ABSTRACT
Automatic Number Plate Recognition (ANPR) is a type of image processing and pattern recognition technology used to recognize a vehicle's number plate from an image or video. Because of the limited increase in vehicles, which makes human monitoring impossible, ANPR has become a very vital tool in our daily life. Traffic monitoring, auto theft tracking, parking toll management, packing space management, and border checks are just a few examples. Due to the variety of plate formats, varied sizes, rotations, and non-uniform illumination conditions during image capture, it's a difficult task. We examine many approaches for character recognition in this project work.
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 neighbor (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; Optical Character Recognition (OCR) , Template Matching, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN).
