Influence of the wrinkle perception with distance in the objective evaluation of fabric smoothness

Abril, Hector C.; Millán, Marı́a S.; Valencia, Edison

doi:10.1088/1464-4258/10/10/104030

Cited by 22 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the different data acquisition technologies used, the computer-vision-based methods proposed in the existing research can be divided into two categories, namely 2D methods and 3D methods. The 2D methods [5][6][7][8][9][10][11][12] usually use an industrial camera or a scanner to collect the fabric surface data, whose data format is a gray-level 2D digital image. The 2D image expresses the fabric smoothness information as the shadow caused by wrinkles on the sample surface, which is an indirect expression progress with a high environmental dependence.…”

Section: A Image Acquisitionmentioning

confidence: 99%

“…In terms of fabric appearance data acquisition, the existing methods can be divided into two categories, namely 2D methods and 3D methods. The 2D methods [5][6][7][8][9][10][11][12] use an industrial camera or a scanner to collect the fabric images within shadow caused by wrinkles on the fabric surface. 3D methods utilize techniques as laser triangulation [13][14][15][16][17], photometric stereo vision [18,19] and binocular stereo-vision [20][21][22][23] to reconstruct the fabric surface.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2020

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: A Image Acquisitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Non-contact methods such as holography, speckle [1,2], Moiré interferometry [3], and digital image analysis [4][5][6][7][8][9][10][11][12][13][14][15] are proposed for the evaluation of strain dis-Corresponding author, jovita.dargiene@stud.ktu.lt tribution. With different techniques and equipments it is possible to record real-time strain distribution fields.…”

Section: Introductionmentioning

confidence: 99%

Image-based method for the investigation of low flexure rigidity materials

Dargienė¹,

Lukšaitė²,

Domskienė³

2012

Proc. Estonian Acad. Sci.

View full text Add to dashboard Cite

The image analysis method is used for the evaluation of the mechanical behaviour of bias stretched woven material and determination of the zones and values of local deformations of the specimen. To demonstrate the capabilities and reliability of the proposed image analysis method, the simplest and most commonly used uniaxial tensile test was chosen. Using the acquired images, local deformations of the specimen in transverse and longitudinal directions were estimated and regularities of the variation of uniform defonnation zones were assessed.Comparison of the behaviour of materials shows that increase in bending rigidity changes the deformation character of materials. For non-laminated low flexure rigidity materials the formation of localized defonnation zones was estimated at primary stages of deformation, as in the case of stiffer laminated fabric the zones of uniform deformations spread more and do not concentrate within the centre of the specimen. The different nature and shape of local deformation zones indicate that the behaviour of laminated materials is closer to that of isotopic materials.The obtained results show that image analysis can describe the response of low flexure rigidity material to external forces. This method supplements the investigation process of woven materials, increases the accuracy of measurements, and determines the real-time local strains.

show abstract

“…5 Abril et al proposed a method in which two images of the sample were obtained under orthogonal lateral illumination and a joint Canny edge detector was applied to integrate the wrinkling information of both images. 6 In 2009, Yu and Yao presented a stereo vision system for reconstructing the 3D surface of a wrinkled fabric for detecting and characterizing wrinkles and evaluating the severity of wrinkling. 7 In 2010, Zaouali et al put forward an objective method enabling evaluation of multidirectional wrinkling of any colored fabric developed using digital image analysis.…”

mentioning

confidence: 99%

Novel testing equipment for fabric wrinkle resistance simulating actual wear

Liu

2014

Textile Research Journal

View full text Add to dashboard Cite

Wrinkling is one of the most important factors that determine the visual aesthetic of our clothes. To investigate wrinkling characteristics in actual wear and explore the relationship between the wrinkling caused by wearing and testing results of the wrinkle recovery angle (WRA) method, we made a device that can produce wrinkles very similar to those on clothes. Twenty-four fabrics were wrinkled by the device, and the images of wrinkled fabrics were analyzed. Wrinkle density (WD) was defined for wrinkling characterization. In addition, fractal dimension (FD) and gray level co-occurrence matrix (GLCM) variables were also used to describe wrinkling. These features were subsequently correlation analyzed with wrinkle recovery angles in 11 directions. The results show that both FD and WD can be used to characterize the wrinkling behavior and wrinkles generated by the device have obvious fractal characteristics. The larger the wrinkle recovery angle, the lower the fractal dimension. GLCM variables (energy, entropy, contrast, and correlation) had not shown obvious correlation with WRA. Furthermore, the wrinkling behavior in the 45 direction plays an important role in actual wear. It is advised that the WRA in the 45 direction be tested.Keywords fabric wrinkling, wrinkling analysis, wrinkle recovery angle, gray-level co-occurrence matrix, fractal dimension, actual wear Wrinkling, caused by washing, drying, or wearing, is one of the most important characteristics in determining the visual aesthetic of clothes. The annoying wrinkles can not only decrease the quality of clothes but also affect the mood of the wearer. Therefore, it is of vital importance to precisely and objectively measure and evaluate the wrinkle resistance of fabrics. Conventionally, the American Association of Textile Chemists and Colorists (AATCC) TM 66-2008 and AATCC TM 128 2009 are the most commonly used testing methods. In the former method, wrinkles are caused by folding and compressing the fabric and the wrinkle recovery angle (WRA) of warp and weft directions is used to characterize the wrinkling behavior of the fabric. In the latter method, wrinkles are caused by rotating and compressing the fabric, and visual examination is used to evaluate the degree of wrinkling, during which wrinkle grades are acquired via experts by comparing the wrinkled fabrics with the standard replicas.There are deficiencies in subjective evaluation such as inconsistency of the results, difficulty in discriminating between the adjacent grades, and low efficiency. As a result, many experts have devoted themselves to more objective and reliable evaluation methods. In 1995, Youngjoo and Behnam analyzed the wrinkling degree of AATCC replica standards using a combination of texture and profile analysis techniques. 1 In 1999, Su and Xu used the laser line triangulation method to measure the three-dimensional (3D) surface data of a wrinkled fabric and built a neural network to perform wrinkle classification with regard to the visual standard. 2 In 2001, TJ Kang et al. measured ...

show abstract

Influence of the wrinkle perception with distance in the objective evaluation of fabric smoothness

Cited by 22 publications

References 28 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

Image-based method for the investigation of low flexure rigidity materials

Novel testing equipment for fabric wrinkle resistance simulating actual wear

Contact Info

Product

Resources

About