Abstract
Efficient models for text detection have a wide range of applications. However, existing real-time text detection methods mainly focus on the inference speed without considering the number of parameters. In this paper, we propose an efficient, lightweight network called ShallowNet with fewer layers, which significantly reduces the number of parameters and improves the inference speed. Fewer layers usually incur small receptive fields that degrade the performance of large-size text detection. To address such an issue, we utilize dilated convolution with various receptive fields that satisfies the need for different sizes of text detection. Nevertheless, the design of dilated convolution ignores the continuity property of text and results in stickiness and fragment in the text detection tasks. To tackle this challenge, we introduce instance count-aware supervision information that guides the network focus on text instances and preserves the boundaries. The instance count-aware supervision is used as the weight of the loss function. Extensive experiments demonstrate that the proposed method achieves a desirable trade-off between the accuracy, size of the model, and inference speed.
This paper is supported by NSFC (No. 62176155, 61772330, 61876109), Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102), the Shanghai Key Laboratory of Crime Scene Evidence (no. 2017XCWZK01), and the Interdisciplinary Program of Shanghai Jiao Tong University (no. YG2019QNA09).
H. Lu—Also with the MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University.
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
References
Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of AAAI, Artificial Intelligence, pp. 11474–11481 (2020)
Tian, Z., Huang, W., He, T., He, P., Qiao, Yu.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 56–72. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_4
Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2642–2651 (2017)
He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., Li, X.: Single shot text detector with regional attention. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 3066–3074 (2017)
Xie, L., Liu, Y., Jin, L., Xie, Z.: DeRPN: taking a further step toward more general object detection. In: Proceedings of AAAI, Artificial Intelligence, pp. 9046–9053 (2019)
Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: Proceedings of AAAI, Artificial Intelligence, pp. 4161–4167 (2017)
Wang, W., et al.: Shape robust text detection with progressive scale expansion network. In: Proceedings of CVPR, Computer Vision and Pattern Recognition, pp. 9336–9345 (2019)
Wang, H., et al.: All you need is boundary: toward arbitrary-shaped text spotting (2019). http://arxiv.org/abs/1911.09550
Liao, M., Shi, B., Bai, X.: TextBoxes++: a single-shot oriented scene text detector. IEEE Trans. Image Process 27(8), 3676–3690 (2018)
Deng, D., Liu, H., Li, X., Cai, D.: Pixellink: detecting scene text via instance segmentation. In: Proceedings of AAAI, Artificial Intelligence, pp. 6773–6780 (2018)
Xu, Y., Wang, Y., Zhou, W., Wang, Y., Yang, Z., Bai, X.: Textfield: learning a deep direction field for irregular scene text detection. IEEE Trans. Image Process. 28(11), 5566–5579 (2019)
Xie, E., Zang, Y., Shao, S., Yu, G., Yao, C., Li, G.: Scene text detection with supervised pyramid context network. In: Proceedings of AAAI, Artificial Intelligence, pp. 9038–9045 (2019)
Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of ICCV Conference on Computer Vision, pp. 8439–8448 (2019)
Tian, Z., et al.: Learning shape-aware embedding for scene text detection. In: Proceedings of CVPR, Computer Vision, pp. 4234–4243 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, Computer Vision, pp. 770–778 (2016)
Liu, Y., Jin, L., Fang, C.: Arbitrarily shaped scene text detection with a mask tightness text detector. IEEE Trans. Image Process. 29, 2918–2930 (2020)
Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017). https://doi.org/10.1109/TIP.2019.2900589
Lin, T., Dollár, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: Proceedings of CVPR, Computer Vision, pp. 936–944 (2017)
Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: ABCNet: real-time scene text spotting with adaptive Bezier-curve network. In: Proceedings of CVPR, Computer Vision, pp. 9806–9815 (2020)
Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of ICDAR, Computer Society, pp. 1156–1160 (2015)
Chng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: Proceedings of ICDAR, Computer Society, pp. 935–942 (2017)
Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognit. 90, 337–345 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, X., Wu, D., Li, H., Jiang, F., Lu, H. (2021). ShallowNet: An Efficient Lightweight Text Detection Network Based on Instance Count-Aware Supervision Information. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13108. Springer, Cham. https://doi.org/10.1007/978-3-030-92185-9_52
Download citation
DOI: https://doi.org/10.1007/978-3-030-92185-9_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92184-2
Online ISBN: 978-3-030-92185-9
eBook Packages: Computer ScienceComputer Science (R0)