Check patentability & draft patents in minutes with Patsnap Eureka AI!

Fabric fiber component qualitative method based on self-attention

A fabric fiber and qualitative method technology, applied in the field of image recognition, can solve the problems of insufficient analysis accuracy, a large amount of manual labor, limited fabric fiber components, etc., and achieve the effect of solving category restrictions and low manual labor

Active Publication Date: 2022-03-01
上海布眼人工智能科技有限公司
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the commonly used analysis methods of fabric fiber composition can be divided into two categories: physical identification method and chemical identification method, such as microscope method and combustion method.

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 fiber component qualitative method based on self-attention
  • Fabric fiber component qualitative method based on self-attention
  • Fabric fiber component qualitative method based on self-attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0035] The qualitative analysis of fabric fiber composition has extensive and profound applications in many fields such as customs sampling inspection, public security organ investigation, and daily use. For example, during the investigation of the public security organ, the fabric woven with fibers and yarns is more likely to transfer when objects come into contact, and often appears as evidence left over from crimes. The fiber type and possible source can be determined through the identification of fibers, providing a basis for investigation. clues to provide a basis for ascertaining the relevant facts of the case.

[0036] At present, the methods for qualitative analys...

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 fiber component qualitative method based on self-attention, which is applied to the technical field of image recognition and is used for solving the problem of analysis of fabric fiber components with similar waveforms in a near-infrared light scanning spectrogram. The method comprises the following steps: acquiring a near-infrared light scanning spectrogram of a fabric, and inputting the near-infrared light scanning spectrogram of the fabric into a pre-trained self-attention neural network model to obtain a preset existence probability of each fabric fiber component; wherein the self-attention neural network model is obtained by performing self-attention training on a pre-acquired training image by using a self-attention neural network; according to the method, the preset fabric fiber components existing in the fabric are determined on the basis of the preset existence probability of each fabric fiber component, and the fabric fiber components are predicted by inputting the trained self-attention neural network model, so that the accuracy of fabric fiber component identification is improved, the efficiency of fabric fiber component identification is improved, and the manual labor is reduced.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a qualitative method for fabric fiber components based on self-attention. Background technique [0002] Fabric fiber composition analysis is one of the most important items in textile testing, one of the main contents of clothing labeling, and an important judgment indicator for anti-fraud. Among them, the fiber content relates to the important properties of the fabric, and plays a decisive role in the physical and chemical properties and wearing performance of the fabric. [0003] Currently commonly used fabric fiber composition analysis methods can be divided into two categories: physical identification method and chemical identification method, such as microscope method and combustion method. [0004] The attention mechanism is a resource allocation mechanism, which is analogous to the human attention mechanism, that is, using limited attention resources to quickly ...

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): G01N21/359G06N3/08
CPCG01N21/359G06N3/08
Inventor 池明旻
Owner 上海布眼人工智能科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com