License plate identification based on image processing techniques

Abstract

A license plate identification system can be used for numerous applications such as unattended parking lots, security control of restricted areas, traffic law enforcement and automatic toll collection. Such a system captures images of vehicles and identifies license plate numbers automatically. Here we present results of a system in identifying the vehicle license plate through digitized photographic images based on image processing techniques. The developed algorithm is based on two basic processing stages; locating the license plate, and, identifying the individual digits and characters in the license plate. The algorithm takes a raster image of the rear view of a vehicle as input and yields the recognized numbers and characters in the number plate as the output. The performance of the developed algorithm has been tested on a set of real images of vehicles. The first part of the system showed that the algorithm performs quite well in accurately locating the license plates (with 97% efficiency). In the second part which is based on neural network techniques, showed high performance in recognizing digits and characters in located plate regions.