The Design Of License Plate Recognition System Based On HSI Color Space

LPR(License Plate Recognition)is an important component part of intelligent transportation system, and it is based on computer vision technology, through the license plate region orientation, license plate character segment and license plate character recongnition to process the vehicle image, and then get the vehicle license plate number. License Plate Recognition system is widely used in vehicle control system, traffic monitoring system, and the development of that has important significance in the realized of Intelligent Transportation System, the urban traffic safety maintenance, and prevent traffic jams.This paper first use of color characteristics, the texture characteristics and geometric features of vehicle images, proposed a novel algorithm based on combination of multi-component edge license plate location in the HSI color space; And then in the location of the licence in regional pretreatment of basis, use the vertical projection method to segment the license plate character; Finally use the template matching method to identify the license plate character. The simulation results show that the algorithm can satisfy the License Plate Recognition system accuracy and speed requirements.In system dsign, this paper used the S3C2440A processor of the ARM series as system platform, the first transplant BSP (Board Support Package), then customize the Windows Embedded CE 6.0 operating system, finally based on this algorithm to write the License Plate Recognition software, and implements a License Plate Recognition system based on ARM processor.