A Single-Stage Multi-Style License Plate Recognition Method Based on Attention

Longbin Wu, Sen Liu, Yufei Xie, Haowei Lee, Xiaohui Duan
Proceedings of the 16th Asian Conference on Machine Learning, PMLR 260:495-510, 2025.

Abstract

Automatic license plate recognition is applied widely in life, but it is still a challenging task in open scenarios. The current ALPR methods require multiple recognitions in multi-license plate scenarios. Furthermore, they have complex recognition structures and insufficient recognition capabilities for multi-style license plates. To solve the above problems, this paper proposes a single-stage multi-style multi-license plate recognition method based on the attention mechanism: CLPRNet. We use a spatial attention module based on UNet to separate the license plate character sequence into each attention heatmap in order. This approach unifies license plates with different character lengths and different character rows into a single processing logic, thereby enabling CLPRNet to recognize multiple styles without additional style judgement branches. At the same time, we abandon the traditional method of cropping RoI from image or feature, and instead combine attention to recognize characters directly, which allows CLPRNet to recognize multiple license plates in a single pass. To address the issue of an inadequate number of multi-style license plate samples, this paper also proposes a multi-style license plate generation method. In the single-stage methods, CLPRNet demonstrates better detection performance on the CCPD dataset and better recognition performance on the FN, Rotate, and Tilt subsets of the CCPD dataset. Compared with the existing license plate recognition methods, CLPRNet can recognize more styles of license plates. Test results and ablation experiments have shown the effectiveness of our proposed method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v260-wu25a, title = {A Single-Stage Multi-Style License Plate Recognition Method Based on Attention}, author = {Wu, Longbin and Liu, Sen and Xie, Yufei and Lee, Haowei and Duan, Xiaohui}, booktitle = {Proceedings of the 16th Asian Conference on Machine Learning}, pages = {495--510}, year = {2025}, editor = {Nguyen, Vu and Lin, Hsuan-Tien}, volume = {260}, series = {Proceedings of Machine Learning Research}, month = {05--08 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v260/main/assets/wu25a/wu25a.pdf}, url = {https://proceedings.mlr.press/v260/wu25a.html}, abstract = {Automatic license plate recognition is applied widely in life, but it is still a challenging task in open scenarios. The current ALPR methods require multiple recognitions in multi-license plate scenarios. Furthermore, they have complex recognition structures and insufficient recognition capabilities for multi-style license plates. To solve the above problems, this paper proposes a single-stage multi-style multi-license plate recognition method based on the attention mechanism: CLPRNet. We use a spatial attention module based on UNet to separate the license plate character sequence into each attention heatmap in order. This approach unifies license plates with different character lengths and different character rows into a single processing logic, thereby enabling CLPRNet to recognize multiple styles without additional style judgement branches. At the same time, we abandon the traditional method of cropping RoI from image or feature, and instead combine attention to recognize characters directly, which allows CLPRNet to recognize multiple license plates in a single pass. To address the issue of an inadequate number of multi-style license plate samples, this paper also proposes a multi-style license plate generation method. In the single-stage methods, CLPRNet demonstrates better detection performance on the CCPD dataset and better recognition performance on the FN, Rotate, and Tilt subsets of the CCPD dataset. Compared with the existing license plate recognition methods, CLPRNet can recognize more styles of license plates. Test results and ablation experiments have shown the effectiveness of our proposed method.} }
Endnote
%0 Conference Paper %T A Single-Stage Multi-Style License Plate Recognition Method Based on Attention %A Longbin Wu %A Sen Liu %A Yufei Xie %A Haowei Lee %A Xiaohui Duan %B Proceedings of the 16th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Vu Nguyen %E Hsuan-Tien Lin %F pmlr-v260-wu25a %I PMLR %P 495--510 %U https://proceedings.mlr.press/v260/wu25a.html %V 260 %X Automatic license plate recognition is applied widely in life, but it is still a challenging task in open scenarios. The current ALPR methods require multiple recognitions in multi-license plate scenarios. Furthermore, they have complex recognition structures and insufficient recognition capabilities for multi-style license plates. To solve the above problems, this paper proposes a single-stage multi-style multi-license plate recognition method based on the attention mechanism: CLPRNet. We use a spatial attention module based on UNet to separate the license plate character sequence into each attention heatmap in order. This approach unifies license plates with different character lengths and different character rows into a single processing logic, thereby enabling CLPRNet to recognize multiple styles without additional style judgement branches. At the same time, we abandon the traditional method of cropping RoI from image or feature, and instead combine attention to recognize characters directly, which allows CLPRNet to recognize multiple license plates in a single pass. To address the issue of an inadequate number of multi-style license plate samples, this paper also proposes a multi-style license plate generation method. In the single-stage methods, CLPRNet demonstrates better detection performance on the CCPD dataset and better recognition performance on the FN, Rotate, and Tilt subsets of the CCPD dataset. Compared with the existing license plate recognition methods, CLPRNet can recognize more styles of license plates. Test results and ablation experiments have shown the effectiveness of our proposed method.
APA
Wu, L., Liu, S., Xie, Y., Lee, H. & Duan, X.. (2025). A Single-Stage Multi-Style License Plate Recognition Method Based on Attention. Proceedings of the 16th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 260:495-510 Available from https://proceedings.mlr.press/v260/wu25a.html.

Related Material