期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：7
出版社：S.S. Mishra
摘要：License plate recognition in vehicles is a major problem due to the acquisition of images because vehicles are generally in motion, and weather conditions like sunlight, fog. The images of licence plate may also contain black borders or some stickers. License plate recognition not only involves recognition of characters but also pre-processing of licence plate. In this paper, the images of the vehicle's licence plate are collected from the car parking areas and from the web. First, the any noise, black border or any unwanted region other than character present on the image is removed. Then each individual character is segmented. The features of each character are calculated using Gaussian Hermite Moments and wavelets. These features are used as input to the neural networks for character recognition. The recognition rate of neural networks using wavelets and Gaussian Hermite Moments are also compared with the Moment Invariants and Principal Component Analysis. The recognition rate of neural network is 97.6%.
