摘要
传统的车牌识别系统采用多流程分步处理方式,容易累积误差,降低识别准确率。YOLO模型是一种深度学习目标检测算法,将目标定位、图像分割和识别整合为统一框架,利用卷积神经网络实现对图像目标的快速准确检测。本文提出基于YOLOv8模型设计一种车牌自动识别系统,介绍了车牌识别流程中的相关技术、系统分析与设计,通过模型训练对系统功能进行了实验验证。测试结果显示车牌识别成功率达到了预期效果。
The traditional license plate recognition system adopts a multi-step processing method,which is prone to accumulating errors and reducing recognition accuracy.The YOLO model is a deep learning object detection algorithm that integrates object localization,image segmentation,and recognition into a unified framework,utilizing convolutional neural networks to achieve fast and accurate detection of image targets.This paper proposes using the YOLOv8 model to design an automatic license plate recognition system,introduces the relevant technologies,system analysis,and design in the license plate recognition process,and experimentally verifies the system functions through model training.The test results show that the success rate of license plate recognition has achieved the expected effect.
作者
朱玲丽
吴许俊
安尘潇
江杨
Zhu Lingli;Wu Xujun;An Chenxiao;Jiang Yang(Department of Computer Science and Engineering,Taizhou Institute of Science and Technology,Nanjing University of Science and Technology,Taizhou,Jiangsu 225300,China)
出处
《计算机时代》
2025年第8期52-56,60,共6页
Computer Era
基金
江苏省大学生创新创业训练计划项目(202313842033Y)
2024年江苏高校“青蓝工程”优秀教学团队项目。
关键词
车牌识别
YOLOv8
卷积神经网络
图像目标
License Plate Recognition
YOLOv8
Convolutional Neural Network
Image Target
