New framework based on complementary methods for efficiency and accuracy of license plate recognition system

Abstract

This paper represents a new and intelligent system for license plate recognition used in many cases, for example: unattended parking lots, security control of restricted areas, traffic law enforcement, congestion pricing, and automatic toll collection. The proposed system is a process based on a combination of the complement methods that increases the accuracy of output data and is generally accountable on the images that have many problems and aren't answerable with a particular approach. The performance of this system is in a form that, firstly, the input image is given to all the complement methods in order for the location of the plate candidate to be determined, then their response is investigated according to the valence function and finally the location of plate is properly determined by the majority of votes and ensures the accuracy of output data. If the complement methods are chosen correctly, this proposed system will be responsive to the images in which the license plate recognition is likely. This method has been tested on two data sets that have different images of the background, considering the distance, and angle of view so that the correct extraction rate of plate location reached at 100% and 99% respectively.