Automatic License Plate Recognition (ALPR) is becoming a popular study area and is applied in many fields such as transportation or smart city. However, there are still several limitations when applying many current methods to practical problems due to the variation in real-world situations such as light changes, unclear License Plate (LP) characters, and image quality. Almost recent ALPR algorithms process on a single frame, which reduces accuracy in case of worse image quality. This paper presents methods to improve license plate recognition accuracy by tracking the license plate in multiple frames. First, the Adaptive License Plate Rotation algorithm is applied to correctly align the detected license plate. Second, we propose a method called Character Time-series Matching to recognize license plate characters from many consequence frames. The proposed method archives high performance in the UFPR-ALPR dataset which is \boldmath$96.7\%$ accuracy in real-time on RTX A5000 GPU card. We also deploy the algorithm for the Vietnamese ALPR system. The accuracy for license plate detection and character recognition are 0.881 and 0.979 $mAP^{test}[email protected] respectively. The source code is available at https://github.com/chequanghuy/Character-Time-series-Matching.git

翻译：自动车牌识别（ALPR）正成为热门研究领域，并广泛应用于交通、智慧城市等多个场景。然而，由于现实情境中光照变化、车牌字符不清晰及图像质量差异等可变因素，当前多数方法在实际应用中仍存在局限性。近期ALPR算法多基于单帧图像处理，在图像质量较差时识别精度显著下降。本文提出通过多帧车牌追踪提升识别精度的方法：首先，采用自适应车牌旋转算法对检测到的车牌进行精准对齐；其次，提出基于字符时间序列匹配的方法，从连续帧中识别车牌字符。所提方法在UFPR-ALPR数据集上达到高性能，在RTX A5000 GPU上实现实时处理，准确率为96.7%。同时将算法部署至越南ALPR系统，车牌检测与字符识别的mAP^[email protected]精度分别为0.881和0.979。源代码已开源：https://github.com/chequanghuy/Character-Time-series-Matching.git