Garment smoothness appearance evaluation through computer vision

Silvestre-Blanes, Javier; Berenguer-Sebastiá, Joaquin; Pérez-Lloréns, Rubén; Miralles, Ignacio; Moreno, J.

doi:10.1177/0040517511424530

Cited by 14 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then the smoothness appearance of the samples is also evaluated by image analysis algorithms. In another study [46], the proposed method can evaluate the smoothness appearance for real garment. In addition, imagebased wrinkle recovery angle are also used to evaluate the wrinkle properties of fabrics [47,48].…”

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

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

View full text Add to dashboard Cite

show abstract

“…For the quantitative evaluation method for garment appearance, textile image analysis method is broadly used to evaluate wrinkle on the fabric surface [8] and fit properties of garments [9] and so on. However, there are no researches about the adhesive interlining effects on garments appearances with image analysis.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Assessment of Jackets Appearances with Bonding Adhesive Interlinings using Two-dimensional and Three-dimensional Analysis

Kim

Sonehara

Takatera

2013

IJAE

View full text Add to dashboard Cite

Abstract:The quantitative assessment methods for appearance differences of jackets caused by bonding different adhesive interlinings to face fabric were investigated. A sensory test was carried out to evaluate jacket appearance differences depending on different adhesive interlinings. The quantitative assessment methods of jacket appearances were investigated using 2D and 3D image analysis. The outlines of cross point location for both lapel and bottom in the front view were obtained from the 2D images. The horizontal and vertical cross-sections of bottom part for each jacket were obtained from the 3D images. The compared results with the obtained 2D and 3D images showed a possibility to evaluate jacket appearance changes by bonding adhesive interlining. The variances of the curvature of the vertical cross-section were also obtained. The variances were compared with sensory test results and those showed high correlation each other. Therefore, it was able to evaluate the jacket appearance quantitatively using variance of the curvature from cross-sections of 3D images.

show abstract

“…In addition, many advanced algorithms and image processing technologies are being used in the evaluation of fabric smoothness appearance. [18][19][20] However, the image technology can be only a helpful method to enhance the repeatability and efficiency of result analysis, but the primary evaluation methods are still from the American Association of Textile Chemists and Colorists (AATCC) smoothness appearance standard by using the visual test principle, and the time-consuming laundering or creasing courses prior to smoothness evaluation and the effects of fabric textures on evaluation results are inevitable.…”

mentioning

confidence: 99%

In situ characterization of the morphological wrinkling of woven fibrous materials by a mechanical test

Sun

Wang

et al. 2020

Textile Research Journal

View full text Add to dashboard Cite

Wrinkling is one of the most common flaws of woven fabrics in domestic use and industrial applications. It is necessary to develop an objective evaluation method to quantify the smoothness appearance of fabrics effectively. Herein, a fabric multi-deformation tester (FMDT) was designed to evaluate the smoothness appearance of garment fabrics by one sequential mechanical test, overcoming the main difficulties of the existing visual measurement methods for wrinkling evaluation of fabrics with complex colors and patterns. The k-means clustering algorithm was used to objectively cluster the fabric samples based on the characteristic parameters, including the wrinkle-induced residual force ( F wr), hysteresis distance ( H fr), position deflection ( D fr) and stretching recovery slope ( S tr), from the testing curve and the thickness and weight of fabrics, and comparisons with subjective evaluation were also conducted. The results reveal that the k-means clustering is able to classify the smoothness appearance of fabrics using the selected characteristic parameters, showing a good consistency with the subjective clustering results. The feasibility of using the mechanical and deformation properties of textiles to characterize fabric smoothness appearance is proved, and the FMDT provides a potential method to analyze the wrinkling of fibrous materials in a convenient way.

show abstract

Garment smoothness appearance evaluation through computer vision

Cited by 14 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

Quantitative Assessment of Jackets Appearances with Bonding Adhesive Interlinings using Two-dimensional and Three-dimensional Analysis

In situ characterization of the morphological wrinkling of woven fibrous materials by a mechanical test

Contact Info

Product

Resources

About