A novel license plate recognition system using YOLO in comparison with histogram of oriented gradient algorithm for better accuracy

View at publisher Summarise with VIRAT
Authors: Shaik Jigunu, W. Deva Priya, T. Srihari
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The major goal of the study is to compare the HoG Algorithm with YOLO for license plate recognition in the context of intelligent transport systems. By automating vehicle identification, License Plate Recognition (LPR) improves security, law enforcement, and traffic management. It decreases errors and manual labour in fleet tracking, parking management, and toll collecting. Materials and Procedures: Using a total of 2000 samples, 1600 were utilised for training and 400 for testing, the histograms of the YOLO method and the orientated gradient algorithm were compared as two groups. In order to measure accuracy, the statistical comparison used a G-power (alpha) value of 0.8. Results: YOLO outperforms HoG, Algorithm, which has an accuracy rate of 81.96%, with a higher accuracy rate of 91.30%. The Independent Sample T-Test yielded a statistically significant value of 0.007, according to the study. This p-value shows that the study’s findings are statistically significant because it is below the 0.05 cutoff ( p

Fields of Study & Subjects

Vehicle License Plate Recognition Advanced Neural Network Applications Video Surveillance and Tracking Methods

Publication details

Journal / source
CRC Press eBooks
Pages
68–73
Publication date
25 March 2026
Language
EN
Document type
Book chapter