YOLOv8和LPRNet融合的车牌识别系统设计OA
Design of a License Plate Recognition System by integrating YOLOv8 and LPRNet
车牌检测与识别作为智能交通管理的重要组成部分,广泛应用于道路监管、停车场管理等场景.为提高车牌识别的准确性,本文构建一种高效快捷的车牌检测与识别系统.将YOLOv8 目标检测模型与LPRNet车牌识别网络结合运用,提升模型的精度与鲁棒性.测试的结果表明,系统对车牌检测与字符识别的精度达到85%,平均推理速度为40.30ms,具有较好的有效性与高效性.
License plate detection and recognition,as an important component of intelligent transportation management,are widely used in scenarios such as road supervision and parking lot management.To improve the accuracy of license plate recognition,this article constructs an efficient and fast license plate detection and recognition system.Combining YOLOv8 object detection model with LPRNet license plate recognition network to improve the accuracy and robustness of the model.The test results show that the system achieves an accuracy of 85%for license plate detection and character recognition,with an average inference speed of 40.30ms,demonstrating good effectiveness and efficiency.
林镕城;邱健数;赵章圳;邹佳铭
浙江工贸职业技术学院人工智能学院 浙江 温州 325026浙江工贸职业技术学院人工智能学院 浙江 温州 325026浙江工贸职业技术学院人工智能学院 浙江 温州 325026浙江工贸职业技术学院人工智能学院 浙江 温州 325026
计算机与自动化
深度学习卷积神经网络车牌识别车牌检测
Deep LearningConvolutional Neural NetworksLicense Plate DetectionLicense Plate Recognition
《福建电脑》 2025 (1)
85-89,5
本文得到2024年浙江省大学生科技创新活动计划(No.2024R455A005)资助.
评论