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

Method for characterizing samples using neural networks

A neural network and sample technology, which is applied in the field of using neural network to represent samples, can solve problems such as not fast enough to manage video streams, and achieve the effect of rapid implementation

Active Publication Date: 2020-09-04
UNIV DE REIMS CHAMPAGNE ARDENNE +1
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this is not fast enough to manage the video stream satisfactorily

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
  • Method for characterizing samples using neural networks
  • Method for characterizing samples using neural networks
  • Method for characterizing samples using neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0111] figure 2 An example of a step of preparing data for input into at least one neural network in the method according to the invention is shown. In this example, the spectral image is taken by a thermal imaging camera, forming a so-called thermal image. The observed parameter based on these images is the temperature of the surface of the sample E.

[0112] In step A, a set of thermal images 2 is acquired from the sample E to be characterized in a predetermined acquisition period T, for example using an infrared thermal imaging camera.

[0113] In step B, a data volume D(Nx, Ny, Ne) corresponding to the instantaneous temperature value is generated from the thermal image 2 in the coordinate system, where Nx and Ny correspond to the along direction (x, y) of the pixel N of the image 2 and Ne corresponds to the acquisition expressed in number of images or in time, or in the case of multispectral imaging or hyperspectral imaging in wavelength.

[0114] In step EP, a set of ...

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 present invention relates to a method for characterizing a sample using a set of spectral images of the sample to be characterized, which have been previously acquired, in particular by infrared thermography or spectral imaging, and to at least one neural network, the method comprising the steps of: generating at least one volume of values of a parameter observed from said spectral images fora plurality of coordinates of the pixels of the images and a plurality of acquisitions, extracting at least one set of input data from said data volume, said input data corresponding to the values ofthe observed parameter for a pixel of the same coordinates according to different acquisitions, wherein at least one transformation function has been applied to said values, training said at least oneneural network using the input data to extract at least one characteristic of the sample to be characterized.

Description

technical field [0001] The present invention relates to methods and devices for characterizing samples based on spectral images, in particular obtained by infrared thermography, and using deep neural networks. Background technique [0002] Most known monitoring systems (especially those used to prevent accidents, route traffic, or make decisions, e.g. for detection and / or for non-destructive testing of components and / or various effects) is based on the use of many sensors and the use of known detection techniques. Infrared, near-infrared (NIR) and ultraviolet (UV) radiation can be used. In particular, far-infrared electromagnetic radiation (also known as radiant heat) emitted continuously by any object with a temperature above absolute zero (-273.15° C.) is used. Specific detectors allow this radiation to be sensed at specific wavelengths and convert these wavelengths into brightness values ​​related to the surface temperature of the object, thereby creating a thermal imag...

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): G01J3/28
CPCG01J3/28G06N3/08G06N20/10G06T7/0004G06T2207/10048G06T2207/10024G06T2207/10036G06T2207/30188G06T2207/20084G01N2021/8887G01N2021/8883G06N3/048G06N3/045G01J3/2823G01J2003/2826
Inventor 瓦雷里·弗拉比厄埃里克·佩兰西赫姆·梅兹加尼
Owner UNIV DE REIMS CHAMPAGNE ARDENNE
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com