Real-Time Scene Text Recognition by Binary Convolutional Encoder-Decoder NetworkZichuan Liu, Yixing Li, Fengbo Ren, Wang Ling Goh, Hao Yu

Char-Net: A Character-Aware Neural Network for Distorted Scene Text RecognitionWei Liu, Chaofeng Chen, Kwan-Yee K. Wong

TextBoxes++: A Single-Shot Oriented Scene Text DetectorMinghui Liao, Baoguang Shi, Xiang Bai

2017

Focusing Attention: Towards Accurate Text Recognition in Natural ImagesZhanzhan Cheng, Fan Bai, Yunlu Xu, Gang Zheng

TextBoxes: A Fast Text Detector with a Single Deep Neural NetworkMinghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu

Detection and Recognition of Text Embedded in Online Images via Neural Context ModelsChulmoo Kang, Gunhee Kim, Suk I. Yoo

2016

Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training DataXinghua Lou, Ken Kansky, Wolfgang Lehrach, CC Laan, Bhaskara Marthi, D. Phoenix, Dileep George

Robust Scene Text Recognition with Automatic RectificationBaoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai

Recursive Recurrent Nets with Attention Modeling for OCR in the WildChen-Yu Lee, Simon Osindero

Context-Aware Mathematical Expression Recognition: An End-to-End Framework and A BenchmarkWenhao He, Yuxuan Luo, Fei Yin, Han Hu, Junyu Han, Errui Ding, Cheng-Lin Liu

Reading Scene Text in Deep Convolutional SequencesPan He, Weilin Huang, Yu Qiao, Chen Change Loy, Xiaoou Tang

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural ImagesAndreas Veit, Tomas Matera, Lukas Neumann, Jiri Matas, Serge Belongie

Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text RecognitionZecheng Xie, Zenghui Sun, Lianwen Jin, Hao Ni, Terry Lyons

Reading Text in the Wild with Convolutional Neural NetworksMax Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman

2015

Deep Structured Output Learning for Unconstrained Text RecognitionMax Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman

Real-Time Lexicon-Free Scene Text Localization and RecognitionLukas Neumann, Jiri Matas

An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionBaoguang Shi, Xiang Bai, Cong Yao

2014

Synthetic Data and Artificial Neural Networks for Natural Scene Text RecognitionMax Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman

Deep Features for Text SpottingMax Jaderberg, Andrea Vedaldi, Andrew Zisserman

Word Spotting and Recognition with Embedded AttributesJon Almazan, Albert Gordo, Alicia Fornes, Ernest Valveny

2013

PhotoOCR: Reading Text in Uncontrolled ConditionsAlessandro Bissacco, Mark Cummins, Yuval Netzer, Hartmut Neven

Scene Text Recognition using Part-based Tree-structured Character DetectionCunzhao Shi, Chunheng Wang, Baihua Xiao, Yang Zhang, Song Gao, Zhong Zhang

2012

Real-Time Scene Text Localization and RecognitionLukas Neumann, Jiri Matas

文字分割

2018

Shape Robust Text Detection with Progressive Scale Expansion NetworkXiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text DetectionQiangpeng Yang, Mengli Cheng, Wenmeng Zhou, Yan Chen, Minghui Qiu, Wei Lin

Learning Markov Clustering Networks for Scene Text DetectionZichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, Wang Ling Goh

Multi-Oriented Scene Text Detection via Corner Localization and Region SegmentationPengyuan Lyu, Cong Yao, Wenhao Wu, Shuicheng Yan, Xiang Bai

PixelLink: Detecting Scene Text via Instance SegmentationDan Deng, Haifeng Liu, Xuelong Li, Deng Cai

2017

Cascaded Segmentation-Detection Networks for Word-Level Text SpottingSiyang Qin, Roberto Manduchi

2016

Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training DataXinghua Lou, Ken Kansky, Wolfgang Lehrach, CC Laan, Bhaskara Marthi, D. Phoenix, Dileep George

端到端ocr

2018

Towards End-to-End License Plate Detection and Recognition: A Large Dataset and BaselineZhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, Liusheng Huang

代码：https://github.com/detectRecog/CCPD

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary ShapesPengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai

An end-to-end TextSpotter with Explicit Alignment and AttentionTong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun代码：https://github.com/tonghe90/textspotter

FOTS: Fast Oriented Text Spotting with a Unified NetworkXuebo Liu, Ding Liang, Shi Yan, Dagui Chen, Yu Qiao, Junjie Yan

SEE: Towards Semi-Supervised End-to-End Scene Text RecognitionChristian Bartz, Haojin Yang, Christoph Meinel代码：https://github.com/Bartzi/see

2017

Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition FrameworkMichal Busta, Lukas Neumann, Jiri Matas代码：https://github.com/MichalBusta/DeepTextSpotter

Towards End-to-end Text Spotting with Convolutional Recurrent Neural NetworksHui Li, Peng Wang, Chunhua Shen

2015

Deep learning for text spottingMaxwell Jaderberg

2012

End-to-End Text Recognition with Convolutional Neural NetworksTao Wang, David J. Wu, Adam Coates, Andrew Y. Ng代码：http://cs.stanford.edu/people/twangcat/ICPR2012_code/SceneTextCNN_demo.tar

数据集

生成数据

Dataset	Train	Validation	Test	Character-Level Annotation	Word-Level Annotation
Synthetic Word	7,224,612	802,734	891,927	No	Yes (Cropped Word)
SynthText in the Wild	800,000	No	No	Yes (Rectangle)	Yes (Quadrangle)

ICDAR数据

Dataset	Train	Validation	Test	Character-Level Annotation	Word-Level Annotation
ICDAR 2013	229	No	233	Yes (Pixel-Level)	Yes (Rectangle)
ICDAR 2015	1000	No	500	No	Yes (Quadrangle)
ICDAR 2017 COCO-Text	43,486	10,000	10,000	No	Yes (Rectangle)
ICDAR 2017 MLT	7200	1800	email to nibal.nayef@univ-lr.fr	No	Yes (Quadrangle)

不规则数据

Dataset	Train	Validation	Test	Character-Level Annotation	Word-Level Annotation	Line-Level Annotation
Total-Text	1255	No	300	Yes	Yes (Polygon)	No
SCUT-CTW1500	1000	No	500	No	Yes (Polygon)	No
Uber-Text	59,001	23,606	35,362	No	No	Yes (Polygon)

视频数据

Dataset	Year	Category	Source	Task	Language
ICDAR 2017 DOST	2017	Scene text	Video	Localization/Tracking/Recognition	English/Japanese
USTB-VidTEXT	2016	Embedded caption	Video	Localization/Recognition	English/Chinese
ICDAR 2015 Text in Videos	2015	Scene text	Video	Localization/Tracking/Recognition	English/Spanish/French/Japanese
YouTube Video	2014	Embedded caption/Scene text	Video	Localization/Tracking/Recognition	English
Merino-Gracia	2014	Scene text	Video	Tracking	English
ICDAR 2013 Text in Videos	2013	Scene text	Video	Localization/Tracking/Recognition	English/Spanish/French/Japanese
Minetto	2011	Scene text	Video	Localization/Tracking/Recognition	English
SVT	2010	Scene text	Video frames	Localization/Recognition	English
TREC	2002	Embedded caption/Scene text	Video frames	Search	English

致谢

这个资源是基于 image-text-localization-recognition 和 Awesome-Scene-Text-Recognition.