License plate classification method, license plate classification device and computer readable storage medium

Abstract

The invention discloses a license plate classification method, a license plate classification device and a computer readable storage medium, and the method comprises the steps: carrying out license plate recognition of a first license plate image, and obtaining a license plate recognition result; encoding the license plate recognition result to obtain a first license plate feature; performing feature extraction on the first license plate image to obtain a second license plate feature; and processing the first license plate feature and the second license plate feature by using a classification network to obtain a first license plate classification result. In this way, the accuracy of license plate classification can be improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a license plate classification method, a license plate classification device and a computer-readable storage medium. Background technique [0002] Overseas license plate classification technology refers to the country where a license plate is input and the license plate belongs to. The current license plate classification technology is mainly divided into two categories: traditional image processing methods and deep learning. Compared with traditional image processing methods, deep learning-based license plate The classification method has higher accuracy, is suitable for various types of license plate classification, and has a wider application range. However, because the overseas license plate country classification task needs to obtain the license plate data of various overseas countries, it is difficult to collect complete data, which has high requirements ...

AI Technical Summary

Problems solved by technology

However, because the overseas license plate country classification task needs to obtain the license plate data of various overseas countries, it is difficult to collect complete data, which has high requirements for the generalization ability of the classification model; in addition, some countries (especially those with similar geographical locations) National) license plates have high similarity and are difficult to distinguish. Some countries have a wide variety of license plates, that is, there is a problem of "small differences between classes and large differences within classes", resulting in low classification accuracy

Images