Integral images-based approach for fabric defect detection

Fouda, Y. M.

doi:10.1016/j.optlastec.2021.107608

Cited by 9 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also studies that detect defects on different materials using CNN. Defect-detection studies are on glass panels [24], wood [25], and fabric [26][27][28][29][30].…”

Section: B Deep-learning Techniquesmentioning

confidence: 99%

Deep Learning Based Classification of Military Cartridge Cases and Defect Segmentation

et al. 2022

View full text Add to dashboard Cite

The final stage of the production process in the industry is quality control. Quality control answers the question of is there a defect on the surface of the products. Frequently the quality control is performed manually. The disadvantages of manual quality control are high error rate (low accuracy), low product rate (low performance) and high expense rate (high cost). The solution is automatic quality control using machine vision systems. These systems classify the products and segment the defects on their surfaces by processing the images taken by cameras during the production process in real-time. Some products like military cartridge cases have metallic, cylindrical, non-uniform texture and highly reflective surface. So, the quality of images is very important. Another factor that affects the accuracy is the nonuniform texture of the product surface. Distinguishing the product non-uniform texture from defect texture is a challenging problem. In previous works, this problem have been tried to be solved with image processing and deep learning techniques and the accuracy of 97% and 96% have been obtained, appropriately. According to NATO standards, the accuracy of the classification of the military cartridge cases should be above 99%. In this work, the methodology for classification of the military cartridge cases and segmentation of the defects on their surfaces with non-uniform texture is proposed to increase the accuracy. In scope of the proposed methodology the datasets with non-defective, defective and labeled/masked image classes of the cartridge cases were created, the deep learning models to classify the military cartridge cases and segment the defects on their surfaces were proposed, implemented and obtained results were evaluated using the metrics such as Accuracy, Precision, Recall, F1-Score, Jaccard Index (JI) and Mean Intersection over Union (mIoU). Obtained results showed that the proposed methodology increased the accuracy of classification to 100% with the DenseNet169 model and the F1-Score of segmentation to 92.1% with Improved U-Net and ResUnet models.

show abstract

“…There are also studies that detect defects on different materials using CNN. Defect-detection studies are on glass panels [24], wood [25], and fabric [26][27][28][29][30].…”

Section: B Deep-learning Techniquesmentioning

confidence: 99%

Deep Learning Based Classification of Military Cartridge Cases and Defect Segmentation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…3 In fabric production, most of the detection is performed manually, having low efficiency with only 70% accuracy, and the high labor cost is overwhelming for many companies. 4 Thus, automated fabric defect detection has become an urgent need for developing the textile industry.…”

mentioning

confidence: 99%

Lightweight Single Shot Multi-Box Detector: A fabric defect detection algorithm incorporating parallel dilated convolution and dual channel attention

Liu,

Huang,

Zhao

et al. 2023

Textile Research Journal

View full text Add to dashboard Cite

For the textile industry, fabric defect detection is an important part of production. In order to make the automatic fabric defect detection system used in production sites, this article proposes a lightweight algorithm Lightweight Single Shot Multi-Box Detector (LW-SSD) to address the issues of low detection accuracy, high computational complexity, and difficulty in deploying on hardware devices with limited computing power in fabric defect detection. Firstly, MobileNetv3 is introduced as the backbone network to reduce the number of model parameters. Secondly, in the feature fusion module, down-sampling stacking is used to fuse the feature maps processed by maximum pooling and regular 3 × 3 convolution, respectively, to enhance the generalization and small target feature extraction capability of the network. Then, the dilated convolution is incorporated into the Inceptionv3 to form a multi-branch parallel dilated convolution module, which can expand the receptive field of the feature layer and enhance the extraction of the target information. Finally, a dual-channel attention module is added, which adds the maximum pooling operation based on the efficient channel attention for deep convolutional neural networks (ECA) channel attention mechanism to highlight defect features and suppress background noise features. The experiments show that the accuracy of the system is improved while maintaining the faster detection speed. Among them, the LW-SSD algorithm has an accuracy improvement of 10.03% on the self-made dataset, a reduction of 58% in the number of model parameters compared to the Single Shot Multi-Box Detector (SSD) algorithm, and the detection speed reaches 48 frames per second.

show abstract

“…is particularly important! The existing surface defect detection methods include traditional classical artificial vision, virtual structured light, point cloud scanning, ultrasonic detection and other methods [4][5][6][7]. After a long period of development, artificial vision is an indispensable and widely used method, but its shortcomings are still obvious, such as low efficiency, relying on experience, easy to miss detection, difficult to quantify visualization, large individual differences, difficult to unify standards, and difficult to trace the source.…”

mentioning

confidence: 99%

Research on Digital Testing Technology for Full Surface Defects of Cross scale Heteromorphic Metal Devices

Liu

Ma²,

Bai³

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

There are many types of cross scale special-shaped metal components in various fields, and the surface quality (defects) of some key components will affect the device performance and even cause the long-term stability and reliability of the system to decline. The existing manual inspection methods are difficult to accurately quantify and establish a digital traceability database, so it is urgent to study the automatic digital inspection technology of full surface defects. However, most of the devices are curved surfaces with different shapes, large size spans, various types of surface defects and diffuse reflection imaging, and the background of machine vision images is complex, which greatly increases the difficulty of defect detection. Based on the principle of machine vision imaging, this paper designs a long depth of field and low distortion imaging system for curved surfaces. Combined with a flexible scanning motion mechanism with multiple degrees of freedom, this paper studies the technology of complex background defect extraction to realize the full surface defect detection of cross scale special-shaped metal devices.

show abstract

Integral images-based approach for fabric defect detection

Cited by 9 publications

References 33 publications

Deep Learning Based Classification of Military Cartridge Cases and Defect Segmentation

Deep Learning Based Classification of Military Cartridge Cases and Defect Segmentation

Lightweight Single Shot Multi-Box Detector: A fabric defect detection algorithm incorporating parallel dilated convolution and dual channel attention

Research on Digital Testing Technology for Full Surface Defects of Cross scale Heteromorphic Metal Devices

Contact Info

Product

Resources

About