Enhancing Image Recognition of Damaged Number Plate in the Running Vehicle using Genetic Algorithm Compared with Morphological Dilation Algorithm

Abstract

Aim: Automatic number plate detection of damaged number plates of the vehicle using image processing algorithms and improving the accuracy rate of readability in recognition of the number plates. Materials and methods: Two sample groups using 237 images from the sample dataset, which is tested at 80% for G power with t-test analysis. To improve the accuracy of recognition, the genetic algorithm is proposed and compared with the morphological dilation algorithm. Results: Test results prove that the genetic algorithm has an accuracy of 92.8%, which seems to be better than the morphological dilation algorithms accuracy of 90.82%. Since the significance is around 0.046, there is a statistically significant difference among the study group with (p<0.05). Conclusion: For distorted and damaged images, the detection and recognition of number plates using the genetic method seems to appear better than the morphological dilation algorithm. Detection of violations using road side cameras can perform better with proposed work.