A High Performance Algorithm of Vehicle Plate Location and Recognition in Intelligent Transportation

Abstract

For the problem of slow plate location, the low accuracy of information identifying in the intelligent transportation system, a new algorithm of vehicle plate location and character recognition with high performance is presented in this paper. Firstly, the vehicle plate image is pre-processed, and then search for the edge of rapidly protruding rectangular, collect the similar trend of bilateral curve in the search area of rectangular, then selected the area with outstanding bilateral similar characteristics, so locate the true license plate which contains characters. Finally, match with the bit weight value of the multi-template by the improving neural network model, and identify the characters. The proposed algorithm focuses on the rectangular features of license plates and the important features of parallel bilateral with character, to the use of algorithm with the new parallel ectopic template removed improved the speed of vehicle plate location and the accuracy of character recognition.