The Research And Implementation Of Algorithms Of License Plate Localization And Character Segmentation

License plate recognition (LPR) is the technique to draw the character information from the vehicle image and confirm the identity of the vehicle through using computer vision, image processing, pattern recognition, and so on. LPR is an important study field in the Intelligent transportation system (ITS), and it has great apply value in the common security, traffic management, flow observation and electronic charge system.LPR consists of plate localization, character segmentation, and character recognition. This paper aims at researching the following two aspects of the license plate recognition system: license plate localization and character segmentation.A license plate localization algorithm based on sliding-window searching including two steps: primary localization and precise localization, was proposed in this paper. Primary localization process utilized the denseness of pixels whose direction is vertical to locate the plate. The counts of feature pixels in a fixed size sliding-window was calculated to find the approximate candidate regions. Precise localization process located the boundary of the license plate through adopting row scanning method to measure the interval between the license plate region and the outboard region. In order to correct the slant license plate, a method based on horizontal projection of rotation images was proposed which has the advantages of rapidness and effect.Character segmentation is the key step of the LPR and is the base of character recognition. A segmentation method of vertical projection combined with the prescient knowledge of the characters in the license plate is brought forward and it solved those problems such as non-integrity, position shift, character abrasion, character distortion, and so on. Meanwhile, in order to detect the false license plate region, a Haar-like feature was proposed in this paper.The algorithm we adopted is not restricted by the location and the size of the plate in the image, and it has strong anti-jamming ability to lean,distortion,pollution and blur, and has great robustness and real-time.