Fabric defect fetection via weighted low-rank decomposition and Laplacian regularization

Ji, Xuan; Liang, Jiuzhen; Di, Lan; Xia, Yunfei; Hou, Zhenjie; Huan, Zhan; Huan, Yuxi

doi:10.1177/1558925020957654

Cited by 9 publications

(11 citation statements)

References 41 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final Loss function of our design used to control the generator is Loss m = Loss f f t + Loss piexl + Loss mean (8) With this three-part Loss function, we obtain better generation results, which are shown in Chapter 4.…”

Section: Similarity Image Lossmentioning

confidence: 87%

“…the WGIS [4] method is based on the GIS method with the addition of wavelet transform processing. Template correction (TC) [5], ID [6], TVSL [7], and WLRL [8] are methods that utilize template matching for defect detection.GHOG [9], which takes advantage of the fact that the defective part of a defective image is redundant and prominent in the background, uses Gabor and the histogram of orientation gradients (HOG) to divide the image into low-rank and sparse parts so that the defects are detected.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised direct generation of defect residual images forfabric defect detection

Cheng

Liang

Líu

2022

Preprint

Self Cite

View full text Add to dashboard Cite

When performing fabric defect detection, ground truth is required for training with supervisedlearning, more steps are required for training with unsupervised learning, and background noise isgenerated during the training process. To solve the above problems, we propose the fabric defectdetection model with unsupervised direct defect residual image generation (UDDGAN). The gener-ative adversarial network model architecture is used in the main body of the model, and we designthe patch structure such that the defect residual images can be generated directly. We use a gen-erator with block blocks and a double discriminator to make the generated image closer to thetarget image. We incorporate similar image loss when training the generator to minimize the gen-erated background noise, which ensures the accuracy of the detection results. We achieve betterresults on a benchmark dataset for fabric defect detection at Zhejiang University and compare itwith six methods. The experimental results show that our method works well on a variety of metrics.

show abstract

Section: Similarity Image Lossmentioning

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Unsupervised direct generation of defect residual images forfabric defect detection

Cheng

Liang

Líu

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Firstly, deep convolution neural network is used to extract fabric features and generate feature matrix, and then low rank recovery model was used to locate defects. Ji et al 25 proposed a detection method based on weighted low rank decomposition and Laplacian regularization term. By introducing Laplacian regularization term to expand the distance between background and defect area, the robustness of the model is enhanced.…”

Section: Related Workmentioning

confidence: 99%

“…The theory of biological vision is used to characterize the fabric Qizi et al 27 Low rank representation with texture prior Prior information is used to guide the decomposition of low rank model Ji et al 25 Weighted low rank decomposition and Laplacian regularization…”

Section: Low Rank Decomposition With Biological Vision Modelingmentioning

confidence: 99%

Fabric defect detection based on deep-handcrafted feature and weighted low-rank matrix representation

Jiang

Liu

et al. 2021

Journal of Engineered Fibers and Fabrics

View full text Add to dashboard Cite

In the process of textile production, automatic defect detection plays a key role in controlling product quality. Due to the complex texture features of fabric image, the traditional detection methods have poor adaptability, and low detection accuracy. The low rank representation model can divide the image into the low rank background and sparse object, and has proven suitable for fabric defect detection. However, how to further effectively characterize the fabric texture is still problematic in this kind of method. Moreover, most of them adopt nuclear norm optimization algorithm to solve the low rank model, which treat every singular value in the matrix equally. However, in the task of fabric defect detection, different singular values of feature matrix represent different information. In this paper, we proposed a novel fabric defect detection method based on the deep-handcrafted feature and weighted low-rank matrix representation. The feature characterization ability is effectively improved by fusing the global deep feature extracted by VGG network and the handcrafted low-level feature. Moreover, a weighted low-rank representation model is constructed to treat the matrix singular values differently by different weights, thus the most distinguishing feature of fabric texture can be preserved, which can efficiently outstand the defect and suppress the background. Qualitative and quantitative experiments on two public datasets show that our proposed method outperforms the state-of-the-art methods.

show abstract

“…6 Traditional fabric defect detection methods are roughly divided into four categories: statistical, 7 spectral analysis, 8 model-based, 9 and low-rank decomposition. 10 Ji et al 11 proposed a detection method based on weighted low rank decomposition and Laplacian regularization term. By introducing Laplacian regularization term to expand the distance between background and defect area, the robustness of the model is enhanced.…”

Section: Introductionmentioning

confidence: 99%

Fabric defect detection based on transfer learning and improved Faster R-CNN

Zhao

Shi

Zheng

et al. 2022

Journal of Engineered Fibers and Fabrics

View full text Add to dashboard Cite

Fabric defect detection is an important quality inspection process in the textile industry. A fabric defect detection system based on transfer learning and an improved Faster R-CNN is proposed to solve the problems of low detection accuracy, general convergence ability, and poor detection effect for small target defects in existing fabric defect detection algorithms. The pre-trained weights on the big dataset Imagenet are first extracted for transfer learning. Images are then input into the improved Faster R-CNN network, while the ResNet50 and ROI Align are used to replace the original VGG16 feature extraction network structure and a region of interest (ROI) pooling layer to avoid the problems of region mismatch caused by two quantizations from ROI pooling. The region proposal network (RPN) is combined with the multi-scale feature pyramid FPN to generate candidate regions with richer semantic information and project them onto the feature map to obtain the corresponding feature matrix. Cascaded modules are integrated and different IoU thresholds are used for each level to distinguish positive and negative samples. Finally, the softmax classifier is adopted to identify the image and obtain the predictions. The experimental results show that the detection accuracy and convergence ability of the improved Faster R-CNN are greatly enhanced compared with the current mainstream models, which provides a reference for future fabric defect detection methods.

show abstract

Fabric defect fetection via weighted low-rank decomposition and Laplacian regularization

Cited by 9 publications

References 41 publications

Unsupervised direct generation of defect residual images forfabric defect detection

Unsupervised direct generation of defect residual images forfabric defect detection

Fabric defect detection based on deep-handcrafted feature and weighted low-rank matrix representation

Fabric defect detection based on transfer learning and improved Faster R-CNN

Contact Info

Product

Resources

About