Baek et al., “What Is Wrong With Scene Text Recognition Model Comparisons?” (ICCV 2019)
Optional · paper guide 2 of 4 for DLCV 06 · Text in Images: OCR and Document Understanding. Citation numbers refer to the reference list at the bottom of this page.
Navigate: this page and this track: Navigate: this page and this track
Challenge
By 2019 many scene-text recognizers each claimed state-of-the-art accuracy, but they had been trained on different synthetic datasets and tested on different versions of the same benchmarks, so it was impossible to tell which ideas helped [7].

Figure source: [7], Published paper PDF, PDF page 4. Original PDF.
Method
Fix the data, then decompose the models. The paper fixes training to the union of MJSynth (8.9 M images) and SynthText (5.5 M) and evaluates on the union of seven benchmarks, 8,539 images in total. It then describes recognizers as four stages — transformation (none or TPS), feature extraction (VGG, RCNN or ResNet), sequence modeling (none or BiLSTM) and prediction (CTC or attention) — and trains all combinations, each with five random seeds, measuring accuracy, time per image and number of parameters.
Results
- Dataset inconsistency was real. Two versions of IC03 (860 and 867 images) and of IC15 (1,811 and 2,077) were in use, and on IC03 the seven missing examples alone can move accuracy by 0.8 points. Training on MJSynth only, SynthText only or both gave clearly different accuracies for the same model.
- Modules have different costs. Attention mainly costs time; the feature extractor mainly costs memory. Accuracy gains from each upgrade were about twice as large on irregular benchmarks (curved, rotated, perspective) as on regular ones.
- Some failures are shared by all 24 models: 644 of 8,539 images (7.5%). The paper groups them into calligraphic fonts, vertical text, special characters, heavy occlusion, low resolution and label noise.
Reading the evidence
The main figure plots accuracy against time and against parameters for all combinations, with the frontier of best trade-offs; read along a frontier to see which module upgrade buys the most accuracy per millisecond or per parameter. The module table reports marginal accuracy (averaged over all combinations containing a module), which shows a module’s typical effect but not its best case. Check which benchmark subsets every reported number uses.
Problems
All models are trained on synthetic data only and evaluated on English letters and digits; the framework predates transformer recognizers and large pre-training.
Conclusion
It is the source of the four-stage view of recognition in the main text, of the “diversity over size” lesson for synthetic data, and of the warning to check subsets and label noise before comparing numbers.
References
- S. Long, X. He and C. Yao, “Scene text detection and recognition: The deep learning era,” International Journal of Computer Vision, vol. 129, pp. 161–184, 2021. doi
- X. Chen, L. Jin, Y. Zhu, C. Luo and T. Wang, “Text recognition in the wild: A survey,” ACM Computing Surveys, vol. 54, no. 2, 2021. doi
- L. Cui, Y. Xu, T. Lv and F. Wei, “Document AI: Benchmarks, models and applications,” arXiv:2111.08609, 2021. arXiv
- Q. Zhang, B. Wang, V. S.-J. Huang, J. Zhang, Z. Wang, H. Liang, C. He and W. Zhang, “Document parsing unveiled: Techniques, challenges, and prospects for structured information extraction,” arXiv:2410.21169, 2024. arXiv
- D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, L. Gomez i Bigorda, S. Robles Mestre, J. Mas et al., “ICDAR 2013 Robust Reading Competition,” in Proc. International Conference on Document Analysis and Recognition (ICDAR), pp. 1484–1493, 2013. doi
- D. Karatzas, L. Gomez-Bigorda, A. Nicolaou, S. Ghosh, A. Bagdanov, M. Iwamura, J. Matas et al., “ICDAR 2015 competition on Robust Reading,” in Proc. International Conference on Document Analysis and Recognition (ICDAR), pp. 1156–1160, 2015. doi
- 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 Proc. IEEE/CVF ICCV, pp. 4714–4722, 2019. doi
- N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, 1979. doi
- J. Sauvola and M. Pietikäinen, “Adaptive document image binarization,” Pattern Recognition, vol. 33, no. 2, pp. 225–236, 2000. doi
- C. K. Ch’ng and C. S. Chan, “Total-Text: A comprehensive dataset for scene text detection and recognition,” in Proc. ICDAR, pp. 935–942, 2017. doi
- Y. Liu, L. Jin, S. Zhang, C. Luo and S. Zhang, “Curved scene text detection via transverse and longitudinal sequence connection,” Pattern Recognition, vol. 90, pp. 337–345, 2019. doi
- X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, W. He and J. Liang, “EAST: An efficient and accurate scene text detector,” in Proc. IEEE CVPR, pp. 2642–2651, 2017. doi
- W. Wang, E. Xie, X. Li, W. Hou, T. Lu, G. Yu and S. Shao, “Shape robust text detection with progressive scale expansion network,” in Proc. IEEE/CVF CVPR, pp. 9328–9337, 2019. doi
- M. Liao, Z. Wan, C. Yao, K. Chen and X. Bai, “Real-time scene text detection with differentiable binarization,” in Proc. AAAI Conference on Artificial Intelligence, vol. 34, pp. 11474–11481, 2020. doi
- Y. Baek, B. Lee, D. Han, S. Yun and H. Lee, “Character region awareness for text detection,” in Proc. IEEE/CVF CVPR, pp. 9357–9366, 2019. doi
- 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 TPAMI, vol. 39, no. 11, pp. 2298–2304, 2017. doi
- A. Graves, S. Fernández, F. Gomez and J. Schmidhuber, “Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,” in Proc. ICML, pp. 369–376, 2006. doi
- B. Shi, M. Yang, X. Wang, P. Lyu, C. Yao and X. Bai, “ASTER: An attentional scene text recognizer with flexible rectification,” IEEE TPAMI, vol. 41, no. 9, pp. 2035–2048, 2019. doi
- M. Li, T. Lv, J. Chen, L. Cui, Y. Lu, D. Florencio, C. Zhang, Z. Li and F. Wei, “TrOCR: Transformer-based optical character recognition with pre-trained models,” in Proc. AAAI Conference on Artificial Intelligence, vol. 37, pp. 13094–13102, 2023. doi
- D. Bautista and R. Atienza, “Scene text recognition with permuted autoregressive sequence models,” in Proc. ECCV, pp. 178–196, 2022. doi
- S. Fang, H. Xie, Y. Wang, Z. Mao and Y. Zhang, “Read like humans: Autonomous, bidirectional and iterative language modeling for scene text recognition,” in Proc. IEEE/CVF CVPR, pp. 7094–7103, 2021. doi
- Y. Liu, Z. Li, M. Huang, B. Yang, W. Yu, C. Li, X.-C. Yin, C.-L. Liu, L. Jin and X. Bai, “OCRBench: On the hidden mystery of OCR in large multimodal models,” Science China Information Sciences, vol. 67, 2024. doi
- M. Jaderberg, K. Simonyan, A. Vedaldi and A. Zisserman, “Synthetic data and artificial neural networks for natural scene text recognition,” arXiv:1406.2227, 2014. arXiv
- A. Gupta, A. Vedaldi and A. Zisserman, “Synthetic data for text localisation in natural images,” in Proc. IEEE CVPR, pp. 2315–2324, 2016. doi
- X. Liu, D. Liang, S. Yan, D. Chen, Y. Qiao and J. Yan, “FOTS: Fast oriented text spotting with a unified network,” in Proc. IEEE/CVF CVPR, pp. 5676–5685, 2018. doi
- 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 Proc. ECCV, pp. 71–88, 2018. doi
- Y. Liu, H. Chen, C. Shen, T. He, L. Jin and L. Wang, “ABCNet: Real-time scene text spotting with adaptive Bezier-curve network,” in Proc. IEEE/CVF CVPR, pp. 9806–9815, 2020. doi
- X. Zhong, J. Tang and A. Jimeno Yepes, “PubLayNet: Largest dataset ever for document layout analysis,” in Proc. ICDAR, pp. 1015–1022, 2019. doi
- B. Pfitzmann, C. Auer, M. Dolfi, A. S. Nassar and P. Staar, “DocLayNet: A large human-annotated dataset for document-layout segmentation,” in Proc. ACM SIGKDD, pp. 3743–3751, 2022. doi
- Y. Xu, M. Li, L. Cui, S. Huang, F. Wei and M. Zhou, “LayoutLM: Pre-training of text and layout for document image understanding,” in Proc. ACM SIGKDD, pp. 1192–1200, 2020. doi
- R. Smith, “An overview of the Tesseract OCR engine,” in Proc. ICDAR, vol. 2, pp. 629–633, 2007. doi
- Y. Huang, T. Lv, L. Cui, Y. Lu and F. Wei, “LayoutLMv3: Pre-training for document AI with unified text and image masking,” in Proc. ACM International Conference on Multimedia, pp. 4083–4091, 2022. doi
- G. Jaume, H. K. Ekenel and J.-P. Thiran, “FUNSD: A dataset for form understanding in noisy scanned documents,” in Proc. ICDAR Workshops (OST), 2019. doi
- G. Kim, T. Hong, M. Yim, J. Nam, J. Park, J. Yim, W. Hwang, S. Yun, D. Han and S. Park, “OCR-free document understanding transformer,” in Proc. ECCV, pp. 498–517, 2022. doi
- K. Lee, M. Joshi, I. R. Turc, H. Hu, F. Liu, J. M. Eisenschlos, U. Khandelwal, P. Shaw, M.-W. Chang and K. Toutanova, “Pix2Struct: Screenshot parsing as pretraining for visual language understanding,” in Proc. ICML, PMLR vol. 202, pp. 18893–18912, 2023. PMLR
- L. Blecher, G. Cucurull, T. Scialom and R. Stojnic, “Nougat: Neural optical understanding for academic documents,” in Proc. ICLR, 2024. OpenReview · arXiv
- U.-V. Marti and H. Bunke, “The IAM-database: An English sentence database for offline handwriting recognition,” International Journal on Document Analysis and Recognition, vol. 5, pp. 39–46, 2002. doi
- C.-L. Liu, F. Yin, D.-H. Wang and Q.-F. Wang, “CASIA online and offline Chinese handwriting databases,” in Proc. ICDAR, pp. 37–41, 2011. doi
- 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 Proc. ICDAR, pp. 1429–1434, 2017. doi · arXiv
- T.-L. Yuan, Z. Zhu, K. Xu, C.-J. Li, T.-J. Mu and S.-M. Hu, “A large Chinese text dataset in the wild,” Journal of Computer Science and Technology, vol. 34, pp. 509–521, 2019. doi · arXiv
- F. Xue and R. Ishida (eds.), “Requirements for Chinese Text Layout,” W3C Group Note (draft of 7 October 2026). W3C
- N. Nayef, Y. Patel, M. Busta, P. N. Chowdhury, D. Karatzas, W. Khlif, J. Matas et al., “ICDAR2019 Robust Reading Challenge on multi-lingual scene text detection and recognition — RRC-MLT-2019,” in Proc. ICDAR, pp. 1582–1587, 2019. doi · arXiv
- R. A. Wagner and M. J. Fischer, “The string-to-string correction problem,” Journal of the ACM, vol. 21, no. 1, pp. 168–173, 1974. doi
- M. Mathew, D. Karatzas and C. V. Jawahar, “DocVQA: A dataset for VQA on document images,” in Proc. IEEE/CVF WACV, pp. 2199–2208, 2021. doi
- A. Mishra, K. Alahari and C. V. Jawahar, “Scene text recognition using higher order language priors,” in Proc. BMVC, 2012. doi
- K. Wang, B. Babenko and S. Belongie, “End-to-end scene text recognition,” in Proc. IEEE ICCV, pp. 1457–1464, 2011. doi
- L. Ouyang, Y. Qu, H. Zhou, J. Zhu, R. Zhang, Q. Lin, B. Wang, Z. Zhao et al., “OmniDocBench: Benchmarking diverse PDF document parsing with comprehensive annotations,” in Proc. IEEE/CVF CVPR, pp. 24838–24848, 2025. CVF
- H. Wei, C. Liu, J. Chen, J. Wang, L. Kong, Y. Xu, Z. Ge, L. Zhao et al., “General OCR theory: Towards OCR-2.0 via a unified end-to-end model,” arXiv:2409.01704, 2024. arXiv
- J. Poznanski, A. Rangapur, J. Borchardt, J. Dunkelberger, R. Huff, D. Lin, C. Wilhelm et al., “olmOCR: Unlocking trillions of tokens in PDFs with vision language models,” arXiv:2502.18443, 2025. arXiv
- H. Wei, Y. Sun and Y. Li, “DeepSeek-OCR: Contexts optical compression,” arXiv:2510.18234, 2025. arXiv
- C. Wolf and J.-M. Jolion, “Object count/area graphs for the evaluation of object detection and segmentation algorithms,” International Journal of Document Analysis and Recognition, vol. 8, pp. 280–296, 2006. doi