A Robust and Efficient Method for Improving Accuracy of License Plate Characters Recognition

TL;DR

This paper introduces a robust and efficient license plate character recognition method using contour-based features and K-NN classifier, achieving over 99% accuracy on a dataset of 1200 samples.

Contribution

The paper presents a novel contour-based feature extraction combined with K-NN classification for license plate character recognition, improving accuracy and robustness.

Findings

99% correct recognition rate on dataset

Average 99.41% accuracy with validation

Effective contour and feature-based approach

Abstract

License Plate Recognition (LPR) plays an important role on the traffic monitoring and parking management. A robust and efficient method for enhancing accuracy of license plate characters recognition based on K Nearest Neighbours (K-NN) classifier is presented in this paper. The system first prepares a contour form of the extracted character, then the angle and distance feature information about the character is extracted and finally K-NN classifier is used to character recognition. Angle and distance features of a character have been computed based on distribution of points on the bitmap image of character. In K-NN method, the Euclidean distance between testing point and reference points is calculated in order to find the k-nearest neighbours. We evaluated our method on the available dataset that contain 1200 sample. Using 70% samples for training, we tested our method on whole samples and obtained 99% correct recognition rate.Further, we achieved average 99.41% accuracy using three/strategy validation technique on 1200 dataset.