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

Wool cashmere fiber identification method based on improved Mask R-CNN neural network

A neural network and wool cashmere technology, applied in the field of image recognition, can solve the problems of difficult wool cashmere deep-level feature extraction, SVM classification, low recognition accuracy, and insufficient robustness of image segmentation, so as to improve classification accuracy , Remove interlaced fibers and improve accuracy

Pending Publication Date: 2022-03-04
浙江省轻工业品质量检验研究院 +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are two problems. One is that the wool and cashmere fibers in the image are interlaced in many cases, and the robustness of the image segmentation is not enough; the other is that the morphological characteristics of the wool and cashmere itself are highly similar. Hierarchical features are extracted, which will lead to low classification and recognition accuracy of SVM

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
  • Wool cashmere fiber identification method based on improved Mask R-CNN neural network
  • Wool cashmere fiber identification method based on improved Mask R-CNN neural network
  • Wool cashmere fiber identification method based on improved Mask R-CNN neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention uses deep learning technology to train the model, automatically extracts and learns the characteristics of the target, and continuously trains to update the weight coefficient of the network structure until the gradient is 0 and the value of the loss function reaches the minimum. At this time, the difference between the predicted value and the actual value The difference reaches the minimum, and the accuracy of classification and recognition reaches the highest. There are many kinds of image segmentation networks based on deep learning. Here, the improved Mask R-CNN neural network is used, and the Transformer is used as the backbone backbone network to extract the feature maps of the image, and then the candidate ROI is sent to the RPN region proposal network for labeling. Classification (foreground or background) and bounding box (Bounding box) regression, on the basis of filtering out a part of the candidate ROI, perform ROI Align operation on the...

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 relates to the technical field of image recognition. The invention aims to provide a wool / cashmere fiber identification method based on an improved Mask R-CNN neural network. The method has the characteristics of high identification speed and high identification accuracy. According to the technical scheme, the wool and cashmere fiber identification method based on the improved Mask R-CNN neural network comprises the following steps: 1) collecting a plurality of wool and cashmere fiber images to make a data set, and labeling each fiber in each fiber image in the data set; 2) inputting the data set into an improved Mask R-CNN neural network for training, and obtaining a trained improved Mask R-CNN neural network; and 3) carrying out classification identification on wool and cashmere fibers by using the improved Mask R-CNN neural network.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a wool cashmere fiber recognition method based on an improved Mask R-CNN neural network. Background technique [0002] Wool and cashmere fibers are two important materials in the textile industry, but cashmere has much better performance than wool, and the price is correspondingly much more expensive. Both wool and cashmere are composed of protein. They are highly similar not only in terms of appearance and comfort, but also in terms of physical properties and chemical composition. Some wool fibers are mixed in the production process of clothing products to seek greater profits, which violates the legitimate rights and interests of consumers. The output of wool and cashmere fiber in my country is very large, and the total annual production is still increasing. Therefore, it is very necessary to effectively and accurately identify wool and cashmere fiber. [0003] At p...

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): G06V20/10G06V10/26G06V10/40G06V10/764G06V10/774G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/214G06F18/24G06F18/253
Inventor 卢鸯瞿瑞德李子印孔繁圣从明芳韩高锋
Owner 浙江省轻工业品质量检验研究院
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