Abstract
Optical text recognition models are widely applied in document processing systems. However, a high-quality text recognition model usually requires large number of samples, extensive amount of time and computation resources. In this paper, we propose a few-shot learning framework for unsegmented text recognition, which comprises of a conventional encoder-decoder recognition module, as well as a generative module for convolutional feature generation. In the meta-training stage, a base model for general text recognition and feature vector generation is trained with large synthesized text image dataset. In the meta-testing stage, the base model is adjusted with a small number of authentic samples. With the complementation of synthesized feature vectors, the base model is adapted to the target dataset distribution. The proposed framework only requires a few authentic samples. It is both data- and time- efficient in adapting existing models to new target datasets. Experimental results on authentic datasets used in industrial applications show that the proposed meta-testing approach outperforms conventional transfer learning by up to 5.84%.
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
Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. (CSUR) 54(2), 1–35 (2021)
de Sousa Neto, A.F., Bezerra, B.L.D., Toselli, A.H., Lima, E.B.: Htr-flor++ a handwritten text recognition system based on a pipeline of optical and language models. In: Proceedings of the ACM Symposium on Document Engineering 2020, pp. 1–4 (2020)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018–3027 (2017)
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: Proceedings of the Conference on Neural Information Processing Systems (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2015)
Luo, C., Zhu, Y., Jin, L., Wang, Y.: Learn to augment: Joint data augmentation and network optimization for text recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13746–13755 (2020)
Rey-Area, M., Guirado, E., Tabik, S., Ruiz-Hidalgo, J.: Fucitnet: improving the generalization of deep learning networks by the fusion of learned class-inherent transformations. Inf. Fusion 63, 188–195 (2020)
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. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298–2304 (2017)
Yousef, M., Hussain, K.F., Mohammed, U.S.: Accurate, data-efficient, unconstrained text recognition with convolutional neural networks. Pattern Recogn. 108, 107482 (2020)
Zharikov, I., Nikitin, P., Vasiliev, I., Dokholyan, V.: Ddi-100: Dataset for text detection and recognition. In: Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control, pp. 1–5 (2020)
Acknowledgment
This work is supported by National Key Research and Development Program of China under grant No.2018YFB0204403. Corresponding author is Shijing Si from Ping An Technology (Shenzhen) Co., Ltd.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, J., Si, S., Hong, Z., Qu, X., Zhu, X., Xiao, J. (2021). Case Study of Few-Shot Learning in Text Recognition Models. In: Zhang, W., Zou, L., Maamar, Z., Chen, L. (eds) Web Information Systems Engineering – WISE 2021. WISE 2021. Lecture Notes in Computer Science(), vol 13081. Springer, Cham. https://doi.org/10.1007/978-3-030-91560-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-91560-5_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91559-9
Online ISBN: 978-3-030-91560-5
eBook Packages: Computer ScienceComputer Science (R0)