COMPARISON OF CHARACTER RECOGNITION METHODS FOR NIGERIAN VEHICLE LICENSE PLATE NUMBER

ABSTRACT

Automatic Number Plate Recognition (ANPR) is an image processing and pattern recognition technology for recognising the vehicle number plate from an image or video of a vehicle. ANPR has become a very important tool in our daily lives because of the increase of vehicles plying the road, which make it difficult to be properly monitored by humans. ANPR has several use cases some of which are traffic monitoring, tracking of stolen cars, managing parking toll, packing space management and border checkpoints. In this work, an Automatic Number Plate Recognition (ANPR) System for Nigerian license plates is developed and a comparative analysis of the following character recognition methods; Optical Character Recognition (OCR), Template Matching, K-nearest neighbour (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN), is carried out to determine the most accurate for character recognition of Nigerian license plate characters. A detailed discussion on each method listed above has been carried out along with an implementation of each method in development of an ANPR system for Nigerian license plates, the output of each method at the character recognition stage was as follows; OCR , Template Matching, KNN, SVM, ANN.