Abstract
Irregular license plate recognition remains challenging due to the irregular layouts of characters, such as multi-line and perspective-distorted layouts. Many previous methods are based on different attention mechanisms, which generate attention weights and aggregate the features to obtain character features for recognition. However, we found that attention-based methods suffer from attention deviation and character misidentification of similar glyphs. We infer that the lack of global perception is the main reason for these problems. Hence, we propose to integrate sufficient global information into the network to improve irregular license plate recognition. Firstly, we propose the deformable spatial attention module to integrate global layout information into attention calculations, thus generating more accurate attention. Secondly, we propose the global perception module that integrates global visual information into feature extraction to enhance the completeness of character features, making them more representative, and thereby alleviating character misidentification. Experiments demonstrate that our method achieves state-of-the-art results, with a significant improvement of 6.7% on irregular license plates. Our codes are available at https://github.com/MMM2024/GP_LPR.
Y.-Y. Liu and Q. Liu—These authors contributed equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: ICCV, pp. 4714–4722 (2019)
Björklund, T., et al.: Robust license plate recognition using neural networks trained on synthetic images. PR 93, 134–146 (2019)
Chen, S.L., et al.: End-to-end multi-line license plate recognition with cascaded perception. In: ICDAR (2023)
Duan, S., et al.: Attention enhanced convnet-RNN for Chinese vehicle license plate recognition. In: PRCV, pp. 417–428 (2018)
Fan, X., Zhao, W.: Improving robustness of license plates automatic recognition in natural scenes. TITS 23(10), 18845–18854 (2022)
Graves, A., et al.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML, pp. 369–376 (2006)
Hsu, G., Chen, J., Chung, Y.: Application-oriented license plate recognition. IEEE Trans. Veh. Technol. 62(2), 552–561 (2013)
Ke, X., Zeng, G., Guo, W.: An ultra-fast automatic license plate recognition approach for unconstrained scenarios. TITS 24(5), 5172–5185 (2023)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Laroca, R., et al.: On the cross-dataset generalization in license plate recognition. In: VISIGRAPP, pp. 166–178 (2022)
Laroca, R., et al.: An efficient and layout-independent automatic license plate recognition system based on the YOLO detector. CoRR abs/1909.01754 (2019)
Li, C., et al.: PP-OCRv3: more attempts for the improvement of ultra lightweight OCR system. CoRR abs/2206.03001 (2022)
Li, H., Shen, C.: Reading car license plates using deep convolutional neural networks and LSTMs. CoRR abs/1601.05610 (2016)
Li, H., Wang, P., Shen, C.: Toward end-to-end car license plate detection and recognition with deep neural networks. TITS 20(3), 1126–1136 (2019)
Liu, Q., et al.: Fast recognition for multidirectional and multi-type license plates with 2D spatial attention. In: ICDAR, pp. 125–139 (2021)
Lu, N., et al.: Automatic recognition for arbitrarily tilted license plate. In: ICVIP, pp. 23–28 (2018)
Lu, Q., Liu, Y., et al.: License plate detection and recognition using hierarchical feature layers from CNN. Multim. Tools Appl. 78(11), 15665–15680 (2019)
Luo, C., Jin, L., Sun, Z.: MORAN: a multi-object rectified attention network for scene text recognition. PR 90, 109–118 (2019)
Qin, S., Liu, S.: Towards end-to-end car license plate location and recognition in unconstrained scenarios. Neural Comput. Appl. 34(24), 21551–21566 (2022)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR, pp. 6517–6525 (2017)
Selmi, Z., Halima, M.B., Pal, U., et al.: DELP-DAR system for license plate detection and recognition. Pattern Recogn. Lett. 129, 213–223 (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. TPAMI 39(11), 2298–2304 (2017)
Silva, S.M., Jung, C.R.: License plate detection and recognition in unconstrained scenarios. In: ECCV, pp. 593–609 (2018)
Spanhel, J., et al.: Holistic recognition of low quality license plates by CNN using track annotated data. In: AVSS, pp. 1–6 (2017)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998–6008 (2017)
Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI, pp. 12216–12224 (2020)
Wang, T., et al.: Efficient license plate recognition via parallel position-aware attention. In: PRCV, vol. 13536, pp. 346–360 (2022)
Wang, Y., Bian, Z., Zhou, Y., et al.: Rethinking and designing a high-performing automatic license plate recognition approach. TITS 23(7), 8868–8880 (2022)
Wu, C., et al.: How many labeled license plates are needed? In: PRCV, pp. 334–346 (2018)
Xu, H., Zhou, X., Li, Z., et al.: EILPR: toward end-to-end irregular license plate recognition based on automatic perspective alignment. TITS 23(3), 2586–2595 (2022)
Xu, Z., et al.: Towards end-to-end license plate detection and recognition: a large dataset and baseline. In: ECCV, pp. 261–277 (2018)
Zhang, K., Zhang, Z., Li, Z., et al.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Zhang, L., Wang, P., Li, H., et al.: A robust attentional framework for license plate recognition in the wild. TITS 22(11), 6967–6976 (2021)
Zhang, Y., Wang, Z., Zhuang, J.: Efficient license plate recognition via holistic position attention. In: AAAI, pp. 3438–3446 (2021)
Zherzdev, S., Gruzdev, A.: LPRNet: license plate recognition via deep neural networks. CoRR abs/1806.10447 (2018)
Zhu, X., et al.: Deformable convnets V2: more deformable, better results. In: CVPR, pp. 9308–9316 (2019)
Zhuang, J., et al.: Towards human-level license plate recognition. In: ECCV, pp. 314–329 (2018)
Zou, Y., et al.: License plate detection and recognition based on YOLOv3 and ILPRNET. Sign. Image Video Process. 16(2), 473–480 (2022)
Acknowledgement
This work was partly supported by the National Key Research and Development Program of China under Grant 2020AAA0109700 and partly by the National Natural Science Foundation of China under Grant 62076024 and Grant 62006018.
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 Switzerland AG
About this paper
Cite this paper
Liu, YY., Liu, Q., Chen, SL., Chen, F., Yin, XC. (2024). Irregular License Plate Recognition via Global Information Integration. In: Rudinac, S., et al. MultiMedia Modeling. MMM 2024. Lecture Notes in Computer Science, vol 14555. Springer, Cham. https://doi.org/10.1007/978-3-031-53308-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-53308-2_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53307-5
Online ISBN: 978-3-031-53308-2
eBook Packages: Computer ScienceComputer Science (R0)