An Adaptive Color Constancy Method Based on Image Local Contrast

A technology of local contrast and color constancy, which is applied in the field of adaptive color constancy based on local contrast of images, and can solve the problems of inappropriate real-time processing and poor flexibility.

Inactive Publication Date: 2020-07-07
SICHUAN UNIV
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] So far, no algorithm is suitable for almost all data sets, the flexibility is relatively poor, and it is not suitable for real-time processing

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
  • An Adaptive Color Constancy Method Based on Image Local Contrast
  • An Adaptive Color Constancy Method Based on Image Local Contrast
  • An Adaptive Color Constancy Method Based on Image Local Contrast

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to facilitate those skilled in the art to understand the technical content of the present invention, the content of the present invention will be further explained below in conjunction with the accompanying drawings.

[0029] Such as figure 1 Shown is the solution flow chart of the present invention, the technical solution adopted by the present invention is: an adaptive color constant method based on local image contrast, comprising:

[0030] S1. Obtain the local contrast of the image by calculating the local standard deviation of each pixel;

[0031] S2. Divide the original image into three color channels of R, G, and B. Each color channel selects the size of the Gaussian kernel according to the local contrast calculated in step S1, and performs convolution to obtain the response CR of the central receptive field of the neuron in the V1 area. ;

[0032] S3. Divide the original image into three color channels of R, G, and B, and convolve each color channel w...

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 discloses an adaptive color constancy method based on image local contrast. Aiming at the problems that the conventional color constancy algorithm cannot be applicable to all data and ispoor in flexibility, a brain's visual adaptive information processing mechanism is simulated by adaptively adjusting a kernel function size of a difference of Gaussian (DoG) function and a suppressive weight of a central-peripheral receptive field by virtue of image local contrast, and a high-level visual cortex V4 region integrates input signals from a low-level visual cortex V1 region by virtueof an adaptive sparse coding manner, so that the light source color of the scene is estimated. The same parameter is set on different data sets, and excellent effects can be achieved; the method is very efficient, the position and color of the light source can be well estimated, and the image is subjected to real-time color correction.

Description

technical field [0001] The invention belongs to the related technical fields of computer vision, image processing, artificial intelligence, signal processing and cognitive science, and particularly relates to a technology for estimating the color of a light source of a scene from a color image and realizing image color correction. Background technique [0002] Visual computing is a very broad field. Color constancy emphasizes the constancy of our visual system to the color perception of external objects. It refers to extracting the most stable visual color information from sensory information to obtain the most essential understanding of external objects. The ability of the human visual system to automatically remove the color cast of the scene caused by the color change of the light source in the scene is called color constancy. [0003] Color constancy can be analyzed from different perspectives, such as computer vision, optics, psychology, etc. We regard the color consta...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/90G06T5/00G06T5/40G06N3/06
CPCG06N3/061G06T5/001G06T5/40G06T7/90
Inventor 高绍兵南颖肖杨琚锡平钱含笑
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap