Abstract
Nowadays, the scene text detection approaches based on deep learning have already achieved promising performances. However, due to the insufficient use of the intermediate feature layer information of the neural network, and the learning of the indistinguishable scale and hard examples, it is difficult to improve the accuracy and the recall. Therefore, based on the Fully Convolutional Networks (FCNs), we propose a hierarchical scene text detector concerning hard examples. Specifically, our proposed detector HST-DHE directly predicts text lines of arbitrary orientations in full images without pre-defined anchor boxes. And the feature pyramid is constructed to predict the features at different levels to make full use of the feature information in the middle layers. At the same time, the loss function is redesigned to make the network focus on hard examples and further improve the precision of text detection. Experiments on standard datasets including ICDAR 2013, ICDAR 2015 and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art detectors. According to the results, our proposed method has stronger robustness in multi-scale and multi-direction natural scene images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Lin, T., Dollr, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of CVPR, pp. 936–944 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimedia 20(11), 3111–3122 (2018)
Jiang, Y., et al.: \(R^{2}\)CNN: Rotational Region CNN for Orientation Robust Scene Text Detection. CoRR abs/1706.09579 (2017)
Lin, T., Goyal, P., Girshick, R., He, K., Dollr, P.: Focal loss for dense object detection. In: Proceedings of ICCV, pp. 2999–3007 (2017)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of CVPR, pp. 761–769 (2016)
Huang, L., Yang, Y., Deng, Y., Yu, Y.: Densebox: Unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874. (2015)
Rezatofighi, S., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of CVPR (2019)
Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of ICDAR, pp. 1156–1160 (2015)
Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of CVPR (2012)
Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: Proceedings of CVPR, pp. 2642–2651 (2017)
Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Cong Yao.: TextSnake: a flexible representation for detecting text of arbitrary shapes. In: Proceedings of ECCV, pp. 19–35 (2018)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, J., Zhang, Z., Li, J. (2021). A Hierarchical Scene Text Detector Concerning Hard Examples. In: Meng, H., Lei, T., Li, M., Li, K., Xiong, N., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2020. Lecture Notes on Data Engineering and Communications Technologies, vol 88. Springer, Cham. https://doi.org/10.1007/978-3-030-70665-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-70665-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70664-7
Online ISBN: 978-3-030-70665-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)