Awesome

Scene Text Recognition Resources

<p align='right'>Author: 陈晓雪</p> The paper "Text Recognition in the Wild: A Survey" (accepted to appear in ACM Computing Surveys) in arXiv version is available now.

❗❗ Newest Version Can be Found Here ❗❗

This repository is no longer maintaining now, and you can refer to our newest one

Scene Text Recognition Recommendations

Updates

Dec 24, 2019: add 20 papers and update corresponding tables.

Feb 29, 2020: add AAAI-2020 papers and update corresponding tables.

May 8, 2020: add CVPR-2020 papers and update corresponding tables.

Dec 8, 2020: add 11 papers and update corresponding tables. You can download the new Excel prepared by us. (Password: sj2t)

• 1. Datasets
  • 1.1 Regular Latin Datasets
  • 1.2 Irregular Latin Datasets
  • 1.3 Multilingual Datasets
  • 1.4 Synthetic Datasets
  • 1.5 Comparison of the Benchmark Datasets
• 2. Performance Comparison of Recognition Algorithms
  • 2.1 Characteristics Comparison of Recognition Approaches
  • 2.2 Performance Comparison on Benchmark Datasets
    • 2.2.1 Performance Comparison of Recognition Algorithms on Regular Latin Datasets
    • 2.2.2 Performance Comparison of Recognition Algorithms on Irregular Latin Datasets
• 3. Survey
• 4. OCR Service
• 5. References
• 6.Help
• 7.Copyright

<a id="1-datasets"></a>

1. Datasets

<a id="11-regular-latin-datasets"></a>

1.1 Regular Latin Datasets

• IIIT5K[31]：
  • Introduction: The IIIT5K dataset [31] contains 5,000 text instance images: 2,000 for training and 3,000 for testing. It contains words from street scenes and from originally-digital images. Every image is associated with a 50 -word lexicon and a 1,000 -word lexicon. Specifically, the lexicon consists of a ground-truth word and some randomly picked words.
  • Link: IIIT5K-download
• SVT[1]：
  • Introduction: The SVT dataset [1] contains 350 images: 100 for training and 250 for testing. Some images are severely corrupted by noise, blur, and low resolution. Each image is associated with a 50 -word lexicon.
  • Link: SVT-download
• ICDAR 2003(IC03)[33]：
  • Introduction: The IC03 dataset [33] contains 509 images: 258 for training and 251 for testing. Specifically, it contains 867 cropped text instances after discarding images that contain non-alphanumeric characters or less than three characters. Every image is associated with a 50 -word lexicon and a full-word lexicon. Moreover, the full lexicon combines all lexicon words.
  • Link: IC03-download
• ICDAR 2013(IC13)[34]：
  • Introduction: The IC13 dataset [34] contains 561 images: 420 for training and 141 for testing. It inherits data from the IC03 dataset and extends it with new images. Similar to IC03 dataset, the IC13 dataset contains 1,015 cropped text instance images after removing the words with non-alphanumeric characters. No lexicon is associated with IC13 . Notably, 215 duplicate text instance images [65] exist between the IC03 training dataset and the IC13 testing dataset. Therefore, care should be taken regarding the overlapping data when evaluating a model on the IC13 testing data.
  • Link: IC13-download
• SVHN[45]：
  • Introduction: The SVHN [45] dataset contains more than 600,000 digits of house numbers in natural scenes. It is obtained from a large number of street view images using a combination of automated algorithms and the Amazon Mechanical Turk (AMT) framework. The SVHN dataset was typically used for scene digit recognition.
  • Link: SVHN-download

<a id="12-irregular-latin-datasets"></a>

1.2 Irregular Latin Datasets

• SVT-P[35]：
  • Introduction: The SVT-P [35] dataset contains 238 images with 639 cropped text instances. It is specifically designed to evaluate perspective distorted text recognition. It is built based on the original SVT dataset by selecting the images at the same address on Google Street View but with different view angles. Therefore, most text instances are heavily distorted by the non-frontal view angle. Moreover, each image is associated with a 50-word lexicon and a full-word lexicon.
  • Link: SVT-P-download (Password : vnis)
• CUTE80[36]：
  • Introduction: The CUTE80 dataset [36] contains 80 high-resolution images with 288 cropped text instances. It focuses on curved text recognition. Most images in CUTE80 have a complex background, perspective distortion, and poor resolution. No lexicon is associated with CUTE80.
  • Link: CUTE80-download
• ICDAR 2015(IC15)[37]：
  • Introduction: The IC15 dataset [37] contains 1,500 images: 1,000 for training and 500 for testing. Specifically, it contains 2,077 cropped text instances, including more than 200 irregular text samples. As text images were taken by Google Glasses without ensuring the image quality, most of the text is very small, blurred, and multi-oriented. No lexicon is provided.
  • Link: IC15-download
• COCO-Text[38]：
  • Introduction: The COCO-Text dataset [38] contains 63,686 images with 145,859 cropped text instances. It is the first large-scale dataset for text in natural images and also the first dataset to annotate scene text with attributes such as legibility and type of text. However, no lexicon is associated with COCO-Text.
  • Link: COCO-Text-download
• Total-Text[39]：
  • Introduction: The Total-Text dataset [39] contains 1,555 images with 11,459 cropped text instance images. It focuses on curved scene text recognition. Images in Total-Text have more than three different orientations, including horizontal, multi-oriented, and curved. No lexicon is associated with Total-Text.
  • Link: Total-Text-download

<a id="13-multilingual-datasets"></a>

1.3 Multilingual Datasets

• RCTW-17(RCTW competition，ICDAR17)[40]：
  • Introduction: The RCTW-17 dataset contains 12,514 images: 11,514 for training and 1,000 for testing. Most are natural images collected by cameras or mobile phones, whereas others are digital-born. Text instances are annotated with labels, fonts, languages, etc.
  • Link: RCTW-17-download
• MTWI(competition)[41]：
  • Introduction: The MTWI dataset contains 20,000 images. This is the first dataset constructed by Chinese and Latin web text. Most images in MTWI have a relatively high resolution and cover diverse types of web text, including multi-oriented text, tightly-stacked text, and complex-shaped text.
  • Link: MTWI-download (Password:gox9)
• CTW[42]：
  • Introduction: The CTW dataset includes 32,285 high-resolution street view images with 1,018,402 character instances. All images have character-level annotations: the underlying character, the bounding box, and six other attributes.
  • Link: CTW-download
• SCUT-CTW1500[43]：
  • Introduction: The SCUT-CTW1500 dataset contains 1,500 images: 1,000 for training and 500 for testing. In particular, it provides 10,751 cropped text instance images, including 3,530 with curved text. The images are manually harvested from the Internet, image libraries such as Google Open-Image, or phone cameras. The dataset contains a lot of horizontal and multi-oriented text
  • Link: SCUT-CTW1500-download

• LSVT(LSVT competition, ICDAR2019)[57]:
  • Introduction: The LSVT dataset contains 20,000 testing samples, 30,000 fully annotated training samples, and 400,000 training samples with weak annotations (i.e., with partial labels). All images are captured from streets and reflect a large variety of complicated real-world scenarios, e.g., store fronts and landmarks.
  • Link: LSVT-download
• ArT(ArT competition, ICDAR2019)[58]:
  • Introduction: The ArT dataset [58] contains 10,166 images: 5,603 for training and 4,563 for testing. ArT is a combination of Total-Text, SCUT-CTW 1500 , and Baidu Curved Scene Text 4 , which was collected to introduce the arbitrary-shaped text problem. Moreover, all existing text shapes (i.e., horizontal, multi-oriented, and curved) have multiple occurrences in the ArT dataset.
  • Link: ArT-download
• ReCTS-25k(ReCTS competition, ICDAR2019)[59]:
  • Introduction: The ReCTS-25k dataset [59] contains 25,000 images: 20,000 for training and 5,000 for testing. All the images are from the Meituan-Dianping Group, collected by Meituan business mer- chants, using phone cameras under uncontrolled conditions. Specifically, ReCTS-25 k dataset mainly contains images of Chinese text on signboards.
  • Link: ReCTS-download
• MLT(MLTcompetition, ICDAR2019) [81]:
  • Introduction: The MLT-2019 dataset [81] contains 20,000 images: 10,000 for training (1,000 per language) and 10,000 for testing. The dataset includes ten languages, representing seven different scripts: Arabic, Bangla, Chinese, Devanagari, English, French, German, Italian, Japanese, and Korean. The number of images per script is equal.
  • Link: MLT-download

<a id="14-synthetic-datasets"></a>

1.4 Synthetic Datasets

• Synth90k [53] :
  • Introduction: The Synth90k dataset contains 9 million synthetic text instance images from a set of 90k common English words. Words are rendered onto natural images with random transformations and effects, such as random fonts, colors, blur, and noises. Synth90k dataset can emulate the distribution of scene text images and can be used instead of real-world data to train data-hungry deep learning algorithms. Besides, every image is annotated with a ground-truth word.
  • Link: Synth90k-download
• SynthText [54] :
  • Introduction: The SynthText dataset contains 800,000 images with 6 million synthetic text instances. As in the generation of Synth90k dataset, the text sample is rendered using a randomly selected font and transformed according to the local surface orientation. Moreover, each image is annotated with a ground-truth word.
  • Link: SynthText-download
• Verisimilar Synthesis [73] :
  • Introduction: The Verisimilar Synthesis dataset [73] contains 5 million synthetic text instance images. Given background images and source texts, a semantic map and a saliency map are first determined which are then combined to identify semantically sensible and apt locations for text embedding. The color, brightness, and orientation of the source texts are further determined adaptively according to the color, brightness, and contextual structures around the embedding locations within the background image.
  • Link: Verisimilar Synthesis
• UnrealText [88]:
  • Introduction: The UnrealText dataset [88] contains 600K synthetic images with 12 million cropped text instances. It is developed upon Unreal Engine 4 and the UnrealCV plugin [89]. Text instances are regarded as planar polygon meshes with text foregrounds loaded as texture. These meshes are placed in suitable positions in 3D world, and rendered together with the scene as a whole. The same font set from Google Fonts and the same text corpus, i.e., Newsgroup20, are used as SynthText does.
  • Link: Verisimilar Synthesis

<a id="15-comparison-of-the-benchmark-datasets"></a>

1.5 Comparison of the Benchmark Datasets

<a id="2-performance-comparison-of-recognition-algorithms"></a>

2. Performance Comparison of Recognition Algorithms

<a id="21-characteristics-comparison-of-recognition-approaches"></a>

2.1 Characteristics Comparison of Recognition Approaches

It is notable that 1) "Reg" stands for regular Latin datasets. 2) "Irreg" stands for irregular Latin datasets. 3) "Seg" denotes the segmentation-based methods. 4) "Extra" indicates the methods that use the extra datasets other than Synth90k and SynthText. 5) "CTC" represents the methods that apply the CTC-based algorithm to decode. 6) "Attn" represents the method that apply the attention mechanism to decode.

You can also download the new Excel prepared by us. (Password: sj2t)

<a id="22-performance-comparison-on-benchmark-datasets"></a>

2.2 Performance Comparison on Benchmark Datasets

In this section, we compare the performance of the current advanced algorithms on benchmark datasets, including IIIT5K，SVT，IC03，IC13，SVT-P，CUTE80，IC15，COCO-Text, RCTW-17, MWTI, CTW，SCUT-CTW1500, LSVT, ArT and ReCTS-25k.

It is notable that 1) The '*' indicates the methods that use the extra datasets other than Synth90k and SynthText. 2) The bold represents the best recognition results. 3) '^' denotes the best recognition results of using extra datasets. 4) '@' represents the methods under different evaluation that only uses 1811 test images. 5) 'SK', 'ST', 'ExPu', 'ExPr' and 'Un' indicates the methods that use Synth90K, SynthText, Extra Public Data, Extra Private Data and unknown data, respectively. 6) 'D_A' means data augmentation. 7) IC5-S contains only 1811 cropped text instances.

<a id="221-performance-comparison-of-recognition-algorithms-on-regular-latin-datasets"></a>

2.2.1 Performance Comparison of Recognition Algorithms on Regular Latin Datasets

2.2.2 Performance Comparison of Recognition Algorithms on Irregular Latin Datasets

<a id="3-survey"></a>

3. Survey

[50] [TPAMI-2015] Q. Ye and D. Doermann, “Text detection and recognition in imagery: A survey,” IEEE Trans. Pattern Anal. Mach. Intell, vol. 37, no. 7, pp. 1480–1500, 2015. paper

[51] [Frontiers-Comput. Sci-2016] Y. Zhu, C. Yao, and X. Bai, “Scene text detection and recognition: Recent advances and future trends,” Frontiers of Computer Science, vol. 10, no. 1, pp. 19–36, 2016. paper

[52] [IJCV-2020] Long S, He X, Yao C. Scene text detection and recognition: The deep learning era[J]. International Journal of Computer Vision, 2020: 1-24. paper code

[90] [ACM Computing Surveys-2020] X. Chen, L. Jin, Y. Zhu, C. Luo, and T. Wang, “Text Recognition in the Wild: A Survey," ACM Computing Surveys (CSUR) 2020. paper code

<a id="4-ocr-service"></a>

4. OCR Service

<a id="5-references"></a>

5. References

[1] [ICCV-2011] K. Wang, B. Babenko, and S. Belongie, “End-to-end scene text recognition,” in Proceedings of ICCV, 2011, pp. 1457–1464. paper

[2] [BMVC-2012] A. Mishra, K. Alahari, and C. Jawahar, “Scene text recognition using higher order language priors,” in Proceedings of BMVC, 2012, pp. 1–11. paper dataset

[3] [ICPR-2012] T. Wang, D. J. Wu, A. Coates, and A. Y. Ng, “End-to-end text recognition with convolutional neural networks,” in Proceedings of ICPR, 2012, pp. 3304–3308. paper

[4] [ICDAR-2013] V. Goel, A. Mishra, K. Alahari, and C. Jawahar, “Whole is greater than sum of parts: Recognizing scene text words,” in Proceedings of ICDAR, 2013, pp. 398–402. paper

[5] [ICCV-2013] A. Bissacco, M. Cummins, Y. Netzer, and H. Neven, “Photoocr: Reading text in uncontrolled conditions,” in Proceedings of ICCV, 2013, pp. 785–792. paper

[6] [ICCV-2013] T. Quy Phan, P. Shivakumara, S. Tian, and C. Lim Tan, “Recognizing text with perspective distortion in natural scenes,” in Proceedings of ICCV, 2013, pp. 569–576. paper

[7] [ICLR-2014] O. Alsharif and J. Pineau, “End-to-end text recognition with hybrid HMM maxout models,” in Proceedings of ICLR: Workshop, 2014. paper

[8] [TPAMI-2014] J. Almaz ́an, A. Gordo, A. Forn ́ es, and E. Valveny, "Word spotting and recognition with embedded attributes,” IEEE Trans. Pattern Anal. Mach. Intell, vol. 36, no. 12, pp. 2552–2566, 2014. paper code

[9] [CVPR-2014] C. Yao, X. Bai, B. Shi, and W. Liu, “Strokelets: A learned multiscale representation for scene text recognition,” in Proceedings of CVPR, 2014, pp. 4042–4049. paper

[10] [IJCV-2015] J. A. Rodriguez-Serrano, A. Gordo, and F. Perronnin, “Label embedding: A frugal baseline for text recognition,” Int. J. Comput. Vis, vol. 113, no. 3, pp. 193–207, 2015. paper

[11] [ECCV-2014] M. Jaderberg, A. Vedaldi, and A. Zisserman, “Deep features for text spotting,” in Proceedings of ECCV, 2014, pp. 512–528. paper code

[12] [ACCV-2014] B. Su and S. Lu, “Accurate scene text recognition based on recurrent neural network,” in Proceedings of ACCV, 2014, pp. 35–48. paper

[13] [CVPR-2015] A. Gordo, “Supervised mid-level features for word image representation,” in Proceedings of CVPR, 2015, pp. 2956–2964. paper

[14] [IJCV-2015] M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman, “Reading text in the wild with convolutional neural networks,” Int. J. Comput. Vis, vol. 116, no. 1, pp. 1–20, 2016. paper code

[15] [ICLR-2015] M. Jaderberg, K. Simonyan, and A. Zisserman, “Deep structured output learning for unconstrained text recognition,” in Proceedings of ICLR, 2015. paper

[16] [TPAMI-2017] B. Shi, X. Bai, and C. Yao, “An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition,” IEEE Trans. Pattern Anal. Mach. Intell, vol. 39, no. 11, pp. 2298–2304, 2017. paper code-Torch7 code-Pytorch

[17] [CVPR-2016] B. Shi, X. Wang, P. Lyu, C. Yao, and X. Bai, “Robust scene text recognition with automatic rectification,” in Proceedings of CVPR, 2016, pp. 4168–4176. paper

[18] [CVPR-2016] C.-Y. Lee and S. Osindero, “Recursive recurrent nets with attention modeling for OCR in the wild,” in Proceedings of CVPR, 2016, pp. 2231–2239. paper

[19] [BMVC-2016] W. Liu, C. Chen, K.-Y. K. Wong, Z. Su, and J. Han, “STAR-Net: A spatial attention residue network for scene text recognition,” in Proceedings of BMVC, 2016, p. 7. paper

[20] [IJCAI-2017] X. Yang, D. He, Z. Zhou, D. Kifer, and C. L. Giles, “Learning to read irregular text with attention mechanisms,” in Proceedings of IJCAI, 2017, pp. 3280–3286. paper

[21] [ICCV-2017] F. Yin, Y.-C. Wu, X.-Y. Zhang, and C.-L. Liu, “Scene text recognition with sliding convolutional character models,” in Proceedings of ICCV, 2017. paper code

[22] [ICCV-2017] Z. Cheng, F. Bai, Y. Xu, G. Zheng, S. Pu, and S. Zhou, “Focusing attention: Towards accurate text recognition in natural images,” in Proceedings of ICCV, 2017, pp. 5086–5094. paper

[23] [CVPR-2018] Z. Cheng, Y. Xu, F. Bai, Y. Niu, S. Pu, and S. Zhou, “AON: Towards arbitrarily-oriented text recognition,” in Proceedings of CVPR, 2018, pp. 5571–5579. paper code

[24] [NC-2019] Y. Gao, Y. Chen, J. Wang, M. Tang, and H. Lu, “Reading scene text with fully convolutional sequence modeling,” Neurocomputing, vol. 339, pp. 161–170, 2019. paper

[25] [AAAI-2018] W. Liu, C. Chen, and K.-Y. K. Wong, “Char-Net: A character-aware neural network for distorted scene text recognition.” in Proceedings of AAAI, 2018, pp. 7154–7161. paper

[26] [AAAI-2018] Z. Liu, Y. Li, F. Ren, W. L. Goh, and H. Yu, “Squeezedtext: A real-time scene text recognition by binary convolutional encoderdecoder network,” in Proceedings of AAAI, 2018, pp. 7194–7201. paper

[27] [CVPR-2018] F. Bai, Z. Cheng, Y. Niu, S. Pu, and S. Zhou, “Edit probability for scene text recognition,” in Proceedings of CVPR, 2018, pp. 1508–1516. paper

[28] [ECCV-2018] Y. Liu, Z. Wang, H. Jin, and I. Wassell, “Synthetically supervised feature learning for scene text recognition,” in Proceedings of ECCV, 2018, pp. 449–465. paper

[29] [ICIP-2018] Y. Gao, Y. Chen, J. Wang, M. Tang, and H. Lu, “Dense chained attention network for scene text recognition,” in Proceedings of ICIP, 2018, pp. 679–683. paper

[30] [TPAMI-2018] B. Shi, M. Yang, X. Wang, P. Lyu, C. Yao, and X. Bai, “ASTER: An attentional scene text recognizer with flexible rectification,” IEEE Trans. Pattern Anal. Mach. Intell, vol. 41, no. 9, pp. 2035–2048, 2019. paper code

[31] [CVPR-2012] A. Mishra, K. Alahari, and C. Jawahar, “Top-down and bottom-up cues for scene text recognition,” in Proceedings of CVPR, 2012, pp. 2687–2694. paper

[32] https://github.com/Canjie-Luo/MORAN_v2

[33] [ICDAR-2003] S. M. Lucas, A. Panaretos, L. Sosa, A. Tang, S. Wong, and R. Young, “ICDAR 2003 robust reading competitions,” in Proceedings of ICDAR, 2003, pp. 682–687. paper

[34] [ICDAR-2013] D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, L. G. i Bigorda, S. R. Mestre, J. Mas, D. F. Mota, J. A. Almazan, and L. P. De Las Heras, “ICDAR 2013 robust reading competition,” in Proceedings of ICDAR, 2013, pp. 1484–1493. paper

[35] [ICCV-2013] T. Quy Phan, P. Shivakumara, S. Tian, and C. Lim Tan, “Recognizing text with perspective distortion in natural scenes,” in Proceedings of ICCV, 2013, pp. 569–576. paper

[36] [Expert Syst.Appl-2014] A. Risnumawan, P. Shivakumara, C. S. Chan, and C. L. Tan, “A robust arbitrary text detection system for natural scene images,” Expert Systems with Applications, vol. 41, no. 18, pp. 8027–8048, 2014. paper

[37] [ICDAR-2015] D. Karatzas, L. Gomez-Bigorda, A. Nicolaou, S. Ghosh, A. Bagdanov, M. Iwamura, J. Matas, L. Neumann, V. R. Chandrasekhar, S. Lu et al., “ICDAR 2015 competition on robust reading,” in Proceedings of ICDAR, 2015, pp. 1156–1160. paper

[38] [arXiv-2016] A. Veit, T. Matera, L. Neumann, J. Matas, and S. Belongie, “Coco-text: Dataset and benchmark for text detection and recognition in natural images,” CoRR abs/1601.07140, 2016. paper code

[39] [IJDAR-2019] C.-K. Ch’ng, C. S. Chan, and C.-L. Liu, “Total-text: toward orientation robustness in scene text detection,” International Journal on Document Analysis and Recognition (IJDAR), pp. 1–22, 2019. paper code

[40] [ICDAR-2017] B. Shi, C. Yao, M. Liao, M. Yang, P. Xu, L. Cui, S. Belongie, S. Lu, and X. Bai, “ICDAR2017 competition on reading chinese text in the wild (rctw-17),” in Proceedings of ICDAR, 2017, pp. 1429–1434. paper

[41] [ICPR-2018] M. He, Y. Liu, Z. Yang, S. Zhang, C. Luo, F. Gao, Q. Zheng, Y. Wang, X. Zhang, and L. Jin, “ICPR2018 contest on robust reading for multi-type web images,” in Proceedings of ICPR, 2018, pp. 7–12. paper

[42] [JCS&T-2019] Yuan T L, Zhu Z, Xu K, et al. A large chinese text dataset in the wild[J]. Journal of Computer Science and Technology, 2019, 34(3): 509-521. paper code

[43] [arXiv-2017] L. Yuliang, J. Lianwen, Z. Shuaitao, and Z. Sheng, “Detecting curve text in the wild: New dataset and new solution,” CoRR abs/1712.02170, 2017. paper code

[44] [ECCV-2018] P. Lyu, M. Liao, C. Yao, W. Wu, and X. Bai, “Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes,” in Proceedings of ECCV, 2018, pp. 67–83. paper code

[45] [NIPS-W-2011] Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, “Reading digits in natural images with unsupervised feature learning,” in Proceedings of NIPS, 2011. paper

[46] [PR-2019] C. Luo, L. Jin, and Z. Sun, “MORAN: A multi-object rectified attention network for scene text recognition,” Pattern Recognition, vol. 90, pp. 109–118, 2019. paper code

[47] [ACM-2019] Xie H, Fang S, Zha Z J, et al, “Convolutional Attention Networks for Scene Text Recognition,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 15, pp. 3 2019. paper

[48] [AAAI-2019] M. Liao, J. Zhang, Z. Wan, F. Xie, J. Liang, P. Lyu, C. Yao, and X. Bai, “Scene text recognition from two-dimensional perspective,” in Proceedings of AAAI, 2019, pp. 8714–8721. paper

[49] [AAAI-2019] H. Li, P. Wang, C. Shen, and G. Zhang, “Show, attend and read: A simple and strong baseline for irregular text recognition,” in Proceedings of AAAI, 2019, pp. 8610–8617. paper code

[50] [TPAMI-2015] Q. Ye and D. Doermann, “Text detection and recognition in imagery: A survey,” IEEE Trans. Pattern Anal. Mach. Intell, vol. 37, no. 7, pp. 1480–1500, 2015. paper

[51] [Frontiers-Comput. Sci-2016] Y. Zhu, C. Yao, and X. Bai, “Scene text detection and recognition: Recent advances and future trends,” Frontiers of Computer Science, vol. 10, no. 1, pp. 19–36, 2016. paper

[52] [IJCV-2020] Long S, He X, Yao C. Scene text detection and recognition: The deep learning era[J]. International Journal of Computer Vision, 2020: 1-24. paper code

[53] [NIPS-W-2014] M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman, “Synthetic data and artificial neural networks for natural scene text recognition,” in Proceedings of NIPS-W, 2014. paper code

[54] [CVPR-2016] A. Gupta, A. Vedaldi, and A. Zisserman, “Synthetic data for text localisation in natural images,” in Proceedings of CVPR, 2016, pp. 2315–2324. paper code

[55] [CVPR-2019] F. Zhan and S. Lu, “ESIR: End-to-end scene text recognition via iterative image rectification,” in Proceedings of CVPR, 2019, pp. 2059–2068. paper

[56] [CVPR-2019] Y. Zhang, S. Nie, W. Liu, X. Xu, D. Zhang, and H. T. Shen, “Sequence-to-sequence domain adaptation network for robust text image recognition,” in Proceedings of CVPR, 2019, pp. 2740–2749. paper code

[57][ICDAR-2019] Y. Sun, Z. Ni, C.-K. Chng, Y. Liu, C. Luo, C. C. Ng, J. Han, E. Ding, J. Liu, D. Karatzas et al., “ICDAR 2019 competition on large-scale street view text with partial labeling–RRC-LSVT,” in Proceedings of ICDAR, 2019, pp. 1557–1562. paper Link

[58][ICDAR-2019] C.-K. Chng, Y. Liu, Y. Sun, C. C. Ng, C. Luo, Z. Ni, C. Fang, S. Zhang, J. Han, E. Ding et al., “ICDAR2019 robust reading challenge on arbitrary-shaped text (RRC-ArT),” in Proceedings of ICDAR, 2019, pp. 1571–1576. paper Link

[59][ICDAR-2019] X. Liu, R. Zhang, Y. Zhou, Q. Jiang, Q. Song, N. Li, K. Zhou, L. Wang, D. Wang, M. Liao et al., “ICDAR 2019 robust reading challenge on reading chinese text on signboard,” in Proceedings of ICDAR, 2019, pp. 1577–1581. paper Link

[60] [NC-2019] X. Chen, T. Wang, Y. Zhu, L. Jin, and C. Luo, “Adaptive embedding gate for attention-based scene text recognition,” Neurocomputing, vol. 381, pp. 261–271, 2020. paper

Newly added references (Dec 24, 2019)

[61] [ICFHR-2018] C. Wang, F. Yin, and C.-L. Liu, “Memory-augmented attention model for scene text recognition,” in Proceedings of ICFHR, 2018, pp. 62–67. paper

[62] [ICCV-2019] M. Yang, Y. Guan, M. Liao, X. He, K. Bian, S. Bai, C. Yao, and X. Bai, “Symmetry-constrained rectification network for scene text recognition,” in Proceedings of ICCV, 2019, pp. 9147–9156. paper

[63] [ICCV-2019] Y. Sun, J. Liu, W. Liu, J. Han, E. Ding, and J. Liu, “Chinese street view text: Large-scale chinese text reading with partially supervised learning,” in Proceedings of ICCV, 2019, pp. 9086–9095. paper

[64] [ICME-2019] S. Wang, Y. Wang, X. Qin, Q. Zhao, and Z. Tang, “Scene text recognition via gated cascade attention,” in Proceedings of ICME, 2019, pp. 1018–1023. paper

[65] [ICCV-2019] J. Baek, G. Kim, J. Lee, S. Park, D. Han, S. Yun, S. J. Oh, and H. Lee, “What is wrong with scene text recognition model comparisons? dataset and model analysis,” in Proceedings of ICCV, 2019, pp. 4714–4722. paper code

[66] [Nips-2017] J. Wang and X. Hu, “Gated recurrent convolution neural network for OCR,” in Proceedings of NIPS, 2017, pp. 335–344. paper code

[67] [NC-2020] Y. Huang, Z. Sun, L. Jin, and C. Luo, “EPAN: Effective parts attention network for scene text recognition,” Neurocomputing, vol. 376, pp. 202–213, 2020. paper

[68] [NC-2019] Y. Gao, Y. Chen, J. Wang, M. Tang, and H. Lu, “Reading scene text with fully convolutional sequence modeling,” Neurocomputing, vol. 339, pp. 161–170, 2019. paper

[69] [ICDAR-W-2019] X. Qi, Y. Chen, R. Xiao, C.-G. Li, Q. Zou, and S. Cui, “A novel joint character categorization and localization approach for characterlevel scene text recognition,” in Proceedings of ICDAR: Workshops, 2019, pp. 83–90. paper

[70] [ICDAR-W-2019] Q. Wang, W. Jia, X. He, Y. Lu, M. Blumenstein, Y. Huang, and S. Lyu, “ReELFA: A scene text recognizer with encoded location and focused attention,” in Proceedings of ICDAR: Workshops, 2019, pp. 71–76. paper

[71] [ICIP-2019] Y. Zhu, S. Wang, Z. Huang, and K. Chen, “Text recognition in images based on transformer with hierarchical attention,” in Proceedings of ICIP, 2019, pp. 1945–1949. paper

[72] [CVPR-2019] F. Zhan, H. Zhu, and S. Lu, “Spatial fusion gan for image synthesis,” in Proceedings of CVPR, 2019, pp. 3653–3662. paper

[73] [ECCV-2018] F. Zhan, S. Lu, and C. Xue, “Verisimilar image synthesis for accurate detection and recognition of texts in scenes,” in Proceedings of ECCV, 2018, pp. 249–266. paper code

[74] [MultiMedia-2018] S. Fang, H. Xie, Z.-J. Zha, N. Sun, J. Tan, and Y. Zhang, “Attention and language ensemble for scene text recognition with convolutional sequence modeling,” in ACM Multimedia Conference on Multimedia Conference, 2018, pp. 248–256. paper code

[75] [Nips-2018] H. Liu, S. Jin, and C. Zhang, “Connectionist temporal classification with maximum entropy regularization,” in Proceedings of NIPS, 2018, pp. 831–841 . paper code

[76] [PR-2017] B. Su and S. Lu, “Accurate recognition of words in scenes without character segmentation using recurrent neural network,” Pattern Recognition, vol. 63, pp. 397–405, 2017. paper

[77] [CVIU-2016] A. Mishra, K. Alahari, and C. Jawahar, “Enhancing energy minimization framework for scene text recognition with top-down cues,” Computer Vision and Image Understanding, vol. 145, pp. 30–42, 2016. paper

[78] [ICPR-2016] X. Liu, T. Kawanishi, X. Wu, and K. Kashino, “Scene text recognition with CNN classifier and WFST-based word labeling,” in Proceedings of ICPR, 2016, pp. 3999–4004. paper

[79] [TPAMI-2019] M. Liao, P. Lyu, M. He, C. Yao, W. Wu, and X. Bai, “Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes,” IEEE Trans. Pattern Anal. Mach. Intell, 2019. paper code

[80] [AAAI-2020] T. Wang, Y. Zhu, L. Jin, C. Luo, X. Chen, Y. Wu, Q. Wang, and M. Cai, “Decoupled attention network for text recognition,” in Proceedings of AAAI, 2020. paper code

Newly added references (Feb 29, 2020)

[81] [ICDAR-2019] N. Nayef, Y. Patel, M. Busta, P. N. Chowdhury, D. Karatzas, W. Khlif, J. Matas, U. Pal, J.-C. Burie, C.-l. Liu et al., “ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition–RRC-MLT-2019,” in Proceedings of ICDAR, 2019, pp. 1582–1587. paper

[82] [arXiv-2019] W. Wang, E. Xie, P. Sun, W. Wang, L. Tian, C. Shen, and P. Luo, “TextSR: Content-aware text super-resolution guided by recognition,” CoRR abs/1909.07113, 2019. paper code

[83] [AAAI-2020] Z. Wan, M. He, H. Chen, X. Bai, and C. Yao, “Textscanner: Reading characters in order for robust scene text recognition,” In Proceedings of AAAI, 2020. paper

[84] [AAAI-2020] W. Hu, X. Cai, J. Hou, S. Yi, and Z. Lin, “GTC: Guided training of ctc towards efficient and accurate scene text recognition,” In Proceedings of AAAI, 2020. paper

[85] [IJCV-2020] C. Luo, Q. Lin, Y. Liu, J. Lianwen, and S. Chunhua, “Separating content from style using adversarial learning for recognizing text in the wild,” Int. J. Comput. Vis. 2020. paper

Newly added references (May 8, 2020)

[86] [CVPR-2020] R. Litman, O. Anschel, S. Tsiper, R. Litman, S. Mazor, and R. Manmatha, “SCATTER: selective context attentional scene text recognizer,” in Proceedings of CVPR, 2020. paper

[87] [CVPR-2020] D. Yu, X. Li, C. Zhang, J. Han, J. Liu, and E. Ding, “Towards accurate scene text recognition with semantic reasoning networks,” in Proceedings of CVPR, 2020. paper

[88] [CVPR-2020] S. Long and C. Yao, “UnrealText: Synthesizing realistic scene text images from the unreal world,” in Proceedings of CVPR, 2020. paper

[89] [ECCV-2016] W. Qiu and A. L. Yuille, “Unrealcv: Connecting computer vision to unreal engine,” in Proceedings of ECCV, 2016, pp. 909–916. paper

[90] [ACM Computing Surveys-2020] X. Chen, L. Jin, Y. Zhu, C. Luo, and T. Wang, “Text Recognition in the Wild: A Survey," ACM Computing Surveys (CSUR) 2020. paper code

Newly added references (Dec 8, 2020)

[91] [ICVGIP-2018] Gupta A, Vedaldi A, Zisserman A. "Learning to read by spelling: Towards unsupervised text recognition," in Proceedings of ICVGIP, 2018. paper

[92] [CVPR-2020] Wan Z, Zhang J, Zhang L, et al, "On Vocabulary Reliance in Scene Text Recognition," in Proceedings of CVPR, 2020. paper

[93] [ECAI-2020] Bleeker M, de Rijke M, "Bidirectional Scene Text Recognition with a Single Decoder," in Proceedings of ECAI, 2020. paper code

[94] [arXiv-2019] Bartz C, Bethge J, Yang H, et al, "KISS: Keeping It Simple for Scene Text Recognition,"CoRR abs/1911.08400, 2019. paper code

[95] [arXiv-2020] Zhang C, Xu Y, Cheng Z, et al, "SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition," CoRR abs/2005.13117, 2020. paper

[96] [arXiv-2020] Lin J, Cheng Z, Bai F, et al, "Text Recognition in Real Scenarios with a Few Labeled Samples," CoRR abs/2006.12209, 2020. paper

[97] [ECCV-2020] Zhang C, Gupta A, Zisserman A. "Adaptive Text Recognition through Visual Matching," in Proceedings of ECCV, 2020. paper code

[98] [ECCV-2020] Zhang H, Yao Q, Yang M, et al, "AutoSTR: Efficient Backbone Search for Scene Text Recognition," in Proceedings of ECCV, 2020. paper code

[99] [ECCV-2020] Yan R, Huang Y, "PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit," in Proceedings of ECCV, 2020. paper

[100] [ECCV-2020] Yue X, Kuang Z, Lin C, et al. RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition," in Proceedings of ECCV, 2020. paper

[101] [CVPR-2020] Zhi Qiao, Yu Zhou, Dongbao Yang, Yucan Zhou, and Weiping Wang. 2020. SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition. In Proceedings of CVPR. paper code

<a id="6help"></a>

6.Help

If you have any problem in our resources, or any good paper/code we missed, please inform us at xxuechen@foxmail.com. Thank you for your contribution.

<a id="7copyright"></a>

<a id="7copyright"></a>

7.Copyright

Copyright © 2020 SCUT-DLVC. All Rights Reserved.