A Sliding and Classifying Approach Towards Real Time Persian License PlateRecognition

Automatic License Plate Recognition, ALPR, is an important part of today’s traffic monitoring andtoll-gate systems. It usually consists of two major parts: plate localization and character recognition. Inthis paper, we propose a real-time algorithm for detection and recognition of Persian license plates infour styles. To be real time, we employ simple and effective techniques and implement our algorithmin pure C++. Unlike conventional methods for finding the location of the plate based on structuralfeatures, we use a sliding and classifying approach combined with some statistical information. Inrecognition phase, two fast and accurate features are trained by a neural network. The proposed systemis evaluated on 100 images of Iranian vehicles, taken from different highway/toll-gate cameras. Inlocalization phase, system detects 100% of the plates properly and in recognition phase, 97.8% ofcharacters are correctly recognized. The overall processing time for single plate is 0.06 s at resolutionof 407x309 and 0.24 s at resolution of 1150×650. These specifications made our algorithm industryreadyand currently. It is used by several corporations working on parking management and lawenforcement systems.