🤖 AI Summary
To address the challenges of recognizing diverse Chinese and English license plates under open-world conditions—characterized by complex imaging environments and scarce annotated bilingual plate data—this paper proposes a lightweight vision-language collaborative framework. Methodologically, it integrates a lightweight Vision Transformer (ViT) visual encoder with a sequence transcription decoder, and introduces a novel perspective correction module jointly supervised by corner-point regression and viewpoint classification to enhance robustness and interpretability. Additionally, synthetic data augmentation, texture-mapping-based realism enhancement, and a coordinate-regression auxiliary network are incorporated to reduce annotation dependency. Evaluated on the CCPD dataset, the framework achieves 99.34% recognition accuracy under coarse localization interference, 99.58% under precise localization, and 98.70% for bilingual plates, operating at 167 FPS—demonstrating both high accuracy and practical efficiency.
📝 Abstract
License plate recognition in open environments is widely applicable across various domains; however, the diversity of license plate types and imaging conditions presents significant challenges. To address the limitations encountered by CNN and CRNN-based approaches in license plate recognition, this paper proposes a unified solution that integrates a lightweight visual encoder with a text decoder, within a pre-training framework tailored for single and double-line Chinese license plates. To mitigate the scarcity of double-line license plate datasets, we constructed a single/double-line license plate dataset by synthesizing images, applying texture mapping onto real scenes, and blending them with authentic license plate images. Furthermore, to enhance the system's recognition accuracy, we introduce a perspective correction network (PTN) that employs license plate corner coordinate regression as an implicit variable, supervised by license plate view classification information. This network offers improved stability, interpretability, and low annotation costs. The proposed algorithm achieves an average recognition accuracy of 99.34% on the corrected CCPD test set under coarse localization disturbance. When evaluated under fine localization disturbance, the accuracy further improves to 99.58%. On the double-line license plate test set, it achieves an average recognition accuracy of 98.70%, with processing speeds reaching up to 167 frames per second, indicating strong practical applicability.