Research Of Car License Plate Recognition Technology

With the rapid development of the road transportation,ITS (Intelligent Transport System)has been considered as a serious problem.The automatic license-plate recognition (LPR)system is the important part of ITS and plays an important role in people's daily life.So it is necessary for us to do more research for it.Generally,LPR system mainly comprises modules of plate location,character isolation and character recognition. This dissertation studies the critical technologies of automatic plate recognition,including plate image preprocessing,plate location,character segmentation and character recognition.The author completed a full set of software algorithms and made a large number of experiments.Image preprocessing is the most critical step in license plates and identification.Based on the integrate treatment of the various pictures,this dissertation sums up the pretreament methods,such as gray,median filtering and expanding contrast,eliminated the noises of images nicely.In the part of plate location,based on the study of plate features and location positioning technology,this dissertation has completed the plate location methods for plate features and mathematical morphology with a real number plates,it presents an improved median filtering method,and has extracted plate regions accurately.Before the plate characters segmentation,the dissertation proposes an algorithm of license plate binary used top-hat operation,maintains the integrity of the plate characters nicely.In the part of plate segmentation,uses dim plate matching and vertical projecting to devide the single character.In the part of character recognition,it presents a recognition algorithm based on back propagation artificial neural network,which is simple,but has strong resistance to noise and higher recognition rate.