Analysis of curve parameters to characterize multidirectional fabric wrinkling by a double extraction method

Sun, Fengxin; Guo, Mingrui; Hu, Xiaojun; Lei, Wang; Gao, Weidong

doi:10.1177/0040517518805372

Cited by 10 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, there is a series of methods that does not measure the wrinkles on the sample surface, namely indirect measurement. These methods evaluate the fabric wrinkle property by measuring the fabric weave parameters, mechanical properties [49], in-situ characterization [50], and shape retention properties [51] of the fabric sample and mapping to the smoothness appearance degree or wrinkle recovery angle.…”

Section: F Objective Methods For Fabric Wrinkle Evaluationmentioning

confidence: 99%

Fusing Convolutional Neural Network Features With Hand-Crafted Features for Objective Fabric Smoothness Appearance Assessment

et al. 2020

Self Cite

View full text Add to dashboard Cite

In the textile and apparel industry, it remains a challenging task to evaluate the fabric smoothness appearance objectively. In existing studies, with computer vision technology, researchers use the hand-crafted image features and deep convolutional neural network (CNN) based image features to describe the fabric smoothness appearance. This paper presents an image classification framework to evaluate the fabric smoothness appearance degree. The framework contains a feature fusion module to fuse the handcrafted and CNN features to take both advantages of them. The framework uses the multi-scale spatial masking model and a pre-trained CNN to extract hand-crafted and CNN features of fabric images respectively. In addition, a mislabeled sample filtering module is set in the framework, which helps to avoid the negative impact of mislabeled samples in training. In the experiments, the proposed framework achieves 85.2%, 96.1%, and 100% average evaluation accuracies under errors of 0 degree, 0.5 degree, and 1 degree respectively. The experiments on the feature fusion and mislabeled sample filtering verified their effectiveness in improving the evaluation accuracies and the label noise robustness. The proposed method outperforms the state-of-theart methods for fabric smoothness assessment. Promisingly, this paper can provide novel research ideas for image-based fabric smoothness assessment and other similar tasks.

show abstract

Section: F Objective Methods For Fabric Wrinkle Evaluationmentioning

confidence: 99%

Fusing Convolutional Neural Network Features With Hand-Crafted Features for Objective Fabric Smoothness Appearance Assessment

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kendall's coefficient of concordance W , as shown in equation (12), was harnessed to analyze the agreement of the subjective evaluation among the six participants (Sun et al. , 2019).…”

Section: Evaluation Of Fabric Touch Propertiesmentioning

confidence: 99%

Digitization of fabric comfort: a multidimensional evaluation strategy to human perceptions of sensorial, thermal and acoustic comfort in clothing

Chen²,

Sun³

2022

IJCST

Self Cite

View full text Add to dashboard Cite

PurposeCurrent measurement methods for fabric comfort attributes generally suffer from either complicated testing processes and intricate measuring equipment or partial evaluation objectives and thus are difficult for effectively evaluating multidimensional human perceptions towards the comprehensive comfort of fabrics. The purpose of this paper is to develop a facile test device, namely fabric comfort tester, to achieve a comprehensive evaluation of human sensations in terms of sensorial, thermal and acoustic comfort in clothing.Design/methodology/approachThe prototype of the designed device was introduced, which enables a simultaneous test for multiple physical and mechanical properties of fabrics based on a force sensor and a set of infrared sensors via constructing multi-deformation states of the measured fabrics. Eleven measurement indices extracted from the measurement curves are defined and interpreted based on correlation analysis. A series of regression models are developed by relating the measurement indices with subjective evaluation results and validated by a set of independent samples.FindingsHuman perceptions of sensorial, thermal and acoustic comfort in clothing can be predicted by the measured physical indices and the designed test device with the developed regression models provides an alternative method to characterize the fabric comfort attributes effectively.Originality/valueThe work develops a novel device for objective evaluation of fabric comfort properties by a simultaneous test, integrating the mechanical measurement with thermal test and thereby filling the gap between the existing evaluation methods and practical requirements for the digitalization of fabric comfort in present textile and garment trade.

show abstract

“…Among them, Ward's hierarchical clustering 27 is used to classify the samples to determine the number of clusters. Based on the number of clusters determined by hierarchical clustering method, the k-means clustering algorithm 28,29 is used to classify the tactile comfort of fabrics.…”

Section: Theoretical Analysismentioning

confidence: 99%

Tactile comfort characterization of knitted fabrics based on the ring-shaped style tester

Shao

Sun

Zheng

et al. 2020

Textile Research Journal

View full text Add to dashboard Cite

The main content of this paper is to objectively characterize the tactile comfort of fabric through the ring-shaped style tester. It mainly explains the objective tactile comfort of knitted fabric through the curve parameters measured by the ring-shaped style tester and structural parameter thickness. In this paper, by adopting the methods of correlation analysis and cluster analysis, the curve parameters, including slope in the linear segments of the left-hand part of the curve ( K1), the right-hand area of the curve ( A2), the distance between the abrupt point and the peak point ( X), the linearity of the left-hand curve ( L) and the ratio of the left-hand area to the right-hand area of the curve ( C), are used. In order to verify its effectiveness, the results of subjective evaluation are compared and analyzed with the objective clustering. The experimental results show that the subjective judgment has good correlation with the objective clustering. This indicates that the curve parameters obtained through the ring-shaped style tester and structural parameters can be used to effectively represent the tactile comfort performance of fabrics.

show abstract

Analysis of curve parameters to characterize multidirectional fabric wrinkling by a double extraction method

Cited by 10 publications

References 17 publications

Fusing Convolutional Neural Network Features With Hand-Crafted Features for Objective Fabric Smoothness Appearance Assessment

Fusing Convolutional Neural Network Features With Hand-Crafted Features for Objective Fabric Smoothness Appearance Assessment

Digitization of fabric comfort: a multidimensional evaluation strategy to human perceptions of sensorial, thermal and acoustic comfort in clothing

Tactile comfort characterization of knitted fabrics based on the ring-shaped style tester

Contact Info

Product

Resources

About