License plate recognition non-inductive payment system based on deep learning

Abstract

The invention discloses a license plate recognition non-inductive payment system based on deep learning, and the system is used for recognizing a license plate through a preset neural network and carrying out the non-inductive payment through combining with a third-party payment system, improves the recognition accuracy, and reduces the parking time of a vehicle. The system comprises a license plate high-definition image acquisition module, an image preprocessing module, a license plate detection module, a feature fusion module, a license plate feature information identification module, an identification result storage module, a third-party payment module and an information pushing module. The license plate high-definition image acquisition module is used for acquiring an original licenseplate image acquired by the high-definition camera at a road gate or a vehicle management entrance / exit; the image preprocessing module is used for screening out a target license plate image meeting requirements from the original license plate images; the license plate detection module is used for extracting a color feature image and a character feature image of the target license plate image; andthe feature fusion module is used for fusing the color feature image and the character feature image into a feature information image of the target license plate.

Description

technical field [0001] The present invention relates to the field of deep learning, in particular to a vehicle plate recognition non-inductive payment system based on deep learning. Background technique [0002] The intelligent management of vehicles has become a common social problem, and the detection and recognition of license plates is one of the main parts of intelligent vehicle management. Identify and record. [0003] At present, the license plate detection and recognition technology has matured and achieved good results. However, most recognition methods are based on single-feature analysis. In complex scenarios, there are errors in the recognition of license plates of different specifications, and the accuracy rate is low. . Contents of the invention [0004] The invention provides a license plate recognition non-inductive payment system based on deep learning, which is used to identify the license plate through a preset neural network and perform non-inductive ...

AI Technical Summary

Problems solved by technology

[0003] At present, the license plate detection and recognition technology has matured and achieved good results. However, most recognition methods are based on single-feature analysis. In complex scenarios, there are errors in the recognition of license plates of different specifications, and the accuracy rate is low.

Images