Low-light image enhancement method and device based on multi-scale filter

By converting low-light images from RGB to HSV color space, and using guided filters and the Retinex algorithm for multi-scale filtering and brightness correction, the problem of unsatisfactory low-light image enhancement effect is solved, and a significant improvement in image quality is achieved.

CN115330608BActive Publication Date: 2026-05-29SUZHOU VOCATIONAL UNIVERSITY (SUZHOU OPEN UNIVERSITY)
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SUZHOU VOCATIONAL UNIVERSITY (SUZHOU OPEN UNIVERSITY)
Filing Date
2022-07-12
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies do not provide ideal image enhancement results under low-light conditions, leading to increased image noise and decreased quality, which affects the accuracy and efficiency of image recognition.

Method used

A multi-scale filter-based approach is adopted. The original image is converted from the RGB color space to the HSV color space, the illumination image is estimated, and a guided filter is used for multi-scale filtering. Combined with the Retinex algorithm and gamma brightness correction, the brightness and saturation are enhanced, and finally the image is restored to the RGB color space.

Benefits of technology

It effectively improves the enhancement effect of low-light images, enhances image quality and recognition accuracy, reduces noise, and enhances image clarity and contrast.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115330608B_ABST
    Figure CN115330608B_ABST
Patent Text Reader

Abstract

The embodiment of the present application discloses a low-illumination image enhancement method and device based on a multi-scale filter. The method comprises the following steps: acquiring a low-illumination original image; converting the original image from an RGB color space to an HSV color space; estimating an illumination image of the original image according to a luminance component of the original image in the HSV color space; performing multi-scale filtering on the illumination image based on a guided filter to obtain a filtered illumination image; and processing the filtered illumination image to obtain an enhanced image. Based on the method and device, the enhancement effect on the low-illumination image can be improved, and the image quality of the low-illumination image can be effectively enhanced.
Need to check novelty before this filing date? Find Prior Art