Scholarlink

License plate recognition system is currently a popular research direction in the field of image recognition. In this paper, a Raspberry Pi-based license plate recognition system is designed, including three hardware modules: camera module, power supply module and LCD display module. These three modules collaborate with each other to accomplish the task of implementing license plate recognition in Raspberry Pi under various scenarios. This paper introduces the composition, hardware construction, program design and functions of the system, and verifies the reliability and stability of the designed system through simulation tests. Firstly, the power supply module provides power for Raspberry Pi 3B+ and other hardware. The Raspberry Pi 3B+ system selects photo recognition or video recognition of license plate information according to the external signal input. The picture or video frame image captured by the camera is input to the Raspberry Pi main control chip. The Raspberry Pi master chip analyzes and processes the data, locates the license plate location and inputs the trained caffe network model for character segmentation and recognition and derives the license plate information. Finally, the recognized license plate information is displayed in real time through an external display. This system is based on Raspberry Pi 3B+ hardware device, using Raspbian system to host pytho3.7 platform, combined with ssd target detection algorithm, refinenet semantic segmentation algorithm, in HyperLPR framework using opencv image processing library and caffe neural network framework to achieve accurate recognition of vehicle license plate. Both picture and camera can be used to detect license plate information.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Deep Learning Approach for License Plate Recognition Using Semantic Segmentation in the HyperLPR Framework

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mughair Aslam Bhatti,
  • Tang Hao,
  • Uzair Aslam Bhatti,
  • Sijjad Ali,
  • Anorgul Ashirova,
  • Muzaffar Shojonov,
  • Sibghat Ullah Bazai

摘要

License plate recognition system is currently a popular research direction in the field of image recognition. In this paper, a Raspberry Pi-based license plate recognition system is designed, including three hardware modules: camera module, power supply module and LCD display module. These three modules collaborate with each other to accomplish the task of implementing license plate recognition in Raspberry Pi under various scenarios. This paper introduces the composition, hardware construction, program design and functions of the system, and verifies the reliability and stability of the designed system through simulation tests. Firstly, the power supply module provides power for Raspberry Pi 3B+ and other hardware. The Raspberry Pi 3B+ system selects photo recognition or video recognition of license plate information according to the external signal input. The picture or video frame image captured by the camera is input to the Raspberry Pi main control chip. The Raspberry Pi master chip analyzes and processes the data, locates the license plate location and inputs the trained caffe network model for character segmentation and recognition and derives the license plate information. Finally, the recognized license plate information is displayed in real time through an external display. This system is based on Raspberry Pi 3B+ hardware device, using Raspbian system to host pytho3.7 platform, combined with ssd target detection algorithm, refinenet semantic segmentation algorithm, in HyperLPR framework using opencv image processing library and caffe neural network framework to achieve accurate recognition of vehicle license plate. Both picture and camera can be used to detect license plate information.