License plate recognition method based on multi-task learning strategy training network model and system thereof

Abstract

The invention provides a license plate recognition method based on a multi-task learning strategy training network model and a system thereof, and the method comprises the following steps: collecting and marking license plate sample pictures used for training a license plate type recognition network model, building a license plate type recognition network model based on deep learning, determining a multi-task learning framework, training a license plate category recognition network model based on deep learning by using the license plate sample pictures in the training set, fixing parameters of the trained license plate category recognition network model, and testing the comprehensive performance of the license plate category recognition network model based on deep learning by using the license plate sample pictures in the test set, and exporting a trained license plate category recognition network model. The license plate category identification method disclosed by the invention has the advantages of light and rapid model, accurate identification, easy deployment, adaptation to various complex scenes and the like, and can be compatible with accurate identification of single-double categories and color categories of gray license plate images and color license plate images.

Description

technical field [0001] The invention relates to digital image processing technology and pattern recognition technology in the field of computer vision, in particular to a license plate recognition method and system based on multi-task learning strategy training network model. Background technique [0002] With the rapid development of economy and society, the number of motor vehicles is also increasing. Realizing automatic identification of vehicle identities can improve vehicle management efficiency and reduce labor costs. Therefore, license plate recognition technology has become a research hotspot in recent years. The license plate category recognition method is an important part of the license plate recognition technology. It can identify the specific category of a given license plate picture, thereby supplementing and improving the license plate recognition information, and can be further used in more complex application scenarios such as deck detection and vehicle acc...

AI Technical Summary

Problems solved by technology

The limitation of this method is that infrared images are usually difficult to obtain, the color information of the license plate is lost, and the character information of the license plate needs to be additionally determined, and the corresponding relationship between the color and character information of the license plate is relatively vague for most license plates

Images