Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fabric image color calibration algorithm based on spectral reflectivity reconstruction

A technology of spectral reflectance and color calibration, applied in image enhancement, image analysis, image data processing, etc., can solve the problem that the reconstruction accuracy of color training samples cannot be guaranteed, and achieve the purpose of reducing the influence of imaging equipment and lighting environment, improving accuracy, The effect of improving the image quality of fabrics

Inactive Publication Date: 2020-04-21
SHANGHAI UNIV OF ENG SCI
View PDF1 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, these methods select representative color training samples based on the minimum average spectral mean square error as the judgment condition. Although they reduce the redundancy of color samples and also show good spectral accuracy, the study found that when the spectral mean square error is the smallest , the color difference of the reconstructed color may not be the smallest, so there is no guarantee that the representative color training samples selected by these methods can have ideal reconstruction accuracy

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
  • Fabric image color calibration algorithm based on spectral reflectivity reconstruction
  • Fabric image color calibration algorithm based on spectral reflectivity reconstruction
  • Fabric image color calibration algorithm based on spectral reflectivity reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0055] According to one or more embodiments, a disclosed fabric image color calibration algorithm based on spectral reflectance reconstruction, such as figure 1 and figure 2 shown, including the following steps:

[0056] Obtain the color training sample and the image of the fabric to be corrected through camera acquisition, obtain the actual system response of the color training sample and the image of the fabric to be corrected, and obtain the true spectral reflectance of the color training sample through a spectrophotometer;

[0057] Construct a virtual imaging system, define a virtual spectral response function, and calculate the virtual system response of all color training samples and their corresponding spectral reflectance estimates;

[0058] According to the color space conversion formula, the color space conversion is performed on the real spectra...

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 fabric image color calibration algorithm based on spectral reflectance reconstruction, relates to the field of fabric image color correction, and solves the problem that thereconstruction precision is affected by image acquisition color distortion in the existing method. The technical scheme includes: acquiring color training samples through collection; constructing a virtual imaging system, and calculating virtual system responses of all color training samples and corresponding spectral reflectance estimated values; performing color space conversion according to a color space conversion formula; adopting a defined spectrum reconstruction error evaluation function to determine a representative color training sample; obtaining a spectral response function of an actual imaging system according to the determined representative color training sample; and obtaining a corresponding reconstructed spectral reflectance through a Wiener estimation method, and obtaininga reconstructed RGB image through color space conversion. According to the fabric image color calibration algorithm based on spectral reflectance reconstruction, the quality of the fabric image is improved, and real yarn color information of the fabric image is obtained.

Description

technical field [0001] The invention relates to fabric image color correction technology, in particular to a fabric image color calibration algorithm based on spectral reflectance reconstruction. Background technique [0002] In the process of fabric production and analysis, digital image analysis technology is used to extract features and design patterns of fabric images, all of which are based on the color data of fabric images. However, because machine vision lacks adaptability and intelligence, and does not have the characteristics of color constancy, changes in image acquisition, transmission, and display systems will cause changes in image color data, directly affecting the accuracy of analysis results. Therefore, it is particularly important to make necessary corrections to the color data of fabric images. [0003] The research shows that the correction method of spectral reflectance reconstruction can effectively reduce the influence of light source and environment ...

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): G06T5/00G06T7/90G06F17/16G01N21/31
CPCG06T7/90G06F17/16G01N21/31G06T5/00
Inventor 辛斌杰王文珍邓娜王益亮陆帅钢刘露露贺炎
Owner SHANGHAI UNIV OF ENG SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products