Damaged number plate detection to improve the accuracy rate using bernsen algorithm over genetic algorithm

Innovative Automatic detection of vehicle number plates using machine learning algorithms and improving the accuracy of recognition. Two sample groups using 237 images forms the sample dataset, which is tested at 80% for G power with t-test analysis. To improve the accuracy of recognition, the berns...

Full description

Saved in:
Bibliographic Details
Main Authors: Petlu, Maheswari, Shanmugam, Udhayakumar, Elangovan, Karthik
Format: Conference Proceeding
Language:English
Subjects:
Damage detection
Genetic algorithms
Machine learning
Roadsides
Vehicle identification
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Innovative Automatic detection of vehicle number plates using machine learning algorithms and improving the accuracy of recognition. Two sample groups using 237 images forms the sample dataset, which is tested at 80% for G power with t-test analysis. To improve the accuracy of recognition, the bernsen algorithm is proposed and compared with the genetic algorithm. Test results prove that in an uneven illuminated environment the bernsen algorithm has an accuracy of 91.5 %, which seems to be better than the genetic algorithm’s accuracy of 88.9%. Since the significance is around 0.17, there is a statistically significant difference among the study group with (p
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0134437