Modified ANPR using Neural Networks

Abstract

Number Plate Recognition is a mass observation technique which is used to identify the vehicles. The identification and acknowledgement of a vehicle license plate is a key method in the greater part of applications related to vehicle movement. Moreover, it is a very famous and dynamic research subject in the field of image processing. Since every vehicle have a unique plate number, so if we have to perceive a specific vehicle we can utilize the license plate. The main objective of automatic vehicle number plate recognition is to design an efficient automatic authorized vehicle identification system by using the number plate. It has three modules namely license plate extraction, segmentation and recognition. . Different methods, techniques and algorithms have been developed to detect and recognize license plates. Nevertheless, due to the license plate characteristics that vary from one country to another in terms of numbering system, colours, language of characters, fonts and size. Further investigations are still needed in this field in order to make the detection and recognition process very efficient. Although this domain has been covered by a lot of researchers, various existing systems operate under well-defined and controlled conditions. For example, some frameworks require complicated hardware to make good quality images or capture images from vehicles with very slow speed. For this reason the detection and recognition of number plates in different conditions and under several climatic variations remains always difficult to realize with good results. For that, we present an automatic system for number plate detection and recognition based on convolutional neural networks. CNN has proved its robustness even with distorted, tilted and illuminated datasets.