Fabric defect detection using local contrast deviations

Shi, Meihong; Fu, Rong; Guo, Yong; Bai, Shixian; Xu, Bugao

doi:10.1007/s11042-010-0472-8

Cited by 24 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, if a model‐based algorithm is introduced into colour‐patterned fabric defect detection, a specific model will be established for each texture, and the cost of each model is prohibitive. Finally, structural methods 13 describe texture primitives and rules governing special fabric organisation of texture primitives that require strong regularity of the fabric texture 14 . Therefore, these structural methods are also challenging for colour‐patterned fabric defect detection.…”

Section: Introductionmentioning

confidence: 99%

Colour‐patterned fabric defect detection based on an unsupervised multi‐scale U‐shaped denoising convolutional autoencoder model

Zhang

Liu

Tan

et al. 2022

Coloration Technology

View full text Add to dashboard Cite

This study proposes an unsupervised, learning‐based, reconstructed scheme and a residual analysis‐based defect detection model for colour‐patterned fabric defect detection problems in the clothing process industry. It solves the challenging problems of existing supervised fabric defect detection methods, such as high costs in manually labelling samples and designing features, unstable generalisation ability and scarcity of defective samples. First, for a specific texture, the training set was constructed by collecting easily accessible defect‐free colour‐patterned fabric images. Second, a multi‐scale U‐shaped denoising convolutional autoencoder was modelled using defect‐free samples, which can reconstruct the newly tested colour‐patterned fabric images automatically. Subsequently, a residual map between the original image and corresponding reconstructed image was calculated. Finally, the defective areas were detected and accurately localised by further opening operations. The experimental results indicated that the proposed method is valid and robust for detecting defects in various colour‐patterned fabrics. Moreover, with the YDFID‐1 dataset, compared with other models, the intersection over union index of the model proposed in the current paper was improved by at least 3.95%.

show abstract

Section: Introductionmentioning

confidence: 99%

Colour‐patterned fabric defect detection based on an unsupervised multi‐scale U‐shaped denoising convolutional autoencoder model

Zhang

Liu

Tan

et al. 2022

Coloration Technology

View full text Add to dashboard Cite

show abstract

“…Funck et al [10] used clustering and region-growing techniques to detect defects on wood images. Various defect detection applications of thresholding technologies are discussed in literatures [11][12][13]. Most of thresholding methods provide expected results for the particular application, but there is not a general method available for defect detection.…”

Section: Introductionmentioning

confidence: 99%

An improved Otsu method using the weighted object variance for defect detection

Yuan

Peng

2015

Applied Surface Science

188

View full text Add to dashboard Cite

a b s t r a c tProstaglandin F2a (PGF) treatment is routinely used in the reproductive management of mares to induce luteolysis and allow a subsequent return to estrus. The objective of this retrospective study was to assess the effect of follicle size at the time of administration of cloprostenol on interval to subsequent ovulation. A secondary objective was to determine the incidence of hemorrhagic anovulatory follicle (HAF) formation after PGF administration. Reproductive records of 275 mares monitored over a total of 520 estrous cycles were evaluated. All mares received a single intramuscular dose of 250 mg of the synthetic PGF analog cloprostenol sodium between days 5 and 12 after ovulation. The average interval from PGF to ovulation was 8.4 AE 2.5 days. The interval from PGF administration to subsequent ovulation was inversely proportional to the diameter of the largest follicle at the time of treatment. Administration of cloprostenol to mares with a large (!35 mm in diameter) diestrous follicle resulted in one of three outcomesdovulation within 48 hours (13.4%) with variable uterine edema, ovulation after 48 hours usually accompanied by the presence of uterine edema (73.1%), or regression without ovulation followed by emergence and eventual ovulation of a new dominant follicle (13.4%). There was no effect of mare age or season on interval from PGF to ovulation. The overall incidence of HAF development after PGF administration in this study was low (2.5%).

show abstract

“…In statistical approach [2][3][4], spatial distribution of gray values is defined by various representations, such as auto-correlation function, co-occurrence matrices, and fractal dimension. And this method employs the statistics of background (defect-free regions) are stationary, can effectively localize the defect region with distinct statistical behavior.…”

Section: Introductionmentioning

confidence: 99%

Fabric defect detection via learned dictionary-based visual saliency

Yang

Liu

et al. 2016

International Journal of Clothing Science and Technology

View full text Add to dashboard Cite

If you would like to write for this, or any other Emerald publication, then please use our Emerald for Authors service information about how to choose which publication to write for and submission guidelines are available for all. Please visit www.emeraldinsight.com/authors for more information. About Emerald www.emeraldinsight.comEmerald is a global publisher linking research and practice to the benefit of society. The company manages a portfolio of more than 290 journals and over 2,350 books and book series volumes, as well as providing an extensive range of online products and additional customer resources and services.Emerald is both COUNTER 4 and TRANSFER compliant. The organization is a partner of the Committee on Publication Ethics (COPE) and also works with Portico and the LOCKSS initiative for digital archive preservation.

show abstract

Fabric defect detection using local contrast deviations

Cited by 24 publications

References 11 publications

Colour‐patterned fabric defect detection based on an unsupervised multi‐scale U‐shaped denoising convolutional autoencoder model

Colour‐patterned fabric defect detection based on an unsupervised multi‐scale U‐shaped denoising convolutional autoencoder model

An improved Otsu method using the weighted object variance for defect detection

Fabric defect detection via learned dictionary-based visual saliency

Contact Info

Product

Resources

About