├── LICENSE
├── README.md
├── detection_ic13_results.png
├── detection_ic15_results.png
├── end2end_ic13_ic15_results.png
├── overall_histogram.png
├── overall_pi_chart.png
├── recognition_ic13_results.png
└── recognition_iiit5k_results.png
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [yyyy] [name of copyright owner]
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # awesome-deep-text-detection-recognition
2 | A curated list of awesome deep learning based papers on text detection and recognition.
3 |
4 |
5 |
6 |
7 |
8 |
9 | ## Text Detection
10 | * Papers are sorted by published date.
11 | * IC is shorts for ICDAR.
12 | * Score is F1-score for localization task.
13 | * (L) stands for score in [leader-board](http://rrc.cvc.uab.es/).
14 | * If the reported score in leader-board is somewhat different from the paper, (L) is provided.
15 | * `*CODE` means official code and `CODE(M)` means that traiend model is provided.
16 |
17 | *Conf.* | *Date* | *Title* | *IC13* | *IC15* | *Resources* |
18 | :---: | :---: |:--- | :---: | :---: | :---: |
19 | '14-ECCV | 14/10/07 | [Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees]( http://www.whuang.org/papers/whuang2014_eccv.pdf) |
20 | 15-CVPR | 15/06/01 | [Symmetry-based text line detection in natural scenes](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zhang_Symmetry-Based_Text_Line_2015_CVPR_paper.pdf) | [0.8043](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=2197) | | [`PRJ`](http://mclab.eic.hust.edu.cn/~xbai/text/symmetry/SymmetryTextLineDetection.html)
[`CODE`](https://github.com/stupidZZ/Symmetry_Text_Line_Detection) |
21 | '16-TIP | 15/10/12 | [Text-Attentional Convolutional Neural Networks for Scene Text Detection](https://arxiv.org/pdf/1510.03283.pdf) | [0.8165](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=7187) |
22 | '15-ICCV | 15/12/13 | [Text Flow : A Unified Text Detection System in Natural Scene Images](https://pdfs.semanticscholar.org/11a0/8ced22775a217ba78c566528ed44ea98e3e3.pdf) |0.8025 |
23 | '16-arXiv | 16/03/31 | [Accurate Text Localization in Natural Image with Cascaded Convolutional TextNetwork](https://arxiv.org/pdf/1603.09423.pdf) | 0.86 | |
24 | '16-CVPR | 16/04/14 | [Multi-Oriented Text Detection with Fully Convolutional Networks](https://arxiv.org/pdf/1604.04018.pdf) | 0.83 | 0.54 | [`*TORCH(M)`](https://github.com/stupidZZ/FCN_Text)
25 | '16-CVPR | 16/04/22 | [Synthetic Data for Text Localisation in Natural Images](http://www.robots.ox.ac.uk/~ankush/textloc.pdf) | 0.847
(L)[0.8359](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=3820) | | [`CODE`](https://github.com/ankush-me/SynthText)
[`DB`](http://www.robots.ox.ac.uk/~vgg/data/scenetext/)
26 | '16-arXiv | 16/06/29 | [Scene Text Detection Via Holistic, Multi-Channel Prediction](https://arxiv.org/pdf/1606.09002.pdf) |0.8433 | 0.6477 |
27 | '16-ECCV | 16/09/12 | [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://arxiv.org/pdf/1609.03605.pdf) | [0.8215](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=13931) | [0.6085](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=13930) | [`*CAFFE(M)`](https://github.com/tianzhi0549/CTPN)
[`CAFFE`](https://github.com/qingswu/CTPN)
[`TF(M)`](https://github.com/eragonruan/text-detection-ctpn)
[`TF`](https://github.com/Li-Ming-Fan/OCR-DETECTION-CTPN)
[`DEMO`](http://textdet.com/)
[`BLOG(CH)`](http://slade-ruan.me/2017/10/22/text-detection-ctpn/)
28 | '17-AAAI | 16/11/21 |[TextBoxes: A fast text detector with a single deep neural network](https://arxiv.org/pdf/1611.06779.pdf) | 0.85
(L)[0.8767](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=21928) | | [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes)
[`TF`](https://github.com/shinjayne/shinTB)
[`BLOG(KR)`](http://jaynewho.com/post/6)
29 | '18-TM | 17/03/03 | [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://arxiv.org/pdf/1703.01086.pdf) | [0.9125](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=15904) | [0.8020](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=17393) | [`*CAFFE`](https://github.com/mjq11302010044/RRPN)
30 | '17-CVPR | 17/03/04 | [Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection](https://arxiv.org/pdf/1703.01425.pdf) | | [0.7064](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=13007)
31 | '17-CVPR | 17/03/19 | [Detecting Oriented Text in Natural Images by Linking Segments](https://arxiv.org/pdf/1703.06520.pdf) | 0.853 | 0.75
(L)[0.7636](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=29245)| [`*TF(M)`](https://github.com/bgshih/seglink)
[`TF(M)`](https://github.com/dengdan/seglink)
[`SLIDE`](http://mclab.eic.hust.edu.cn/~xbai/SpotlightPPT/TextDetection-seglink-spotlight-CVPR17.pdf)
[`VIDEO`](https://www.youtube.com/watch?v=w0vZWUi-m0c) |
32 | '17-arXiv | 17/03/24 | [Deep Direct Regression for Multi-Oriented Scene Text Detection](https://arxiv.org/pdf/1703.08289.pdf) | 0.86 | 0.81 |
33 | '17-arXiv | 17/04/03 | [Cascaded Segmentation-Detection Networks for Word-Level Text Spotting](https://arxiv.org/pdf/1704.00834.pdf) | 0.86 | 0.71 |
34 | '17-CVPR | 17/04/11 | [EAST: An Efficient and Accurate Scene Text Detector](https://arxiv.org/pdf/1704.03155.pdf) | | 0.8072
(L)[0.8038](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=29855) | [`TF(M)`](https://github.com/argman/EAST)
[`TF`](https://github.com/AKSHAYUBHAT/EAST)
[`PYTORCH(M)`](https://github.com/SakuraRiven/EAST)
[`PYTORCH`](https://github.com/songdejia/EAST)
[`DEMO`](http://east.zxytim.com/)
[`KERAS(M)`](https://github.com/kurapan/EAST)
[`VIDEO`](https://www.youtube.com/watch?v=o5asMTdhmvA)
35 | '17-ICIP | 17/05/15 | [WordFence: Text Detection in Natural Images with Border Awareness](https://arxiv.org/pdf/1705.05483.pdf) | 0.86 |
36 | '17-arXiv | 17/06/30 | [R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection](https://arxiv.org/pdf/1706.09579.pdf) | 0.8773 | 0.8254 | [`TF(M)`](https://github.com/DetectionTeamUCAS/R2CNN_Faster-RCNN_Tensorflow)
[`CAFFE(M)`](https://github.com/beacandler/R2CNN)
37 | '17-CVPR | 17/07/21 | [Multi-scale FCN with Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting In The Wild](http://openaccess.thecvf.com/content_cvpr_2017/papers/He_Multi-Scale_FCN_With_CVPR_2017_paper.pdf) | 0.85 | 0.63 |
38 | '17-arXiv | 17/08/17 | [Deep Scene Text Detection with Connected Component Proposals](https://arxiv.org/pdf/1708.05133.pdf) | 0.919 |
39 | '17-ICCV | 17/08/22 | [WordSup: Exploiting Word Annotations for Character based Text Detection](https://arxiv.org/pdf/1708.06720) | 0.9064 | 0.7816 |
40 | '17-ICCV | 17/09/01 | [Single Shot Text Detector with Regional Attention](https://arxiv.org/pdf/1709.00138.pdf) | 0.8704 | [0.7691](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=18294) | [`*CAFFE(M)`](https://github.com/BestSonny/SSTD)
[`PYTORCH`](https://github.com/HotaekHan/SSTDNet)
[`VIDEO`](https://www.youtube.com/watch?v=oBWVgz685-k)
41 | '17-arXiv | 17/09/11 | [Fused Text Segmentation Networks for Multi-oriented Scene Text Detection](https://arxiv.org/pdf/1709.03272.pdf) | | [0.8414](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=30447) |
42 | '17-ICCV | 17/10/13 | [WeText: Scene Text Detection under Weak Supervision](https://arxiv.org/pdf/1710.04826.pdf) | 0.869
(L)[0.8313](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=20665) |
43 | '17-ICCV | 17/10/22 | [Self-organized Text Detection with Minimal Post-processing via Border Learning](http://openaccess.thecvf.com/content_ICCV_2017/papers/Wu_Self-Organized_Text_Detection_ICCV_2017_paper.pdf) | 0.84 | | [`*KERAS(M)`](https://gitlab.com/rex-yue-wu/ISI-PPT-Text-Detector)
44 | '17-ICDAR | 17/11/11 | [Deep Residual Text Detection Network for Scene Text](https://arxiv.org/pdf/1711.04147.pdf) | 0.9117
(L)[0.8925](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=21966) |
45 | '18-AAAI | 17/11/12 | [Feature Enhancement Network: A Refined Scene Text Detector](https://arxiv.org/pdf/1711.04249.pdf) | [0.9161](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=28362) |
46 | '17-arXiv | 17/11/30 | [ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene](https://arxiv.org/pdf/1711.11249.pdf) | | 0.759 |
47 | '18-AAAI | 18/01/04 | [PixelLink: Detecting Scene Text via Instance Segmentation](https://arxiv.org/pdf/1801.01315.pdf) | 0.881 | [0.8519](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=30576) | [`*TF(M)`](https://github.com/ZJULearning/pixel_link) [`TF`](https://github.com/BowieHsu/tensorflow_ocr)
48 | '18-CVPR | 18/01/05 | [FOTS: Fast Oriented Text Spotting with a Unified Network](https://arxiv.org/pdf/1801.01671.pdf) | [0.925](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=1&m=34624) | [0.8984](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=34625) | [`PYTORCH`](https://github.com/jiangxiluning/FOTS.PyTorch)
[`PYTORCH`](https://github.com/xieyufei1993/FOTS)
[`VIDEO`](https://www.youtube.com/watch?v=F7TTYlFr2QM) |
49 | '18-TIP | 18/01/09 | [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://arxiv.org/pdf/1801.02765.pdf) | 0.88 | 0.829
(L)[0.8475](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=29660) | [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes_plusplus)
50 | '18-CVPR | 18/02/27 | [Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation](https://arxiv.org/pdf/1802.08948.pdf) | 0.88 | 0.843 |[`*PYTORCH(M)`](https://github.com/lvpengyuan/corner)
51 | '18-CVPR | 18/03/09 | [An end-to-end TextSpotter with Explicit Alighment and Attention](https://arxiv.org/pdf/1803.03474.pdf) | 0.9 | 0.87 |[`*CAFFE(M)`](https://github.com/tonghe90/textspotter)
52 | '18-CVPR | 18/03/14 | [Rotation-Sensitive Regression for Oriented Scene Text Detection](https://arxiv.org/pdf/1803.05265.pdf) | 0.89 | 0.838 | [`*CAFFE(M)`](https://github.com/MhLiao/RRD)
53 | '18-arXiv | 18/04/08 | [Detecting Multi-Oriented Text with Corner-based Region Proposals](https://arxiv.org/pdf/1804.02690.pdf) | 0.876 | 0.845 | [`*CAFFE(M)`](https://github.com/xhzdeng/crpn)
54 | '18-arXiv | 18/04/24 | [An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches](https://arxiv.org/pdf/1804.09003.pdf) | 0.92 | 0.86 |
55 | '18-IJCAI | 18/05/03 | [IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection](https://arxiv.org/pdf/1805.01167.pdf) | | [0.9047](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=34989) |
56 | '18-arXiv | 18/06/07 | [Shape Robust Text Detection with Progressive Scale Expansion Network](https://arxiv.org/pdf/1806.02559.pdf) | | [0.8721](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=1&m=37493) | [`PRJ`](https://github.com/whai362/PSENet)
57 | '18-ECCV | 18/07/04 | [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://arxiv.org/pdf/1807.01544.pdf) | | 0.826 | [`PYTORCH`](https://github.com/princewang1994/TextSnake.pytorch)
58 | '18-ECCV | 18/07/06 | [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://arxiv.org/pdf/1807.02242.pdf) | 0.917 | 0.86 |
59 | '18-ECCV | 18/07/10 | [Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping](https://arxiv.org/pdf/1807.03547.pdf) | 0.892 |
60 | '19-AAAI | 18/11/21 | [Scene Text Detection with Supervised Pyramid Context Network](https://arxiv.org/pdf/1811.08605.pdf) | 0.921 | 0.872 |
61 | '19-TIP | 18/12/04 | [TextField: Learning A Deep Direction Field for Irregular Scene Text Detection](https://arxiv.org/pdf/1812.01393.pdf) | | 0.824 | [`*CAFFE(M)`](https://github.com/YukangWang/TextField)
62 | '19-CVPR | 19/03/21 | [Towards Robust Curve Text Detection with Conditional Spatial Expansion](https://arxiv.org/pdf/1903.08836.pdf) | | | |
63 | '19-CVPR | 19/03/28 | [Shape Robust Text Detection with Progressive Scale Expansion Network](https://arxiv.org/pdf/1903.12473.pdf) | | 0.857 | [`TF(M)`](https://github.com/liuheng92/tensorflow_PSENet)
64 | '19-CVPR | 19/04/03 | [Character Region Awareness for Text Detection](https://arxiv.org/pdf/1904.01941.pdf) | 0.952 | 0.869 |[`*PYTORCH(M)`](https://github.com/clovaai/CRAFT-pytorch)
[`VIDEO`](https://www.youtube.com/watch?v=HI8MzpY8KMI)
[`PYTORCH`](https://github.com/guruL/Character-Region-Awareness-for-Text-Detection-)
[`TF(M)`](https://github.com/namedysx/CRAFT-tensorflow)
[`KERAS`](https://github.com/RubanSeven/CRAFT_keras)
[`BLOG_CH`](https://medium.com/@xiaosean5408/craft簡介-character-region-awareness-for-text-detection-a5c782408f00)
[`BLOG_KR`](https://data-newbie.tistory.com/187)
[`BLOG_KR`](https://medium.com/qandastudy/character-region-awareness-for-text-detection-craft-review-a7542779e037)
[`BLOG_KR`](https://github.com/chullhwan-song/Reading-Paper/issues/136)|
65 | '19-CVPR | 19/04/13 | [Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes Screen reader support enabled](https://arxiv.org/pdf/1904.06535.pdf) | | 0.877 | |
66 | '19-CVPR | 19/06/16 | [Learning Shape-Aware Embedding for Scene Text Detection](http://jiaya.me/papers/textdetection_cvpr19.pdf) | | 0.877 | |
67 | '19-CVPR | 19/06/16 | [Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation](https://arxiv.org/pdf/1905.05980.pdf) | 0.917 | 0.876 | |
68 | '19-ICCV | 19/08/16 | [Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network](https://arxiv.org/abs/1908.05900) | | 0.829 | |
69 | '19-ICCV | 19/09/02 | [Geometry Normalization Networks for Accurate Scene Text Detection](https://arxiv.org/abs/1909.00794) | | 0.8852 | |
70 | '19-AAAI | 19/11/20 | [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/abs/1911.08947) | | 0.847 | |
71 |
72 |
73 |
74 |
75 |
76 | ## Text Recognition
77 | * Papers are sorted by published date.
78 | * IC is shorts for ICDAR.
79 | * Score is word-accuracy for recognition task.
80 | * For results on IC03, IC13, and IC15 dataset, papers used different numbers of samples per paper,
81 | but we did not distinguish between them
82 | * `*CODE` means official code and `CODE(M)` means that trained model is provided.
83 |
84 | *Conf.* | *Date* | *Title* | *SVT* | *IIIT5k* | *IC03* | *IC13* | *Resources* |
85 | :---: | :---: |:--- | :---: | :---: | :---: | :---: | :---: |
86 | '15-ICLR | 14/12/18 | [Deep structured output learning for unconstrained text recognition](https://arxiv.org/pdf/1412.5903.pdf) | 0.717 | |0.896 | 0.818 | [`TF`](https://github.com/AlexandreSev/Structured_Data)
[`SLIDE`](https://www.robots.ox.ac.uk/~vgg/publications/2015/Jaderberg15a/presentation.pdf)
[`VIDEO`](https://www.youtube.com/watch?v=NYkG38RCoRg)
87 | '16-IJCV | 15/05/07 | [Reading text in the wild with convolutional neural networks](https://arxiv.org/pdf/1412.1842.pdf) | 0.807 | | 0.933 | 0.908 | [`KERAS`](https://github.com/mathDR/reading-text-in-the-wild)
88 | '16-AAAI | 15/06/14 | [Reading Scene Text in Deep Convolutional Sequences](https://arxiv.org/pdf/1506.04395.pdf)
89 | '17-TPAMI | 15/07/21 | [An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition](https://arxiv.org/pdf/1507.05717.pdf) | 0.808 | 0.782 | 0.894 | 0.867 | [`TORCH(M)`](https://github.com/bgshih/crnn)
[`TF`](https://github.com/weinman/cnn_lstm_ctc_ocr)
[`TF`](https://github.com/watsonyanghx/CNN_LSTM_CTC_Tensorflow)
[`TF`](https://github.com/MaybeShewill-CV/CRNN_Tensorflow)
[`TF`](https://github.com/bai-shang/OCR_TF_CRNN_CTC)
[`PYTORCH`](https://github.com/meijieru/crnn.pytorch)
[`PYTORCH(M)`](https://github.com/BelBES/crnn-pytorch)
[`BLOG(KR)`](https://medium.com/@mldevhong/%EB%85%BC%EB%AC%B8-%EB%B2%88%EC%97%AD-rcnn-an-end-to-end-trainable-neural-network-for-image-based-sequence-recognition-and-its-f6456886d6f8)
90 | '16-CVPR | 16/03/09 | [Recursive Recurrent Nets with Attention Modeling for OCR in the Wild](https://arxiv.org/pdf/1603.03101.pdf) | 0.807 | 0.784 | 0.887 | 0.9 |
91 | '16-CVPR | 16/03/12 | [Robust scene text recognition with automatic rectification](https://arxiv.org/pdf/1603.03915.pdf) | 0.819 | 0.819 | 0.901 | 0.886 | [`PYTORCH`](https://github.com/marvis/ocr_attention)
[`PYTORCH`](https://github.com/WarBean/tps_stn_pytorch)
92 | '16-CVPR | 16/06/27 | [CNN-N-Gram for Handwriting Word Recognition](https://www.cs.tau.ac.il/~wolf/papers/CNNNGram.pdf) | 0.8362 | | | | [`VIDEO`](https://www.youtube.com/watch?v=czc2Ipm3Bis)
93 | '16-BMVC | 16/09/19 | [STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition](http://www.visionlab.cs.hku.hk/publications/wliu_bmvc16.pdf) | 0.836 | 0.833 | 0.899 | 0.891 |
94 | '17-arXiv | 17/07/27 | [STN-OCR: A single Neural Network for Text Detection and Text Recognition](https://arxiv.org/pdf/1707.08831.pdf) | 0.798 | 0.86 | | 0.903 | [`*MXNET(M)`](https://github.com/Bartzi/stn-ocr)
[`PRJ`](https://bartzi.de/research/stn-ocr)
[`BLOG`](https://medium.com/@Synced/stn-ocr-a-single-neural-network-for-text-detection-and-text-recognition-220debe6ded4)
95 | '17-IJCAI | 17/08/19 | [Learning to Read Irregular Text with Attention Mechanisms](https://faculty.ist.psu.edu/zzhou/paper/IJCAI17-IrregularText.pdf) |
96 | '17-arXiv | 17/09/06 | [Scene Text Recognition with Sliding Convolutional Character Models](https://arxiv.org/pdf/1709.01727.pdf) | 0.765 | 0.816 | 0.845 | 0.852 |
97 | '17-ICCV | 17/09/07 | [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://arxiv.org/pdf/1709.02054.pdf) | 0.859 | 0.874 | 0.942 | 0.933 |
98 | '18-CVPR | 17/11/12 | [AON: Towards Arbitrarily-Oriented Text Recognition](https://arxiv.org/pdf/1711.04226.pdf) | 0.828 |0.87 | 0.915 ||[`TF`](https://github.com/huizhang0110/AON)
99 | '17-NIPS | 17/12/04 | [Gated Recurrent Convolution Neural Network for OCR](https://papers.nips.cc/paper/6637-gated-recurrent-convolution-neural-network-for-ocr.pdf) | 0.815 | 0.808 | 0.978 | | [`*TORCH(M)`](https://github.com/Jianfeng1991/GRCNN-for-OCR)
100 | '18-AAAI | 18/01/04 | [Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition](http://www.visionlab.cs.hku.hk/publications/wliu_aaai18.pdf) | 0.844 | 0.836 | 0.915 | 0.908 |
101 | '18-AAAI | 18/01/04 | [SqueezedText: A Real-time Scene Text Recognition by Binary Convolutional Encoder-decoder Network](https://pdfs.semanticscholar.org/0e59/f7d7e9c9380b425a94038c7a2500b2f6063a.pdf) | | 0.87 | 0.931 | 0.929 |
102 | '18-CVPR | 18/05/09 | [Edit Probability for Scene Text Recognition](https://arxiv.org/pdf/1805.03384.pdf) | 0.875 | 0.883 | 0.946 | 0.944 |
103 | '18-TPAMI | 18/06/25 | [ASTER: An Attentional Scene Text Recognizer with Flexible Rectification](http://122.205.5.5:8071/UpLoadFiles/Papers/ASTER_PAMI18.pdf) | 0.936 | 0.934 | 0.945 | 0.918 | [`*TF(M)`](https://github.com/bgshih/aster)
[`PYTORCH`](https://github.com/ayumiymk/aster.pytorch)
104 | '18-ECCV | 18/09/08 | [Synthetically Supervised Feature Learning for Scene Text Recognition](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yang_Liu_Synthetically_Supervised_Feature_ECCV_2018_paper.pdf) | 0.871 | 0.894 | 0.947 | 0.94 |
105 | '19-AAAI | 18/09/18 | [Scene Text Recognition from Two-Dimensional Perspective](https://arxiv.org/pdf/1809.06508.pdf) | 0.821 | 0.92 | | 0.914 |
106 | '19-AAAI | 18/11/02 | [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://arxiv.org/pdf/1811.00751.pdf) | 0.845 | 0.915 | | 0.91 | [`*TORCH(M)`](https://github.com/wangpengnorman/SAR-Strong-Baseline-for-Text-Recognition)
107 | '19-CVPR | 18/12/14 | [ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification](https://arxiv.org/pdf/1812.05824.pdf) | 0.902 | 0.933 | | 0.913 | [PRJ](https://github.com/fnzhan/ESIR)
108 | '19-PR | 19/01/10 | [MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition](https://arxiv.org/pdf/1901.03003.pdf) | 0.883 | 0.912 | 0.950 | 0.924 | [`*PYTORCH(M)`](https://github.com/Canjie-Luo/MORAN_v2)
109 | '19-ICCV | 19/04/03 | [What is wrong with scene text recognition model comparisons? dataset and model analysis](https://arxiv.org/pdf/1904.01906.pdf) | 0.875 | | 0.949 | 0.936 | [`*PYTORCH(M)`](https://github.com/clovaai/deep-text-recognition-benchmark)
[`BLOG_KR`](https://data-newbie.tistory.com/156)
110 | '19-CVPR | 19/04/18 | [Aggregation Cross-Entropy for Sequence Recognition](https://arxiv.org/pdf/1904.08364.pdf) | 0.826 | 0.823 | 0.921 | 0.897 | [`*PYTORCH`](https://github.com/summerlvsong/Aggregation-Cross-Entropy) |
111 | '19-CVPR | 19/06/16 | [Sequence-to-Sequence Domain Adaptation Network for Robust Text Image Recognition](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Sequence-To-Sequence_Domain_Adaptation_Network_for_Robust_Text_Image_Recognition_CVPR_2019_paper.pdf) | 0.845 | 0.838 | 0.921 | 0.918 | |
112 | '19-ICCV | 19/08/06 | [Symmetry-constrained Rectification Network for Scene Text Recognition](https://arxiv.org/abs/1908.01957) | 0.889 | 0.944 | 0.95 | 0.939 |
113 | '20-AAAI | 19/12/28 | [TextScanner: Reading Characters in Order for Robust Scene Text Recognition](https://arxiv.org/abs/1912.12422) | 0.895 | 0.926 | | 0.925 |
114 | '20-AAAI | 19/12/21 | [Decoupled Attention Network for Text Recognition](https://arxiv.org/abs/1912.10205) | 0.892 | 0.943 | 0.95 | 0.939 | [`*PYTORCH(M)`](https://github.com/Wang-Tianwei/Decoupled-attention-network)
115 | '20-AAAI | 20/02/04 | [GTC: Guided Training of CTC](https://arxiv.org/abs/2002.01276) | 0.929 | 0.955 | 0.952 | 0.943 |
116 |
117 |
118 |
119 |
120 |
121 |
122 | ## End-to-End Text Recognition
123 | * Papers are sorted by published date.
124 | * IC is shorts for ICDAR.
125 | * Score is F1-score for generic task.
126 | * (L) stands for score in [leader-board](http://rrc.cvc.uab.es/).
127 | * `*CODE` means official code and `CODE(M)` means that trained model is provided.
128 |
129 | *Conf.* | *Date* | *Title* | *IC03* | *IC13* | *IC15* | *Resources* |
130 | :---: | :---: |:--- | :---: | :---: | :---: | :---: |
131 | '12-ICPR | 12/11/11 | [End-to-end text recognition with convolutional neural networks](https://ai.stanford.edu/~ang/papers/ICPR12-TextRecognitionConvNeuralNets.pdf) | 0.67 | | | [`*CODE`](http://cs.stanford.edu/people/twangcat/ICPR2012_code/SceneTextCNN_demo.tar)
132 | '14-ECCV | 14/09/06 | [Deep Features for Text Spotting](https://www.robots.ox.ac.uk/~vgg/publications/2014/Jaderberg14/jaderberg14.pdf) | 0.75 | | | [`PRJ`](http://www.robots.ox.ac.uk/~vgg/research/text/)
[`MATLAB`](https://bitbucket.org/jaderberg/eccv2014_textspotting)
133 | '15-IJCV | 15/05/07 | [Reading Text in the Wild with Convolutional Neural Networks](https://arxiv.org/pdf/1412.1842.pdf) | 0.70 | 0.77 | | [`KERAS`](https://github.com/mathDR/reading-text-in-the-wild)
134 | '15-TPAMI | 15/10/30 | [Real-time Lexicon-free Scene Text Localization and Recognition](http://cmp.felk.cvut.cz/~neumalu1/Neumann_TPAMI2015.pdf) | | 0.542 | 0.156 |
135 | '16-arXiv | 16/04/10 | [TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild](https://arxiv.org/pdf/1604.02619.pdf) | | 0.6843 | 0.4718
(L)[0.533](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=4&m=7807) | [`*CAFFE(M)`](https://github.com/lluisgomez/TextProposals)
136 | '17-AAAI | 16/11/21 | [TextBoxes: A fast text detector with a single deep neural network](https://arxiv.org/pdf/1611.06779.pdf) | | 0.84 | | [`TF`](https://github.com/shinjayne/shinTB)
[`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes)
[`BLOG_KR`](http://jaynewho.com/post/6)
137 | '17-ICCV | 17/07/13 | [Towards End-to-end Text Spotting with Convolution Recurrent Neural Network](https://arxiv.org/pdf/1707.03985.pdf) | | 0.8459 | | [`VIDEO`](https://www.youtube.com/watch?v=j0guWqBJ0lA)
138 | '17-ICCV | 17/10/22 | [Deep TextSpotter An End-to-End Trainable Scene Text Localization and Recognition Framework](http://openaccess.thecvf.com/content_ICCV_2017/papers/Busta_Deep_TextSpotter_An_ICCV_2017_paper.pdf) | | 0.77 | 0.47 | [`VIDEO`](https://www.youtube.com/watch?v=VcNSQGO0j7s)
[`*CAFFE(M)`](https://github.com/MichalBusta/DeepTextSpotter)
139 | '18-CVPR | 18/01/05 | [FOTS: Fast Oriented Text Spotting with a Unified Network](https://arxiv.org/pdf/1801.01671.pdf) | | [0.8477](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=4&m=34627) | [0.6533](http://rrc.cvc.uab.es/?ch=4&com=evaluation&view=method_info&task=4&m=34626) | [`VIDEO`](https://www.youtube.com/watch?v=F7TTYlFr2QM)
[`TF(M)`](https://github.com/Pay20Y/FOTS_TF)
140 | '18-TIP | 18/01/09 | [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://arxiv.org/pdf/1801.02765.pdf) | | [0.8465](http://rrc.cvc.uab.es/?ch=2&com=evaluation&view=method_info&task=4&m=27895) | 0.519 | [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes_plusplus)
141 | '18-CVPR | 18/03/09 | [An end-to-end TextSpotter with Explicit Alignment and Attention](https://arxiv.org/pdf/1803.03474.pdf) | | 0.86 | 0.63 | [`*CAFFE(M)`](https://github.com/tonghe90/textspotter)
142 | '18-TPAMI | 18/06/25 | [ASTER: An Attentional Scene Text Recognizer with Flexible Rectification](http://122.205.5.5:8071/UpLoadFiles/Papers/ASTER_PAMI18.pdf) | | | 0.64 | [`*TF(M)`](https://github.com/bgshih/aster)
143 | '18-ECCV | 18/07/06 | [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://arxiv.org/pdf/1807.02242.pdf) | | 0.865 | 0.624 |
144 | '19-ICCV | 19/08/24 | [Towards Unconstrained End-to-End Text Spotting](https://arxiv.org/pdf/1908.09231.pdf) | | | 0.6994 | [`BLOG_KR`](https://www.notion.so/Towards-Unconstrained-End-to-End-Text-Spotting-0c66c692950f458e9a1323db2a79d143)
145 | '19-ICCV | 19/10/17 | [Convolutional Character Networks](https://arxiv.org/abs/1910.07954) | | | 0.7108 | [`*PYTORCH(M)`](https://github.com/MalongTech/research-charnet)
146 | '19-ICCV | 19/10/27 | [TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting](http://openaccess.thecvf.com/content_ICCV_2019/papers/Feng_TextDragon_An_End-to-End_Framework_for_Arbitrary_Shaped_Text_Spotting_ICCV_2019_paper.pdf) | | | 0.6537 |
147 | '20-AAAI | 19/11/21 | [All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting](https://arxiv.org/pdf/1911.09550) | | 0.841 | 0.641 |
148 | '20-AAAI | 20/02/12 | [Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting](https://arxiv.org/abs/2002.06820) | | 0.858 | 0.651 |
149 |
150 |
151 |
152 |
153 | ## Others
154 | * Papers are sorted by published date.
155 | * `*CODE` means official code and `CODE(M)` means that trained model is provided.
156 |
157 | *Conf.* | *Date* | *Title* | *Description* | *Resources* |
158 | :---: | :---: |:--- | :---: | :---: |
159 | '14-NIPS | 14/06/09 | [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://arxiv.org/pdf/1406.2227.pdf) | Dataset | [`PRJ`](http://www.robots.ox.ac.uk/~vgg/data/text/)
160 | '17-ECCV | 17/02/13 | [End-to-End Interpretation of the French Street Name Signs Dataset](https://arxiv.org/pdf/1702.03970.pdf) | Dataset (FSNS) | [`*TF(M)`](https://github.com/tensorflow/models/tree/master/research/attention_ocr)
161 | '17-arXiv | 17/04/11 | [Attention-based Extraction of Structured Information from Street View Imagery](https://arxiv.org/pdf/1704.03549.pdf) | FSNS | [`*TF(M)`](https://github.com/tensorflow/models/tree/master/research/attention_ocr)
[`TF`](https://github.com/da03/Attention-OCR)
[`TF`](https://github.com/emedvedev/attention-ocr)
[`LUA`](https://github.com/da03/torch-Attention-OCR)
[`BLOG_KR`](https://norman3.github.io/papers/docs/attention_ocr.html)
162 | '17-CVPR | 17/07/21 | [Unambiguous Text Localization and Retrieval for Cluttered Scenes](http://openaccess.thecvf.com/content_cvpr_2017/papers/Rong_Unambiguous_Text_Localization_CVPR_2017_paper.pdf) | Text Retrieval
163 | '17-AAAI | 17/10/22 | [Detection and Recognition of Text Embedded in Online Images via Neural Context Models](http://s-space.snu.ac.kr/bitstream/10371/116866/1/aaai2017_cameraready.pdf) | Dataset | [`PRJ`](https://github.com/cmkang/CTSN)
164 | '18-CVPR | 17/11/17 | [Separating Style and Content for Generalized Style Transfer](https://arxiv.org/pdf/1711.06454.pdf) | Font Style
165 | '17-arXiv | 17/12/06 | [Detecting Curve Text in the Wild New Dataset and New Solution](https://arxiv.org/pdf/1712.02170.pdf) | Dataset (CTW 1500) | [`PRJ`](https://github.com/Yuliang-Liu/Curve-Text-Detector)
166 | '18-AAAI | 17/12/14 | [SEE: Towards Semi-Supervised End-to-End Scene Text Recognition](https://arxiv.org/pdf/1712.05404.pdf) | FSNS | [`PRJ`](https://bartzi.de/research/see)
[`*CHAINER(M)`](https://github.com/Bartzi/see)
167 | '17-CVPR | 18/06/07 | [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networks](https://arxiv.org/pdf/1706.02337.pdf) | Document Layout | [`PRJ`](http://personal.psu.edu/xuy111/projects/cvpr2017_doc.html)
168 | '18-CVPR | 18/06/19 | [DocUNet: Document Image Unwarping via A Stacked U-Net](http://www.juew.org/publication/DocUNet.pdf) | Document Dewarping | [`PRJ`](http://www3.cs.stonybrook.edu/~cvl/docunet.html)
169 | '18-CVPR | 18/06/19 | [Document Enhancement using Visibility Detection](http://webee.technion.ac.il/~ayellet/Ps/18-KKT.pdf) | Document Enhancement | [`PRJ`](http://cgm.technion.ac.il/Computer-Graphics-Multimedia/Software/VisibilityDetection/)
170 | '18-IJCAI | 18/06/22 | [Multi-Task Handwritten Document Layout Analysis](https://arxiv.org/pdf/1806.08852.pdf) | Document Layout
171 | '18-ECCV | 18/07/09 | [Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes](https://arxiv.org/pdf/1807.03021.pdf) | Dataset | [`PRJ`](https://github.com/fnzhan/Verisimilar-Image-Synthesis-for-Accurate-Detection-and-Recognition-of-Texts-in-Scenes)
172 | '19-AAAI | 18/12/03 | [EnsNet: Ensconce Text in the Wild](https://arxiv.org/pdf/1812.00723.pdf) | Text Removal | [`DB`](https://github.com/HCIILAB/Scene-Text-Removal)
173 | '19-CVPR | 18/12/14 | [Spatial Fusion GAN for Image Synthesis](https://arxiv.org/pdf/1812.05840.pdf) | Dataset | [`DB`](https://github.com/fnzhan/SF-GAN)
174 | '19-AAAI | 19/01/27 | [Hierarchical Encoder with Auxiliary Supervision for Table-to-text Generation: Learning Better Representation for Tables](https://www.aaai.org/Papers/AAAI/2019/AAAI-LiuT.3205.pdf) | TableToText |
175 | '19-AAAI | 19/01/27 | [A Radical-aware Attention-based Model for Chinese Text Classification](https://www.aaai.org/Papers/AAAI/2019/AAAI-TaoH.5441.pdf) | Chinese Character Classification |
176 | '19-CVPR | 19/02/25 | [Handwriting Recognition in Low-resource Scripts using Adversarial Learning](https://arxiv.org/pdf/1811.01396.pdf) | Handwritting Recognition | [`TF`](https://github.com/AyanKumarBhunia/Handwriting_Recogition_using_Adversarial_Learning)
177 | '19-CVPR | 19/03/27 | [Tightness-aware Evaluation Protocol for Scene Text Detection](https://arxiv.org/pdf/1904.00813.pdf) | Evaluation | [`CODE`](https://github.com/Yuliang-Liu/TIoU-metric)
178 | '19-ICCV | 19/05/31 | [Scene Text Visual Question Answering](https://arxiv.org/pdf/1905.13648v2) | Dataset | [`ICDAR_DB`](https://rrc.cvc.uab.es/?ch=11)
179 | '19-CVPR | 19/06/16 | [DynTypo: Example-based Dynamic Text Effects Transfer](https://menyifang.github.io/projects/DynTypo/DynTypo_files/Paper_DynTypo_CVPR19.pdf) | Text Effects | [`PRJ`](https://menyifang.github.io/projects/DynTypo/DynTypo.html)
[`VIDEO`](https://youtu.be/FkFQ6bV1s-o)
180 | '19-CVPR | 19/06/16 | [Typography with Decor: Intelligent Text Style Transfer](http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Typography_With_Decor_Intelligent_Text_Style_Transfer_CVPR_2019_paper.pdf) | Text Effects | [`*PYTORCH(M)`](https://daooshee.github.io/Typography2019/)
181 | '19-CVPR | 19/06/16 | [An Alternative Deep Feature Approach to Line Level Keyword Spotting](http://openaccess.thecvf.com/content_CVPR_2019/papers/Retsinas_An_Alternative_Deep_Feature_Approach_to_Line_Level_Keyword_Spotting_CVPR_2019_paper.pdf) | Kyeword Spotting
182 | '19-ICCV | 19/07/23 | [GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition](https://arxiv.org/abs/1907.09653) | Domain Adaptation |
183 | '19-ICCV | 19/09/17 | [Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning](https://arxiv.org/abs/1909.07808) | Dataset | [`ICDAR_DB`](https://rrc.cvc.uab.es/?ch=16)
184 | '19-ICCV | 19/10/02 | [Large-scale Tag-based Font Retrieval with Generative Feature Learning](https://arxiv.org/pdf/1909.02072.pdf) | Font Retrieval |
185 | '19-ICCV | 19/10/27 | [TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts](http://openaccess.thecvf.com/content_ICCV_2019/papers/Hong_TextPlace_Visual_Place_Recognition_and_Topological_Localization_Through_Reading_Scene_ICCV_2019_paper.pdf) | Place Recognition | [`DB`](https://github.com/ziyanghong/dataset)
186 | '19-ICCV | 19/10/27 | [DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks](http://openaccess.thecvf.com/content_ICCV_2019/papers/Das_DewarpNet_Single-Image_Document_Unwarping_With_Stacked_3D_and_2D_Regression_ICCV_2019_paper.pdf) | Document Dewarping | [`*PYTORCH(M)`](https://github.com/cvlab-stonybrook/DewarpNet)
187 |
188 | ## Other lists
189 | * OCR Paper Curation
190 | * [HCIILAB-Detection](https://github.com/HCIILAB/Scene-Text-Detection)
191 | * [HCIILAB-Recognition](https://github.com/HCIILAB/Scene-Text-Recognition)
192 | * [HCIILAB-End2End](https://github.com/HCIILAB/Scene-Text-End2end)
193 | * [whitelok](https://github.com/whitelok/image-text-localization-recognition)
194 | * [tangzhenyu](https://github.com/tangzhenyu/Scene-Text-Understanding)
195 | * [wanghaisheng](https://github.com/wanghaisheng/awesome-ocr)
196 | * [ChanChiChoi](https://github.com/ChanChiChoi/awesome-ocr/blob/master/README.md)
197 | * [handong1587](https://github.com/handong1587/handong1587.github.io/blob/master/_posts/deep_learning/2015-10-09-ocr.md)
198 | * [hs105](https://github.com/hs105/Deep-Learning-for-OCR)
199 |
200 | ## Tutorial Materials
201 | * Lecture slides
202 | * [Irregular Text Detection and Recognition (CBDAR2019 keynote)](http://122.205.5.5:8071/~xbai/Talk_slice/IrregularText-CBDAR2019.pptx)
203 | * [Deep Neural Networks for Scene Text Reading (IC17 Keynote)](http://u-pat.org/ICDAR2017/keynotes/ICDAR2017_Keynote_Prof_Bai.pdf)
204 | * [Oriented Scene Text Detection Revisited (VALSE17 Invited Talk)](http://cloud.eic.hust.edu.cn:8071/~xbai/Talk_slice/Oriented-Scene-Text-Detection-Revisited_VALSE2017.pdf)
205 | * [Scene Text Detection and Recognition (Joint course of Megvii Inc. & Peking Univ.)](https://zsc.github.io/megvii-pku-dl-course/slides/Lecture7(Text%20Detection%20and%20Recognition_20171031).pdf)
206 | * [Classic Text Detectors](https://www.slideshare.net/anyline_io/text-detection-strategies)
207 | * Survey Paper
208 | * [Scene text detection and recognition: recent advances and future trends](https://www.researchgate.net/profile/Xiang_Bai4/publication/286945604_Scene_text_detection_and_recognition_recent_advances_and_future_trends/links/57f720f408ae886b8981d364/Scene-text-detection-and-recognition-recent-advances-and-future-trends.pdf)
209 |
210 | ## Acknowledgment
211 | * This work is done by OCR team in Clova AI powered by NAVER-LINE. NAVER-LINE is an Asian top internet company and develops Clova, a cloud-based AI-assistant platform.
212 | * This repository is scheduled to be updated regularly in accordance with schedules of major AI conferences.
213 |
--------------------------------------------------------------------------------
/detection_ic13_results.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/detection_ic13_results.png
--------------------------------------------------------------------------------
/detection_ic15_results.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/detection_ic15_results.png
--------------------------------------------------------------------------------
/end2end_ic13_ic15_results.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/end2end_ic13_ic15_results.png
--------------------------------------------------------------------------------
/overall_histogram.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/overall_histogram.png
--------------------------------------------------------------------------------
/overall_pi_chart.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/overall_pi_chart.png
--------------------------------------------------------------------------------
/recognition_ic13_results.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/recognition_ic13_results.png
--------------------------------------------------------------------------------
/recognition_iiit5k_results.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/hwalsuklee/awesome-deep-text-detection-recognition/0958b3875043676c61bdf64df95ea81a43ad3c92/recognition_iiit5k_results.png
--------------------------------------------------------------------------------