Image purple edge detection and correction method, device, equipment and medium

By using visible light and infrared image fusion technology, the purple edge region is accurately located, solving the problem of inaccurate purple edge detection under low light conditions and achieving adaptive correction and natural color effect.

CN122415485APending Publication Date: 2026-07-17SHENZHEN TVT DIGITAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHENZHEN TVT DIGITAL TECH CO LTD
Filing Date
2026-04-16
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies are inaccurate in detecting purple fringing under low light conditions, which can easily lead to over- or under-correction and affect the naturalness of image colors.

Method used

The visible light and infrared image fusion technology is used to determine the first candidate region by using the purple, brightness and edge features of the visible light image, and the edge and grayscale features of the infrared image to determine the second candidate region. The purple edge region is accurately locked through fusion and screening, and thermal shadow interference is eliminated based on the infrared grayscale features. Color saturation is adaptively adjusted and color repair is performed.

Benefits of technology

It significantly improves the accuracy of purple fringing detection in low-light and high-noise environments, avoids over- or under-correction caused by noise misjudgment, and the corrected image has natural color and no residue.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122415485A_ABST
    Figure CN122415485A_ABST
Patent Text Reader

Abstract

The application discloses an image purple edge detection and correction method, device, equipment and medium, and the method comprises the steps of acquiring a visible light image and an infrared image; determining a first candidate region based on the purple color feature, highlight feature and edge feature of the visible light image; determining a second candidate region based on the edge feature and high gray scale feature of the infrared image; fusing the first candidate region and the second candidate region to obtain a preliminary purple edge region; screening the preliminary purple edge region according to the gray scale feature of the infrared image to eliminate a heat shadow interference region and obtain a target purple edge region; and adaptively reducing the color saturation of pixels in the target purple edge region according to the infrared edge intensity of the target purple edge region and the visible light saturation, and using non-purple edge pixels in the normal direction of the edge of the target purple edge region to perform color repair. The application can accurately distinguish the real purple edge artifact from image noise or other interference, and naturally correct the same, thereby avoiding color distortion.
Need to check novelty before this filing date? Find Prior Art