Fabric defect detection systems and methods—A systematic literature review

Hanbay, Kazım; Talu, Muhammed Fatih; Özgüven, Ömer Faruk

doi:10.1016/j.ijleo.2016.09.110

Cited by 210 publications

(121 citation statements)

References 57 publications

Supporting

Mentioning

101

Contrasting

Unclassified

Order By: Relevance

“…The aim of this section was to give a general overview of the most commonly used methodologies in the detection of Most authors divide these methods into three groups [1]: statistical, spectral, and model based, but in recent years, the learning approach has become important [4]. In this paper, fabric defect detection methods are categorized into four classes as shown in Figure 1.…”

Section: Detection Methodsmentioning

confidence: 99%

“…In many papers, the images used are private and little information is provided about resolution or other capture properties. This makes it impossible to verify the results and present new methods, which improve results, as it is not possible to make a comparison of results using the same information [4,5]. Another clear drawback in the papers covered in Table 2 is that the set of images is too small to generate acceptable results that have a general application.…”

Section: Related Work and Textile Databasesmentioning

confidence: 99%

“…In addition, as mentioned in Refs. [4] and [5], due to the huge number of fabric defect detection algorithms and techniques, an effective comparison between fabric defect detection methods would be extremely significant, but most studies use different databases, different imaging systems, and different parameters. This means that the lack of a suitable public annotated benchmark makes it difficult for researchers to evaluate, in a quantitative way, the advantages of their algorithms over existing ones, and as such this lack represents a serious limitation on the development of effective and implementable algorithms in some fields, for example, in road lane detection [6], and which also happens in the textile industry.…”

Section: Introductionmentioning

confidence: 99%

“…For this reason, it is important to have a public database that can be used by different authors for their studies and comparisons, since in many cases, as mentioned in Ref. [4], in the majority of the studies "the authors create their own databases by obtaining the images from factory environments or by bringing them to the laboratory and the database is created with proper lighting settings. Therefore, the reliability and validity of the methods is far from objectivity.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Public Fabric Database for Defect Detection Methods and Results

Silvestre-Blanes

Albero-Albero

Miralles

et al. 2019

Autex Research Journal

102

View full text Add to dashboard Cite

The use of image processing for the detection and classification of defects has been a reality for some time in science and industry. New methods are continually being presented to improve every aspect of this process. However, these new approaches are applied to a small, private collection of images, which makes a real comparative study of these methods very difficult. The objective of this paper was to compile a public annotated benchmark, that is, an extensive set of images with and without defects, and make these public, to enable the direct comparison of detection and classification methods. Moreover, different methods are reviewed and one of these is applied to the set of images; the results of which are also presented in this paper.

show abstract

Section: Detection Methodsmentioning

confidence: 99%

Section: Related Work and Textile Databasesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Public Fabric Database for Defect Detection Methods and Results

Silvestre-Blanes

Albero-Albero

Miralles

et al. 2019

Autex Research Journal

102

View full text Add to dashboard Cite

show abstract

“…Automated fabric inspection is the process of detecting, analyzing, and classifying abnormal structure in the fabric surface using machine vision techniques. To be more specific, an automated fabric inspection system should have the following capabilities: (1) be able to determine if an input fabric image is defective or not, (2) be able to locate the defective regions if the input fabric image is defective, and (3) be able to identify the type of the faults for the defective regions.…”

mentioning

confidence: 99%

Fabric defect detection based on saliency histogram features

Wan

Deng

et al. 2019

Computational Intelligence

View full text Add to dashboard Cite

In order to increase the automatic quality control level in the textile industry, depending on the big data collected by the Internet of things of the textile factories, this paper proposes a novel visual saliency–based defect detection algorithm, which has the capability of automatically detecting defect in both nonpatterned and patterned fabrics. The algorithm employs the histogram features extracted from the saliency maps to detect the fabric defects. The algorithm involves three main steps: (1) saliency map generation to highlight the defective regions and suppress the defect‐free regions, (2) saliency histogram features extraction and selection to obtain the feature vectors that can effectively discriminate between the defective and defect‐free fabric images, and (3) fabric defect detection using a two‐class support vector machine classifier that has been trained using sets of feature vectors extracted from defective and defect‐free fabric samples. Experimental results show that our method yields accurate detections, outperforming other state‐of‐the‐art algorithms.

show abstract

CNN‐based defect detection in manufacturing

Hou,

Li,

Cheng

et al. 2024

Adv Control Appl

View full text Add to dashboard Cite

This research introduces an advanced algorithm based on convolutional neural networks for the detection and categorization of surface defects in manufacturing processes. At its core, the algorithm employs a deep learning model that integrates residual networks and attention mechanisms to effectively extract features. Additionally, we have developed a novel feature selection method, named NR, which synergistically combines neighborhood component analysis and ReliefF techniques. This approach enables the selection of more representative deep features for subsequent analysis. For the classification task, we utilize the support vector machine technique, which demonstrates versatility in handling both binary and multi‐class classification scenarios. The reliability and superiority of our algorithm are further validated through a comparative analysis using a dataset specifically tailored for this context. The results indicate that our approach outperforms existing algorithms in accurately identifying manufacturing defects.

show abstract

Fabric defect detection systems and methods—A systematic literature review

Cited by 210 publications

References 57 publications

A Public Fabric Database for Defect Detection Methods and Results

A Public Fabric Database for Defect Detection Methods and Results

Fabric defect detection based on saliency histogram features

CNN‐based defect detection in manufacturing

Contact Info

Product

Resources

About