Abstract
Building a robust text detector suitable for different kinds of scene images is a challenging task because the performance of the text detector will be degraded due to the domain shift between different scenes. In this paper, we propose a cross-domain scene text detection method, consisting of pixel-level domain adaptation component (PDA) and image-level domain adaptation component (IDA), to enhance the robustness of scene text detection cross domains. We implement the PDA and IDA by a Gradient Reverse Layer (GRL) and a domain classifier that can distinguish the input scene comes from the source domain or target domain. Besides, to encourage the model to extract domain-invariant features, we introduce the adversarial training to the GRL block. Thus the detector trained with source data can produce more generalized results on the target domain. Experimental results on two pairs of datasets, including MTWI2018 and MSRA-TD500, ICDAR2015 and ICDAR2013, indicate that our proposed method is effective in cross-domain scene text detection and outperforms the methods without domain adaptation.
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
Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3339–3348 (2018)
Deng, D., Liu, H., Li, X., Cai, D.: Pixellink: detecting scene text via instance segmentation. In: AAAI Conference Artificial Intelligence (2018)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096, 2030 (2016)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: 2011 International Conference on Computer Vision, pp. 999–1006. IEEE (2011)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
He, W., Zhang, X.Y., Yin, F., Liu, C.L.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 745–753 (2017)
Huang, L., Yang, Y., Deng, Y., Yu, Y.: DenseBox: unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015)
Kang, L., Li, Y., Doermann, D.: Orientation robust text line detection in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4034–4041 (2014)
Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: TextBoxes: a fast text detector with a single deep neural network. In: AAAI Conference Artificial Intelligence (2017)
Liao, M., Zhu, Z., Shi, B., Xia, G.S., Bai, X.: Rotation-sensitive regression for oriented scene text detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5909–5918 (2018)
Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: IEEE Conference Computer Vision and Pattern Recognition, pp. 2550–2558 (2017)
Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: 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
Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4068–4076 (2015)
Wang, F., Zhao, L., Li, X., Wang, X., Tao, D.: Geometry-aware scene text detection with instance transformation network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1381–1389 (2018)
Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1083–1090. IEEE (2012)
Yin, X.C., Yin, X., Huang, K., Hao, H.W.: Robust text detection in natural scene images. IEEE Trans. Pattern Anal. Mach. Intell. 36(5), 970–983 (2013)
Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: IEEE Conference Computer Vision and Pattern Recognition, pp. 5551–5560 (2017)
Acknowledgement
This work is in part supported by the National Nature Science Foundation of China (No. 61273273), by the National Key Research and Development Plan, China (No. 2017YFC0112001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, D. et al. (2019). Cross-Domain Scene Text Detection via Pixel and Image-Level Adaptation. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1143. Springer, Cham. https://doi.org/10.1007/978-3-030-36802-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-36802-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36801-2
Online ISBN: 978-3-030-36802-9
eBook Packages: Computer ScienceComputer Science (R0)