Number Plate Recognition System
Li, Ziqi (2025)
2025
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-202504156574
https://urn.fi/URN:NBN:fi:amk-202504156574
Tiivistelmä
This thesis presents the development and implementation of a Number Plate Recognition (NPR) system. The primary objective was to design a system capable of processing images to detect and recognize license plate text.
The system was built using a React-based frontend and a Python-based backend. The frontend provides an interface for uploading images, while the backend uses two identification solutions. The first is YOLO (You Only Look Once) for object detection and EasyOCR for text recognition. The second is Azure's Custom Vision for object detection and computer vision for text recognition.
The results demonstrate that the system can successfully detect license plates and recognize text under various conditions. Limitations include occasional misdetections due to blurred images or obstructed plates. Future development proposals include real-time video stream processing and further integration with intelligent traffic management systems.
The system was built using a React-based frontend and a Python-based backend. The frontend provides an interface for uploading images, while the backend uses two identification solutions. The first is YOLO (You Only Look Once) for object detection and EasyOCR for text recognition. The second is Azure's Custom Vision for object detection and computer vision for text recognition.
The results demonstrate that the system can successfully detect license plates and recognize text under various conditions. Limitations include occasional misdetections due to blurred images or obstructed plates. Future development proposals include real-time video stream processing and further integration with intelligent traffic management systems.