Method and system for discriminating license plate

Abstract

The invention discloses a license plate recognition method, which comprises collecting video stream; whether the license plate recognition is to be triggered or not is judged according to the video stream and a vehicle deceleration enabling signal; when the license plate recognition is judged to be carried out, the video stream is taken as an input image; according to the input image, the edge information of the license plate is calculated and the position of a license plate region is determined, furthermore, a license plate image after correction is obtained according to the edge information; character segmentation is carried out on the license plate image after correction so as to obtain the image of each character; a classifier obtained by pre-training is utilized for recognizing the image of each character, and a final license plate recognition result is obtained according to the recognized character. Meanwhile, the invention also discloses a license plate recognition system. The license plate recognition method and the system disclosed by the invention determines whether the license plate recognition is to be triggered or not according to the video stream and the vehicle deceleration enabling signal, reduces erroneous inspection caused by interferent, carries out installation and debugging without damaging roads, and has lower installation and maintenance cost.

Description

technical field [0001] The invention relates to a license plate recognition technology, in particular to a license plate recognition method and system. Background technique [0002] At present, with the rapid development of computer technology, the information processing ability of computer is constantly improving. Image recognition technology has also developed rapidly with the improvement of computer processing capabilities. Among them, intelligent traffic and electronic police systems based on multimedia and artificial intelligence technology have been widely used around the world. Among these applications, 96% of the automated systems use the automatic license plate recognition technology, and more than 75% of the systems use license plate recognition as the core application. [0003] License plate recognition refers to obtaining the license plate area existing in a certain area of ​​the image from a static or dynamic video image, and further recognizing the characters ...

AI Technical Summary

Problems solved by technology

[0007] Using the above method, the required license plate information can be identified from the video stream. However, the existing method needs to bury the ground induction coil or erect the infrared light curtain in advance, and it takes a lot of manpower and material resources to debug the sensitivity of the ground induction coil or light curtain. , and once there is a problem with the system operation or the equipment is aging and needs to be updated, it is necessary to destroy the road and re-lay the ground induction coil or erect the induction light curtain, so the maintenance cost is relatively high

[0008] At the same time, the ground induction coil and the infrared induction light curtain are prone to false detection

For example: when a non-vehicle object passes the ground sensing coil, or when obstacles such as people or animals enter the sensing area of ​​the infrared sensor light curtain, it may also trigger the license plate recognition device to detect, resulting in false detection and frequent system failures. trigger, resulting in a waste of device resources

[0009] To sum up, it can be seen that the current license plate recognition scheme has a high cost of actual installation and maintenance and a high false detection rate during use.

Images