A Spectral Sparse Reconstruction Method Based on Camera Response Values
A camera response, sparse reconstruction technology, applied in the field of spectral reconstruction, can solve the problem of low spectral reconstruction accuracy, and achieve the effect of high spectral reconstruction accuracy and simple calculation
Active Publication Date: 2022-06-03
山东济清科技服务有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, when the existing compressive sensing method uses the principal component analysis method to calculate the sparse basis, it only considers the spectral set of the training sample and ignores the chromaticity characteristics of the test sample itself, resulting in low spectral 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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0059] FIG. 1 is a flow chart of a spectral sparse reconstruction method based on a camera response value of the present invention.
[0063] y=∫
[0073]
[0084]
[0086]
[0088]
[0089] In the formula, ε is a very small constant (eg, ε=0.01) to avoid infinite computational problems. Obviously, the training samples and the test
[0090]
[0094]
[0097]
[0100]
[0101] In the formula, ξ is the correction coefficient.
[0105] (c) is compared with the spectral reflectance of the printed manuscript, and the root mean square error value between the two is calculated. calculation method
[0106]
[0107] In the formula, r is the spectral reflectance of the printed manuscript, and is the spectral reflectance of the detected printed matter, and n is the wavelength dimension.
[0112] The above-mentioned embodiments are preferred cases of the present invention, and are not intended to limit the protection scope of the present invention.
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
Login to View More Abstract
The present invention provides a spectral sparse reconstruction method based on camera response value, which is characterized in that it includes the following steps: firstly obtain the camera response value corresponding to the color of the object through measurement and calculation in a digital imaging device; then fully consider the training sample spectrum Based on the chromaticity characteristics of the set and test samples, the optimized sparse basis is calculated, and finally the spectral reflectance of the object is reconstructed using the orthogonal matching pursuit algorithm. Therefore, under the premise of considering the influence of the chromaticity characteristics of the training sample spectrum set and the test sample, the spectral reflectance is reconstructed by optimizing the sparse basis, which is simple to calculate, high in spectral reconstruction accuracy, and relatively convenient for users to use.
Description
A Spectral Sparse Reconstruction Method Based on Camera Response Values technical field The present invention relates to a kind of spectral reconstruction method, be specifically related to a kind of spectral sparse reconstruction based on camera response value The method can be widely used in the fields of textile color, printing inspection, artwork reproduction and e-commerce. Background technique The color information based on the spectral reflectance of the object surface is called the color "fingerprint", which is reflected by the measured object. The ratio between the luminous flux and the incident luminous flux is an inherent property of the object and is not affected by external factors. with regular The three-channel camera has different response values, and multispectral images can accurately express the color characteristics of objects in any observation environment. It has been widely used in the fields of textile color, printing inspection, artwork repr...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T11/00G01N21/55G01N21/25
CPCG06T11/001G06T11/006G01N21/55G01N21/25
Inventor 吴光远熊义凡刘敬臧传扬李效周
Owner 山东济清科技服务有限公司