Unlock instant, AI-driven research and patent intelligence for your innovation.

Real overexposure image correction method and device based on channel guidance

An image correction and overexposure technology, which is applied in the field of image processing, can solve problems such as difficult to effectively restore texture information, and achieve the effects of ensuring fidelity, improving accuracy, and improving quality

Pending Publication Date: 2022-08-05
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the technical problems that there is no real paired overexposed image correction data set in the current technology, and the existing learning-based algorithms are difficult to effectively restore the texture information of severely overexposed images or regions, and create a channel-based guidance Real overexposure image correction method and device of

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Real overexposure image correction method and device based on channel guidance
  • Real overexposure image correction method and device based on channel guidance
  • Real overexposure image correction method and device based on channel guidance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Hereinafter, the method and apparatus of the present invention will be described by taking an RGB image as an example.

[0038] like figure 1 As shown, a channel-guided real overexposure image correction method includes the following steps:

[0039]Step 101: Collect real paired overexposure correction data sets (which can be implemented by building a real data acquisition device with a digital single-lens reflex camera). The dataset consists of pairs of overexposed images and normal lighting reference images, each with data in both RAW and sRGB formats.

[0040] To capture high-quality RAW and sRGB images simultaneously, use a DSLR camera (or other compliant image capture device) capable of storing RAW format data.

[0041] Specifically, in order to capture each pair of overexposed RAW / sRGB images, a pre-shooting scene is first selected to ensure that there is no interference from environmental or human factors, as well as the richness of the scene and content of the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a real overexposure image correction method and device based on channel guidance, and belongs to the technical field of image processing. According to the method, data characteristics of an overexposure image based on a RAW format are analyzed, and convolution calculation of channel guidance correction is designed according to different brightness and perception intensity of each color channel of the overexposure RAW image R-G-G-B (red-green-green-blue) obtained by a visible light sensor and further data characteristics of inconsistent texture characteristics and information content retention; and a channel-guided convolutional neural network is further constructed, and an overexposure image correction neural network is trained by using the acquired data set, so that channel-guided high-precision overexposure image correction is realized, and the real overexposure image correction quality is improved. According to the invention, the quality of overexposure correction of the real image can be improved, and the fidelity of the real overexposure correction image is ensured.

Description

technical field [0001] The invention relates to a method and a device for correcting real overexposure images based on channel guidance, and belongs to the technical field of image processing. Background technique [0002] Overexposure correction of images is a technical problem with significant implications for both image processing and social media related tasks and industries. [0003] During the imaging process of the camera, the unreasonable exposure level will directly affect the global brightness and texture information of the imaging, which will significantly reduce the image quality, which will significantly affect the visual effect and information content of the image, and greatly reduce the downstream computer vision algorithms (such as object detection, segmentation, etc.) on it. [0004] Although the overexposure problem can be alleviated to a certain extent by adjusting the parameters of digital cameras such as aperture, exposure time or sensitivity, however, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/10004G06T2207/10024G06N3/045G06T5/90
Inventor 付莹洪阳
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More