An Intelligent and Real-Time System for Plate Recognition under Complicated Conditions

Vehicle Plate Recognition (VPR) algorithm inimages and videos usually consists of the following three steps: 1)Region extraction of the plate (plate localization), 2) characterssegmentation of the plate 3) Recognition of each character. Thispaper presents new methods for real-time plate recognition ineach step. We used a Detector for the Blue Area (DBA) to locatethe plate, Averaging of White Pixels in Objects (AWPO) for thecharacter segmentation, then of method the Euclidian distanceand template matching for character recognition after training.This system used 250 vehicle images with different backgroundsand non-uniform conditions. The proposed system is robustagainst challenges such as illumination and distance changes, anddifferent angles between camera and vehicle, the presence ofshadow, scratches and dirt on the plates. The accuracy rate forthe three stages are 91.6%, 89% and 95.09% respectively. Thereal-time recognition of plates for vehicles is 2.3 seconds, too

Keywords:

Real-time Plate Recognition , Plate Localization Character Segmentation , Template Matching , Euclid Distance ,