Lightweight license plate detection and recognition method based on multi-scale attention mechanism

Abstract

The invention provides a lightweight license plate detection and recognition method based on a multi-scale attention mechanism. Construction of a license plate detection and recognition network comprises the following steps: S1, obtaining pictures as an original data set; S2, processing the original data set to obtain a data set A used for training a model for detecting the license plate and a data set B used for training a model for recognizing the license plate; S3, constructing a deep neural network for detecting the license plate; S4, inputting the original image P1 of the data set A intothe network constructed in the S3 to obtain a license plate detection area P2 and four corners of the license plate; and S5, performing perspective transformation on the P2 according to the angular points of the license plate to obtain a corrected image P3. S6, constructing a deep neural network for recognizing the license plate; S7, inputting P3 into the network constructed in the S6 to obtain alicense plate number corresponding to the detected license plate. According to the invention, a relatively low network parameter quantity and a relatively low calculated quantity can be obtained simultaneously under the condition of ensuring the network accuracy.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a lightweight license plate detection and recognition method based on a multi-scale attention mechanism. Background technique [0002] With the gradual development of the economy, the number of cars is increasing year by year, and the urban traffic pressure we are facing is also increasing. How to efficiently carry out traffic management has become an urgent problem to be solved, and the license plate detection and recognition technology is in traffic management. From traffic violations to accident monitoring, the ability to automatically detect and recognize license plates is one of the key tools used by law enforcement agencies everywhere. The detection and recognition of license plates are not only widely used in road traffic management, but also widely used in parking lots, community security, and wanted vehicles for robbery and robbery. [0003] The traditional licen...

AI Technical Summary

Problems solved by technology

[0003] The traditional license plate detection and recognition method is divided into four stages: image acquisition, license plate location, character segmentation, and character recognition. The disadvantage of this method is that there are too many steps required, and the errors of each step are gradually accumulated. Inaccuracy will cause errors in license plate recognition; and the collected images used in traditional license plate detection and recognition are based on fixed angles, and the accuracy of license plate detection and recognition at large angles in natural scenes is poor.

The license plate detection and recognition method of deep learning has better performance, but because of the use of a deeper network, the parameters of the model are too large, the amount of calculation is too large, and it is difficult to deploy and run on the mobile terminal.

Images