A Simple Number Plate Detection Technique with Support Vector Machine for On-Road Vehicles

Abstract

A Number Plate Detection Technique is a well-known and widely used tool during current era because of the rapid increase in vehicles day by day. The detection of number plates from traffic videos / images system uses a digital image processing technique for the identification of the car registration number plate on the vehicles. This device is utilized indensely populated region to spot the vehicles which are violating the traffic rules, are handed down in malls to allot automobile parking space, identification of the stolen vehicles and also helpful in crime scene investigation. Image of the vehicle is pre-processed by reading the image from a dataset (b) converting it into a gray-scale image and (b) by removing the noises from the image using Gaussian techniques. This number plate is extracted from the image by implementing the contour enhancement method and on extracted characters, machine learning algorithms are used to train the model to perform the segmentation. Within the character recognition process, we classify the characters. The proposed number plate detection technique shows significant improvement in accuracy rate when compared with standard existing systems.