Abstract
Handwritten mathematical expression recognition (HMER), typically regarding as a sequence-to-sequence problem, has made great progress in recent years, where RNN based models have been widely adopted. Although Transformer based model has demonstrated success in many areas, its performance is not satisfied due to the issue of standard attention mechanism in HMER. Therefore, we propose to improve the performance via an attention refinement network in the Transformer framework for HMER. We firstly adopt a shift window attention (SWA) from Swin Transformer to capture spatial contexts of the whole image for HMER. Moreover, we propose a refined coverage attention (RCA) to overcome the issue of lack of converge in the standard attention mechanism, where we utilize a convolutional kernel with a gating function to obtain coverage features. With the proposed RCA, we refine coverage attentions to attenuate the repeating issue of focused areas in the long-sequence. In addition, we utilize a pyramid data augmentation method to generate mathematical expression images with multiple resolutions to enhance the model generalization. We evaluate the proposed attention refinement network on the HMER benchmark datasets of CROHME2014/2016/2019, and extensive experiments demonstrate its effectiveness.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bian, X., Qin, B., Xin, X., Li, J., Su, X., Wang, Y.: Handwritten mathematical expression recognition via attention aggregation based bi-directional mutual learning. In: AAAI 2022, vol. 36, pp. 113–121 (2022)
Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)
Ding, H., Chen, K., Huo, Q.: An encoder-decoder approach to handwritten mathematical expression recognition with multi-head attention and stacked decoder. In: ICDAR 2021, pp. 602–616 (2021)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Huang, K., Hussain, A., Wang, Q.F., Zhang, R.: Deep Learning: Fundamentals, Theory and Applications, vol. 2. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-06073-2
Li, B., et al.: When counting meets HMER: counting-aware network for handwritten mathematical expression recognition. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. LNCS, vol. 13688, pp. 197–214. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19815-1_12
Li, Z., Jin, L., Lai, S., Zhu, Y.: Improving attention-based handwritten mathematical expression recognition with scale augmentation and drop attention. In: ICFHR 2020, pp. 175–180 (2020)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV 2021, pp. 10012–10022 (2021)
Mi, H., Sankaran, B., Wang, Z., Ittycheriah, A.: Coverage embedding models for neural machine translation. arXiv preprint arXiv:1605.03148 (2016)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wang, J., Du, J., Zhang, J., Wang, B., Ren, B.: Stroke constrained attention network for online handwritten mathematical expression recognition. Pattern Recogn. 119, 108047 (2021)
Zhang, J., Du, J., Dai, L.: Multi-scale attention with dense encoder for handwritten mathematical expression recognition. In: ICPR 2018, pp. 2245–2250 (2018)
Zhang, J., Du, J., Dai, L.: Track, Attend, and Parse (TAP): an end-to-end framework for online handwritten mathematical expression recognition. IEEE Trans. Multimedia 21(1), 221–233 (2018)
Zhang, J., Du, J., Yang, Y., Song, Y.Z., Dai, L.: SRD: a tree structure based decoder for online handwritten mathematical expression recognition. IEEE Trans. Multimedia 23, 2471–2480 (2020)
Zhang, J., Du, J., Yang, Y., Song, Y.Z., Wei, S., Dai, L.: A tree-structured decoder for image-to-markup generation. In: ICML 2020, pp. 11076–11085 (2020)
Zhang, J., et al.: Watch, attend and parse: an end-to-end neural network based approach to handwritten mathematical expression recognition. Pattern Recogn. 71, 196–206 (2017)
Zhao, W., Gao, L.: CoMER: modeling coverage for transformer-based handwritten mathematical expression recognition. In: Avidan, S., Brostow, G., Ciss, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. LNCS, vol. 13688, pp. 392–408. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19815-1_23
Zhao, W., Gao, L., Yan, Z., Peng, S., Du, L., Zhang, Z.: Handwritten mathematical expression recognition with bidirectionally trained transformer. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 570–584. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86331-9_37
Acknowledgements
This research was funded by National Natural Science Foundation of China (NSFC) no. 62276258, and Jiangsu Science and Technology Programme no. BE2020006-4.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, J., Wang, Q., Liao, W., Chen, J., Huang, K. (2024). Improving Handwritten Mathematical Expression Recognition via an Attention Refinement Network. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Communications in Computer and Information Science, vol 1967. Springer, Singapore. https://doi.org/10.1007/978-981-99-8178-6_41
Download citation
DOI: https://doi.org/10.1007/978-981-99-8178-6_41
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8177-9
Online ISBN: 978-981-99-8178-6
eBook Packages: Computer ScienceComputer Science (R0)