Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Next-Generation License Plate Detection and Recognition System using YOLOv8

Arslan Amin, Rafia Mumtaz, Muhammad Jawad Bashir, Syed Mohammad Hassan Zaidi

TL;DR

This paper investigates real-time license plate detection and recognition using YOLOv8 variants across two curated datasets. It evaluates YOLOv8n, YOLOv8s, and YOLOv8m for license plate detection and YOLOv8s for character recognition, supplemented by a novel horizontal sequencing method to order detected characters. Key findings show Nano delivers top-tier precision for LPR while Small offers strong CR performance, and a combined Nano-for-LPR plus Small-for-CR pipeline yields an edge-friendly configuration with high accuracy. The work demonstrates a viable path toward robust, efficient LPR/CR systems suitable for deployment on edge devices in Intelligent Transportation Systems.

Abstract

In the evolving landscape of traffic management and vehicle surveillance, efficient license plate detection and recognition are indispensable. Historically, many methodologies have tackled this challenge, but consistent real-time accuracy, especially in diverse environments, remains elusive. This study examines the performance of YOLOv8 variants on License Plate Recognition (LPR) and Character Recognition tasks, crucial for advancing Intelligent Transportation Systems. Two distinct datasets were employed for training and evaluation, yielding notable findings. The YOLOv8 Nano variant demonstrated a precision of 0.964 and mAP50 of 0.918 on the LPR task, while the YOLOv8 Small variant exhibited a precision of 0.92 and mAP50 of 0.91 on the Character Recognition task. A custom method for character sequencing was introduced, effectively sequencing the detected characters based on their x-axis positions. An optimized pipeline, utilizing YOLOv8 Nano for LPR and YOLOv8 Small for Character Recognition, is proposed. This configuration not only maintains computational efficiency but also ensures high accuracy, establishing a robust foundation for future real-world deployments on edge devices within Intelligent Transportation Systems. This effort marks a significant stride towards the development of smarter and more efficient urban infrastructures.

Next-Generation License Plate Detection and Recognition System using YOLOv8

TL;DR

This paper investigates real-time license plate detection and recognition using YOLOv8 variants across two curated datasets. It evaluates YOLOv8n, YOLOv8s, and YOLOv8m for license plate detection and YOLOv8s for character recognition, supplemented by a novel horizontal sequencing method to order detected characters. Key findings show Nano delivers top-tier precision for LPR while Small offers strong CR performance, and a combined Nano-for-LPR plus Small-for-CR pipeline yields an edge-friendly configuration with high accuracy. The work demonstrates a viable path toward robust, efficient LPR/CR systems suitable for deployment on edge devices in Intelligent Transportation Systems.

Abstract

In the evolving landscape of traffic management and vehicle surveillance, efficient license plate detection and recognition are indispensable. Historically, many methodologies have tackled this challenge, but consistent real-time accuracy, especially in diverse environments, remains elusive. This study examines the performance of YOLOv8 variants on License Plate Recognition (LPR) and Character Recognition tasks, crucial for advancing Intelligent Transportation Systems. Two distinct datasets were employed for training and evaluation, yielding notable findings. The YOLOv8 Nano variant demonstrated a precision of 0.964 and mAP50 of 0.918 on the LPR task, while the YOLOv8 Small variant exhibited a precision of 0.92 and mAP50 of 0.91 on the Character Recognition task. A custom method for character sequencing was introduced, effectively sequencing the detected characters based on their x-axis positions. An optimized pipeline, utilizing YOLOv8 Nano for LPR and YOLOv8 Small for Character Recognition, is proposed. This configuration not only maintains computational efficiency but also ensures high accuracy, establishing a robust foundation for future real-world deployments on edge devices within Intelligent Transportation Systems. This effort marks a significant stride towards the development of smarter and more efficient urban infrastructures.

Paper Structure

This paper contains 13 sections, 1 equation, 5 figures, 4 tables.

Table of Contents

  1. Literature Review
  2. Dataset
  3. Mehthodology
  4. Dataset Preparation
  5. YOLOV-8 Architecture
  6. License Plate Recognition with YOLOv8 (n,s,m)
  7. Character Recognition using YOLOv8s
  8. Character Sequencing
  9. Evaluation
  10. Mean Average Precision (mAP)
  11. Loss Functions for Detection:
  12. Results & Discussion
  13. Conclusion

Figures (5)

  • Figure 1: Methodology Overview
  • Figure 2: YOLO c2F module Roboflow
  • Figure 3: LPR and Character Recognition Results
  • Figure 4: YOLO-V8 (n,s,m) - Training Performance on LPR Dataset
  • Figure 5: YOLO-V8s - Training Performance on Character Recognition Dataset