Dimension reduction method for reconstructed spectrum of single RGB image

A RGB image and spectrum technology, applied in the field of spectral imaging, can solve problems such as inconsistency in practical applications, over-fitting, and affecting the accuracy of spectral reconstruction of reflectivity of unknown samples

Active Publication Date: 2020-10-20
NANJING FORESTRY UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The dimensionality reduction method in the prior art can easily lead to overfitting, thus affecting the re...

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
  • Dimension reduction method for reconstructed spectrum of single RGB image
  • Dimension reduction method for reconstructed spectrum of single RGB image
  • Dimension reduction method for reconstructed spectrum of single RGB image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] This embodiment provides a dimensionality reduction method for reconstructing a spectrum from a single RGB image, comprising the following steps:

[0040] Step (1), select sample set

[0041] The Munsell color card and Pantone fluorescent nylon color card FFN100 are used to form the sample set, and the reflectance spectrum of each sample in the sample set is measured with the X-Rite Eye-onePro spectrophotometer to obtain the reflectance spectrum library. Of course, the present invention is not limited to the application support of the aforementioned devices and samples, and is also applicable to any device of the same nature that can realize the functions of the aforementioned devices.

[0042] When acquiring data, the measurement conditions are set as follows: 0 / 45 measurement conditions are used, and the measurement error caused by random noise is reduced by averaging three measurements during the measurement; at the same time, in order to remove the noise caused by s...

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 dimension reduction method for a reconstructed spectrum of a single RGB image, and the method comprises the following steps: (1), selecting a sample set, and setting a training set and a test set; (2) setting a regularization parameter set and a hidden layer number set; (3) setting the number m of extracted feature vectors, randomly selecting regularization parameter values and hidden layer values for the training set, and training by utilizing an improved nonlinear principal component analysis method to obtain n groups of models for extracting the feature vectors; (4) selecting a regularization parameter value p and a hidden layer numerical value o according to the minimum average error value; and (5), obtaining a target feature vector. The few-dimensional feature vectors obtained through the method are used for reconstructing the spectrum, ill-conditioned problems of a reconstruction equation can be reduced, and the reconstruction precision and stability areimproved.

Description

technical field [0001] The invention belongs to the technical field of spectral imaging, and in particular relates to a dimensionality reduction method for reconstructing a spectrum from a single RGB image. Background technique [0002] Spectral images composed of reflectance have been widely used in the fields of color and material analysis in cultural heritage protection, disease analysis and judgment in medical science, and geological and landform identification in earth science and remote sensing. At present, the acquisition equipment of spectral images is mainly composed of spectral cameras, broadband filters or narrow-band light sources and ordinary cameras. This kind of spectral imaging equipment is either expensive (such as a spectral camera), or the process is complicated and not easy to carry, so it is not easy to be popularized and used in fields that require low price and easy portability. In order to avoid the aforementioned problems, in the prior art, a digita...

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): G01J3/42G01J3/28G06K9/62G06N3/04G06N3/08
CPCG01J3/42G01J3/2823G06N3/08G01J2003/425G06N3/045G06F18/2135
Inventor 谢德红左楚
Owner NANJING FORESTRY 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