A license plate recognition method and system in a strong backlight environment

By grayscale and histogram analysis of backlight images, high-quality images are screened and stitched, the problem of license plate recognition under backlight conditions is solved, and high-precision and efficient license plate recognition are achieved.

CN119478914BActive Publication Date: 2025-03-25SHAANXI HIGH SPEED ELECTRONIC ENG CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510074111.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-01-17
Publication Date
2025-03-25
Estimated Expiration
2045-01-17

AI Technical Summary

Technical Problem

Under backlight conditions, it is difficult for the camera to clearly capture license plate information. The existing methods have poor image restoration and are difficult to meet the needs of high-precision recognition.

Method used

By collecting vehicle backlight images, greyscale and grayscale histogram analysis are performed, maximum value points are extracted and grayscale separation points are determined, threshold segmentation is performed to obtain foreground and background areas, high-quality images are filtered and sorted and stitched, the degree of backlight and edge characteristics are evaluated, and the license plate recognition image is finally obtained.

Benefits of technology

It significantly improves the accuracy and efficiency of license plate recognition in backlight environments, enhances the robustness of the system, and ensures the accurate extraction of image quality and license plate information.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to the field of image data processing technology, and in particular to a license plate recognition method and system in a strong backlight environment, comprising: graying the collected image to obtain a gray backlight image; extracting the gray histogram of each image and determining the maximum point, evaluating its peak attribute by the gray difference and pixel number of the maximum point, and then determining the gray separation point; performing threshold segmentation on the image, extracting the foreground and background areas, and calculating the reference value index, and screening out high-quality foreground and background images by threshold judgment; sorting the high-quality images, obtaining the retention index, and performing threshold judgment again to determine the foreground and background images to be retained first; arranging and combining them to form a spliced ​​image, evaluating the backlight degree and edge features, finally sorting to obtain the fitness, extracting the license plate character code, forming a complete license plate number, and realizing license plate recognition in a strong backlight environment. The present invention aims to improve the accuracy of license plate recognition in a backlight environment.
Need to check novelty before this filing date? Find Prior Art