License plate character recognition method based on SURF matching algorithm

Abstract

The invention discloses a simple and effective license plate character recognition method based on an SURF (Speeded-up Robust Features) matching algorithm. The license plate character recognition is conducted by secondary classification of license plate character images, description of SURF keypoints and matching of features. The license plate character recognition method based on the SURF matching algorithm has good affine invariance, and good adaptability to scaling, visual angle variation, illumination difference, shielding and noise, and has higher computing speed compared with the current mainstream feature recognition method. According to the method, license plate characters are integrally classified for the first time, and the characters of the same class are individually subjected to secondary classification, and such classification mode allows the difference of similar characters to be greater and further increases the recognition rate.

Description

technical field [0001] The invention relates to the technical field of pattern recognition and image processing, in particular to a license plate character recognition method based on a SURF feature matching algorithm. Background technique [0002] In intelligent traffic system, video technology has become the main technical means. The license plate recognition system based on video technology has developed rapidly in recent years. License Plate Recognition (LPR) is an indispensable part of the intelligent transportation system. It has been widely used in various fields of transportation, such as highway toll collection, high-speed speeding detection, urban vehicle violation detection and road violation management (running red lights, speeding, retrograde) and other fields, license plate recognition has played a pivotal role. And with the increasing number of cars, the license plate recognition system is also used in security checkpoints (vehicle recording systems), stolen...

AI Technical Summary

Problems solved by technology

However, due to the complex and changeable environment in which the license plate recognition system is used, it is difficult to obtain widely acceptable recognition results.

Although some methods have achieved a certain improvement in the recognition effect, the method is too complicated, or the recognition speed is difficult to meet the requirements.

The characters separated from the actual license plate image are often affected by some external factors, and there are problems such as fracture, deformation, distortion, and staining, which bring great difficulties to character recognition.

Because the automatic license plate recognition system takes pictures outdoors, it is affected by factors such as weather, light, background, license plate model and specification, vehicle speed, license plate defects, pollution and occlusion, and there are uncertainties

These will interfere with the real-time processing and pattern recognition of the system

Images