A Robust Method of License Plate Recognition using ANN

The purpose of this paper is to design a system that can recognize vehicle license plate under poor environmental conditions by using neural network. Adverse environmental condition may refer to the image has been blurred by poor lighting, rain, poor image resolution and haze which make the image not clear. Recognition of a vehicle license plate is usually important for many security and control system. This paper presents a robust method of license plate location, segmentation and reorganization of the characters present in the located plate. The images of various vehicles have been acquired manually and then by cropping the license plate, number plate is extracted then segmentation of gray scale image generated by finding edges using Sobel filter for smoothing image is used to reduce the number of connected component and then bwlabel is used to calculate the connected component and finally, single character is detected. The results show that the proposed method achieved accuracy of 98% by optimizing various parameters with higher recognition rate than the traditional methods. Keywords— license plate, recognition, segmentation, neural network, noise, and filter.