Fabric Defect Detection With Deep Learning and False Negative Reduction

Almeida, T. N. S.; Moutinho, Filipe; Matos-Carvalho, J. P.

doi:10.1109/access.2021.3086028

Cited by 17 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Almeida et al. 59 presented an automatic system complemented with the operator decision called false negative reduction. The overall system demonstrates how operator-assisted systems could be beneficial.…”

Section: Deep Learning-based Fabric Defect Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based fabric defect detection: A review

Kahraman

Durmuşoğlu

2022

Textile Research Journal

View full text Add to dashboard Cite

The use of the deep learning approach in the textile industry for the purpose of defect detection has become an increasing trend in the past 20 years. The majority of publications have investigated a specific problem in this field. Furthermore, many of published reviews or survey articles preferred to investigate papers from a more general perspective. Compared with published review publications, this study is the first up-to-date study that investigates the implementation of deep learning approaches for the detection of fabric defects from 2003 to the present. As the main objective of this study is to review deep learning-based fabric defect detection, the publications regarding fabric defect detection by using deep learning are examined. The methods, database, performance rates, comparisons, and architecture type of these works were compared with each other. The most widely used deep learning architectures customized deep convolutional neural networks, long short-term memory, generative adversarial networks, and autoencoders. Besides the use of the most used deep learning algorithms, the advantages and disadvantages of these approaches have also been expressed.

show abstract

Section: Deep Learning-based Fabric Defect Detectionmentioning

confidence: 99%

“…For categorization purposes, traditional fully connected layers of CNN were performed to classify images into defective and nondefective. 59 presented an automatic system complemented with the operator decision called false negative reduction. The overall system demonstrates how operator-assisted systems could be beneficial.…”

Section: Autoencodersmentioning

confidence: 99%

Deep learning-based fabric defect detection: A review

Kahraman

Durmuşoğlu

2022

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…Therefore, for the size of the image is m × n, the sparse matrix M with the size of (2 × m × n) × (m × n) can be obtained, and the vector V with the size of (2 × m × n) × 1. For the whole image, (12) can be converted into:…”

Section: Principle Of Zonal and Time-sharing Computational Imagingmentioning

confidence: 99%

“…are used to eliminate the interference information and extract the defect information [5]- [11]. Alternatively, deep learning can be used to achieve segmentation and recognition of the defects based on gray images [12]- [16]. However, in most industrial field inspection, it still relies on manual visual inspection.…”

Section: Introductionmentioning

confidence: 99%

Research on Surface Defect Detection Technology Based on the Zonal and Time-Sharing Computational Imaging

Yin

Yuan

et al. 2022

IEEE Access

View full text Add to dashboard Cite

In order to solve the misjudgment problem of different information in common gray images due to the very similar features such as morphology and gray value, and to avoid the high cost of using the 3-D sensor in defect detection, a zonal and time-sharing computational imaging (ZTSCI) is proposed in this paper. Firstly, a four-zone and time-sharing exposure visual imaging system is constructed by monocular telecentric imaging and lights in different directions. Then, according to the gray images under four groups of illumination conditions, and the direction vectors of incident lights, five feature images are calculated, such as fused images of maximum and average, enhanced images of normal vector, gradient and relative height. On the one hand, the image background fluctuation caused by the calculation error introduced by the ideal hypothesis is weakened, and the interference of surface texture to defect detection is reduced. On the other hand, the difference of easily-confused information can be increased in different feature spaces. In this paper, the ZTSCI is further applied to defect detection on the surface of new energy batteries. It solves the problem that defects and interference information are difficult to distinguish in gray images captured with common machine vision methods, reduces the difficulty of subsequent defect recognition, and lays a foundation for improving the accuracy of recognition.

show abstract

“…Recently, with the development of deep learning, several studies to detect defects using a convolutional neural network (CNN) have been proposed [12][13][14][15][16][17][18][19][20][21][22][23]. Xiao et al [12] proposed a hierarchical feature-based CNN (H-CNN) structure that generates regions of interest (ROIs) using region-based CNN (R-CNN) and detects the defect using a fully CNN (F-CNN).…”

Section: Introductionmentioning

confidence: 99%

STAIN Defect Classification by Gabor Filter and Dual-Stream Convolutional Neural Network

Kim²,

Park³

2022

Preprint

View full text Add to dashboard Cite

A STAIN defect is difficult to detect with the naked eye because of its characteristic of having a very minimal difference in brightness with the local area of the surface. Usually, background extraction–based and Gabor filter–based texture feature–based methods have been proposed to detect STAIN defects. Recently, with the development of deep learning, the convolutional neural network (CNN)–based detection method has been proposed. Gabor filter images have an advantage in image texture analysis and can be used as an input to the CNNs. However, because the original image and the Gabor filter image have different domains, it is necessary to design a CNN that can extract features advantageous for STAIN defect classification. In this paper, a CNN for STAIN defect classification using the original image and Gabor filter image was proposed. A Gary-Level Co-occurrence Matrix (GLCM) matrix from the Gabor filter image was constructed, and then the Inverse Difference Moment (IDM) value, which is a homogeneity local feature, was extracted. Gabor filter images suitable for STAIN defect classification were selected using IDM values, and a STAIN defect detection system that uses the selected Gabor filter images and the inspection image as an input to the CNN was constructed. As a result of the experiment based on the magnetic tile data set and the compact camera module (CCM) dataset, it was confirmed that the proposed method has an improved performance based on the precision, recall, and F1-score in comparison to the single-stream CNN-based method.

show abstract

Fabric Defect Detection With Deep Learning and False Negative Reduction

Cited by 17 publications

References 35 publications

Deep learning-based fabric defect detection: A review

Deep learning-based fabric defect detection: A review

Research on Surface Defect Detection Technology Based on the Zonal and Time-Sharing Computational Imaging

STAIN Defect Classification by Gabor Filter and Dual-Stream Convolutional Neural Network

Contact Info

Product

Resources

About