An investigation of woven fabric density measurement using image analysis based on RTV-SFT
Authors:
- 2 September 2022
- journal article
- research article
- Published by Taylor & Francis in The Journal of the Textile Institute
- Vol. 114 (9) , 1291-1300
Abstract
To overcome the shortcomings of time-consuming manual measurement methods of fabric density, a novel density measurement method of woven fabrics using image analysis technology via the relative total variation model based on the view of structure extraction from texture (RTV-SFT) is developed. Firstly, a fabric image acquisition system of multi-zoom portable digital microscope is constructed to obtain color dyed fabric images. Secondly, creatively from the perspective of analyzing periodic structure information of image texture information, a new structure extraction from texture algorithm, namely RTV-SFT is proposed to process fabric images to obtain images without non-periodic texture information aiming to achieve accurate yarn segmentation. Finally, the woven fabric density is calculated by effectively adopting the gray level projection method with the improved Gaussian filter algorithm. In the experiment, compared with manual method, the accuracy of the proposed density measurement method is above 93.3%.Keywords
Funding Information
- National Natural Science Foundation of China
- Shanghai Local Capacity-Building Project
This publication has 16 references indexed in Scilit:
- A novel image processing technology for recognizing the weave of fabricsTextile Research Journal, 2015
- Automatic inspection of density in yarn-dyed fabrics by utilizing fabric light transmittance and Fourier analysisApplied Optics, 2015
- Automatic inspection of yarn-dyed fabric density by mathematical statistics of sub-imagesThe Journal of the Textile Institute, 2014
- Image-Based Reverse Engineering and Visual Prototyping of Woven ClothIEEE Transactions on Visualization and Computer Graphics, 2014
- A new method for the detection and classification of weave pattern repeatTextile Research Journal, 2014
- Recognition of fabric density with quadratic local extremumInternational Journal of Clothing Science and Technology, 2012
- Investigation on the Classification of Weave Pattern Based on an Active Grid ModelTextile Research Journal, 2009
- A novel method for the identification of weave repeat through image processingThe Journal of the Textile Institute, 2009
- Woven Fabric Analysis by Image ProcessingTextile Research Journal, 2000
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992