RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12364)


The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts (e.g., random character sequences) which is unacceptable in most of real application scenarios. In this paper, we first deeply investigate the decoding process of the decoder. We empirically find that a representative character-level sequence decoder utilizes not only context information but also positional information. Contextual information, which the existing approaches heavily rely on, causes the problem of attention drift. To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition. Specifically, it contains a position aware module to enable the encoder to output feature vectors encoding their own spatial positions, and an attention module to estimate glimpses using the positional clue (i.e., the current decoding time step) only. The dynamic fusion is conducted for more robust feature via an element-wise gate mechanism. Theoretically, our proposed method, dubbed RobustScanner, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical. Empirically, it has achieved new state-of-the-art results on popular regular and irregular text recognition benchmarks while without much performance drop on contextless benchmarks, validating its robustness in both contextual and contextless application scenarios.

Supplementary material

504475_1_En_9_MOESM1_ESM.pdf (273 kb)
Supplementary material 1 (pdf 273 KB)


  1. 1.
    Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4715–4723 (2019)Google Scholar
  2. 2.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR, pp. 1–15 (2015)Google Scholar
  3. 3.
    Bai, F., Cheng, Z., Niu, Y., Pu, S., Zhou, S.: Edit probability for scene text recognition. In: CVPR, pp. 1508–1516 (2018)Google Scholar
  4. 4.
    Bartz, C., Bethge, J., Yang, H., Meinel, C.: KISS: keeping it simple for scene text recognition. arXiv preprint arXiv:1911.08400 (2019)
  5. 5.
    Biten, A.F., et al.: Scene text visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4291–4301 (2019)Google Scholar
  6. 6.
    Bleeker, M., de Rijke, M.: Bidirectional scene text recognition with a single decoder. arXiv preprint arXiv:1912.03656 (2019)
  7. 7.
    Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: ICCV, pp. 5076–5084 (2017)Google Scholar
  8. 8.
    Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S.: AON: towards arbitrarily-oriented text recognition. In: CVPR, pp. 5571–5579 (2018)Google Scholar
  9. 9.
    Dai, Z., et al.: Transformer-XL: attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)
  10. 10.
    Gao, Y., Chen, Y., Wang, J., Lei, Z., Zhang, X.Y., Lu, H.: Recurrent calibration network for irregular text recognition. arXiv preprint arXiv:1812.07145 (2018)
  11. 11.
    Gao, Y., Chen, Y., Wang, J., Lu, H.: Reading scene text with attention convolutional sequence modeling. arXiv preprint arXiv:1709.04303 (2017)
  12. 12.
    Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369–376. ACM (2006)Google Scholar
  13. 13.
    Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR (2016)Google Scholar
  14. 14.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  15. 15.
    He, P., Huang, W., Qiao, Y., Loy, C.C., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI (2016)Google Scholar
  16. 16.
    He, W., Yin, F., Zhang, X.-Y., Liu, C.-L.: TextDragon: an end-to-end framework for arbitrary shaped text spotting. In: ICCV, pp. 9076–9085 (2019)Google Scholar
  17. 17.
    Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)
  18. 18.
    Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS, pp. 2017–2025 (2015)Google Scholar
  19. 19.
    Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156–1160. IEEE (2015)Google Scholar
  20. 20.
    Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484–1493 (2013)Google Scholar
  21. 21.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  22. 22.
    Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR 2013), Sydney, Australia (2013)Google Scholar
  23. 23.
    Lee, C.Y., Bhardwaj, A., Di, W., Jagadeesh, V., Piramuthu, R.: Region-based discriminative feature pooling for scene text recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4050–4057 (2014)Google Scholar
  24. 24.
    Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: CVPR, pp. 2231–2239 (2016)Google Scholar
  25. 25.
    Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: AAAI (2019)Google Scholar
  26. 26.
    Liao, M., et al.: Scene text recognition from two-dimensional perspective. arXiv preprint arXiv:1809.06508 (2018)
  27. 27.
    Liu, W., Chen, C., Wong, K.Y.K.: Char-Net: a character-aware neural network for distorted scene text recognition. In: AAAI (2018)Google Scholar
  28. 28.
    Long, S., Guan, Y., Bian, K., Yao, C.: A new perspective for flexible feature gathering in scene text recognition via character anchor pooling. arXiv preprint arXiv:2002.03509 (2020)
  29. 29.
    Luo, C., Jin, L., Sun, Z.: MORAN: a multi-object rectified attention network for scene text recognition. Pattern Recogn. 90, 109–118 (2019)CrossRefGoogle Scholar
  30. 30.
    Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP (2015)Google Scholar
  31. 31.
    Lyu, P., Yang, Z., Leng, X., Wu, X., Li, R., Shen, X.: 2D attentional irregular scene text recognizer. arXiv preprint arXiv:1906.05708 (2019)
  32. 32.
    Mishra, A., Alahari, K., Jawahar, C.V.: Scene text recognition using higher order language priors. In: BMVC-British Machine Vision Conference. BMVA (2012)Google Scholar
  33. 33.
    Mishra, A., Alahari, K., Jawahar, C.V.: Top-down and bottom-up cues for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2687–2694 (2012)Google Scholar
  34. 34.
    Mishra, A., Alahari, K., Jawahar, C.V.: Enhancing energy minimization framework for scene text recognition with top-down cues. Comput. Vis. Image Underst. 145, 30–42 (2016)CrossRefGoogle Scholar
  35. 35.
    Qin, S., Bissacco, A., Raptis, M., Fujii, Y., Xiao, Y.: Towards unconstrained end-to-end text spotting. In: ICCV (2019)Google Scholar
  36. 36.
    Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 569–576 (2013)Google Scholar
  37. 37.
    Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41(18), 8027–8048 (2014)CrossRefGoogle Scholar
  38. 38.
    Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)
  39. 39.
    Sheng, F., Chen, Z., Xu, B.: NRTR: a no-recurrence sequence-to-sequence model for scene text recognition. arXiv preprint (2017)Google Scholar
  40. 40.
    Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. PAMI 39(11), 2298–2304 (2016)CrossRefGoogle Scholar
  41. 41.
    Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR, pp. 4168–4176 (2016)Google Scholar
  42. 42.
    Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. PAMI 41(9), 2035–2048 (2018)CrossRefGoogle Scholar
  43. 43.
    Silva, S.M., Jung, C.R.: License plate detection and recognition in unconstrained scenarios. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 593–609. Springer, Cham (2018). Scholar
  44. 44.
    Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8317–8326 (2019)Google Scholar
  45. 45.
    Sun, Y., Liu, J., Liu, W., Han, J., Ding, E., Liu, J.: Chinese street view text: large-scale Chinese text reading with partially supervised learning. In: ICCV, pp. 9086–9095 (2019)Google Scholar
  46. 46.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS (2014)Google Scholar
  47. 47.
    Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)Google Scholar
  48. 48.
    Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 International Conference on Computer Vision, pp. 1457–1464 (2011)Google Scholar
  49. 49.
    Wang, K., Belongie, S.: Word spotting in the wild. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 591–604. Springer, Heidelberg (2010). Scholar
  50. 50.
    Wang, P., Yang, L., Li, H., Deng, Y., Shen, C., Zhang, Y.: A simple and robust convolutional-attention network for irregular text recognition. aXiv preprint (2019)Google Scholar
  51. 51.
    Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI Conference on Artificial Intelligence (2020)Google Scholar
  52. 52.
    Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., Xie, L.: Aggregation cross-entropy for sequence recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6538–6547 (2019)Google Scholar
  53. 53.
    Xing, L., Tian, Z., Huang, W., Scott, M.R.: Convolutional character networks. In: ICCV, pp. 9126–9136 (2019)Google Scholar
  54. 54.
    Xu, K., Courville, A., Zemel, R.S., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)Google Scholar
  55. 55.
    Yang, M., et al.: Symmetry-constrained rectification network for scene text recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9147–9156 (2019)Google Scholar
  56. 56.
    Yang, X., He, D., Zhou, Z., Kifer, D., Giles, C.L.: Learning to read irregular text with attention mechanisms. In: IJCAI (2017)Google Scholar
  57. 57.
    Zhan, F., Lu, S.: ESIR: end-to-end scene text recognition via iterative image rectification. arXiv preprint arXiv:1812.05824 (2018)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.SenseTime ResearchHong KongChina
  2. 2.School of Cyber Science and EngineeringXi’an Jiaotong UniversityXi’anChina

Personalised recommendations