Color constancy method with adaptive capacity

A color-constant, self-adaptive technology, applied in the field of image processing, which can solve the problems of not taking into account the different sensitivity coefficients of the central area and being unable to automatically adapt to different images.

Active Publication Date: 2014-07-30
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although the Chinese invention patent 200910167730.X also uses the non-classical receptive field model, it does not consider the different sensitivity coefficients of the central area, peripheral area, and sub-area in different scenarios, and cannot automatically adapt to different images with different characteristics

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
  • Color constancy method with adaptive capacity
  • Color constancy method with adaptive capacity
  • Color constancy method with adaptive capacity

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0050] Specific implementation mode 1: Test on the Gehler library

[0051] In the international general color constancy image database Gehler library containing 568 images ( http: / / www.cs.sfu.ca / ~colour / data / shi_gehler / ) to test and evaluate this method. The radius of the central area of ​​the receptive field is set to 1, the radius of the peripheral inhibition area is set to 3, the radius of the sub-area is set to 1, and the P norm is set to 10. The test results are shown in Table 1, which has better results than the classic color constancy algorithm ( The angle error represents the gap between the processed image without color shift and the real image without color shift, the smaller the color, the better the color recovery).

[0052] Table 1. Median angle error of different algorithms for Gehler library images

[0053] Methods

specific Embodiment approach 2

[0054] Specific implementation mode two: test on the SFU library

[0055] In the international common color constancy image database SFU library containing 321 pictures of 31 scenes ( http: / / www.cs.sfu.ca / ~colour / data / colour_constancy_test_images / index.html / ) to test and evaluate this method. The radius of the central area of ​​the receptive field is set to 1, the radius of the peripheral inhibition area is set to 3, the radius of the sub-area is set to 1, and the norm is set to 15. The test results are shown in Table 2 below, which has better results than the classic color constancy algorithm (angle The error represents the difference between the processed image without color shift and the real image without color shift, the smaller the color, the better the color recovery).

[0056] Table 2. Median angle error of different algorithms for SFU library images

[0057] Methods

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 a color constancy method with the adaptive capacity. The method includes the concrete steps that through a non-classic receptive field single antagonism model, different scene images are automatically adapted to by the utilization of the interaction between the inhibiting effect of the periphery and the disinhibition effect of a subregion under different sensitivity coefficients, color images with color bias shot in nonstandard light are restored to color images without color bias in standard light, the colors of the images with color bias can be automatically corrected, and in other words, color constancy is achieved. Tests based on nearly a thousand images on different scenes and under different light conditions of multiple international general color constancy databases prove that the color constancy method with the adaptive capacity has better effect than a classic color constancy algorithm.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to color image color constancy technology, and is a color constancy method based on retinal non-classical receptive field visual mechanism. Background technique [0002] Different from sensors such as cameras, although the color light reflected by the same surface of an object under different lighting conditions is different, the human visual mechanism can obtain the same object surface reflection properties from different incident spectra, so when the external light changes within a certain range When , human beings perceive the color of objects relatively unchanged, and this constancy of color perception within a certain range is called color constancy (Color Constancy). The color of objects collected by sensors such as cameras is determined by the light source, the reflective properties of the object’s surface, and the transmission properties of the sensor itself. A change in ...

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 Applications(China)
IPC IPC(8): H04N9/73G06T5/00G06T7/40
Inventor 张显石李永杰李朝义
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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