Fabrics defects detecting using image processing and neural networks

Jmali, Mohamed; Zitouni, B.; Sakli, Faouzi

doi:10.1109/ictia.2014.7883765

Cited by 9 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is seen that the artificial neural network (ANN) is used in many studies. Kuo and Lee, 4 Huang and Chen, 5 Kumar, 6 Behera and Mani, 7 Bu¨yu¨kkabasakal, 8 C¸elik et al, 9 Jmali et al, 10 and Rebhi et al 11 propose ANN-based studies. Kuo and Lee 4 employ a feedback neural network with three defect characteristics retrieved (maximum length, maximum breadth, and defect gray level).…”

Section: Related Workmentioning

confidence: 99%

The effects of fusion-based feature extraction for fabric defect classification

Çıklaçandır

Utku

Özdemi̇r

2023

Textile Research Journal

View full text Add to dashboard Cite

Image processing has been employed in a variety of fields since the advent of image processing techniques. One of these fields is textiles. The existence of any defect in a fabric is one of the most important factors affecting the quality of the fabric. There are many types of fabric defects that can occur for various reasons. It is critical to figure out what caused the defect and fix it so that it does not occur again. Automation of fabric defect detection has recently attracted a great deal of interest in view of the development in artificial intelligence technology to be able to discover defects with a high degree of success and to limit the harm to the manufacturer. This study focuses on analyzing different feature extraction methods and different classifiers and discussing the advantages/disadvantages of the combinations and, unlike other studies, using feature fusion for feature extraction. Different cases have been created that handle fabric datasets from different angles and apply different methods of feature extraction (convolution neural network, minimum relevance and maximum redundancy) and classification (ensemble learning (EL), k-nearest neighbor, support vector machine (SVM)) for separating defected and un-defected patterned and un-patterned fabrics. ResNet18 is the convolution neural network-based model with the highest performance in feature extraction, while EL and the SVM allow us to achieve close and highly successful results in classification. When feature fusion is used, ResNet18 & GoogLeNet & SVM is the most successful combination compared to the others (94.66%).

show abstract

Section: Related Workmentioning

confidence: 99%

The effects of fusion-based feature extraction for fabric defect classification

Çıklaçandır

Utku

Özdemi̇r

2023

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…In paper [4], it was proposed to provide a diagnostic procedure for detecting and classifying defects in warp and weft using a computer program developed by MATLAB that analyzed images of fabric samples obtained using a flat scanner. Three were determined to detect defects.…”

Section: Literature Surveymentioning

confidence: 99%

“…For the current implementation of this paper, the camera and system with the following specification are used to capture and test the textile material. Table [4] specifies system specification.…”

Section: System Specificationmentioning

confidence: 99%

Fabric Defect Detection Using YOLOv2 and YOLO v3 Tiny

Sujee

Shanthosh

Sudharsun

2020

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

The paper aims to classify the defects in a fabric material using deep learning and neural network methodologies. For this paper, 6 classes of defects are considered, namely, Rust, Grease, Hole, Slough, Oil Stain, and, Broken Filament. This paper has implemented both the YOLOv2 model and the YOLOv3 Tiny model separately using the same fabric data set which was collected for this research, which consists of six types of defects, and uses the convolutional weights which were pretrained on Imagenet dataset. Observed and documented the success rate of both the model in detecting the defects in the fabric material.

show abstract

“…Öğrenme tabanlı çalışmalarda denetimli (supervised) makine öğrenmesi tekniklerinden yapay sinir ağları [24][25][26] ve destek vektör makineleri [27] en çok karşılaşılan metotlardandır. Denetimli makine öğrenmesi tekniklerinde eldeki veri eğitim ve test için olmak üzere ikiye ayrılır.…”

Section: Introductionunclassified

“…Jmali ve ark. [24] kumaş örneklerindeki hataları bulup sınıflandırmak için tek katmanlı sinir ağı kullanırken Kumar [25] ile Kuo ve Lee [26] geri beslemeli sinir ağı kullanırlar. Destek vektör makinelerinin kullanıldığı çalışmalarda sınıfları en iyi ayıran hiperdüzlemi bulmak için genellikle melez sistemlerin geliştirildiği saptanmıştır.…”

Section: Introductionunclassified

Kumaşlarda Hatayı Yerel Olarak Arayan Denetimsiz Bir Sistem

Çiklaçandir¹,

Utku²,

Özdemi̇r³

2020

Tekstil ve Mühendis

View full text Add to dashboard Cite

Defects in the fabrics during or after weaving reduce the quality of them. With the development of technology, the frequency of the defects seen in fabrics has decreased, but still occurs. In the process of detecting fabric defects, the quality control unit tries to detect fabric defects. This process is both personal and time consuming, leading to costly and personal Errors. For this reason, solutions have been proposed in studies to carry out and automate the process under computer control. In this study, fabric images are divided into blocks of equal sizes to find out whether there are any defects in the fabrics. The features, which are Extracted by applying feature extraction method to each block of the image, are inserted into the K-means clustering algorithm. Two different methods are applied for feature extraction (gray level co-formation matrix and median difference) and their performances have been compared. The success rate of detecting the defect increases up to 97.99% when the gray level co-occurrence matrix is used. The success rate of detecting the defect increases up to 86.91% when the median differences are used. In addition, In addition, when the success rates are calculated separately for the defects in the weft direction and the defects in the warp direction, it is concluded that the defects in the weft direction are easier to find than the defects in the warp direction.

show abstract

Fabrics defects detecting using image processing and neural networks

Cited by 9 publications

References 8 publications

The effects of fusion-based feature extraction for fabric defect classification

The effects of fusion-based feature extraction for fabric defect classification

Fabric Defect Detection Using YOLOv2 and YOLO v3 Tiny

Kumaşlarda Hatayı Yerel Olarak Arayan Denetimsiz Bir Sistem

Contact Info

Product

Resources

About