A Robust Fabric Defect Detection Method Based on Improved RefineDet

Xie, Huosheng; Wu, Zesen

doi:10.3390/s20154260

Cited by 37 publications

(23 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our detection speed was somewhat faster at 34 fps, as shown in Table 5, an increase of 13:33% over that realtime detection speed benchmark. While our detection speed was only 3:03% better than that of Xie and Wue, 59 this is a significant improvement due to the larger image size our model processed in real time. The prediction speed of our model was 21.4 ms, as shown in Table 6, an increase of 35.15% from the prediction speed benchmark.…”

Section: Discussionmentioning

confidence: 67%

Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model

Dlamini

Kao²,

Su³

et al. 2021

Textile Research Journal

View full text Add to dashboard Cite

We introduce a real-time machine vision system we developed with the aim of detecting defects in functional textile fabrics with good precision at relatively fast detection speeds to assist in textile industry quality control. The system consists of image acquisition hardware and image processing software. The software we developed uses data preprocessing techniques to break down raw images to smaller suitable sizes. Filtering is employed to denoise and enhance some features. To generalize and multiply the data to create robustness, we use data augmentation, which is followed by labeling where the defects in the images are labeled and tagged. Lastly, we utilize YOLOv4 for localization where the system is trained with weights of a pretrained model. Our software is deployed with the hardware that we designed to implement the detection system. The designed system shows strong performance in defect detection with precision of [Formula: see text], and recall and [Formula: see text] scores of [Formula: see text] and [Formula: see text], respectively. The detection speed is relatively fast at [Formula: see text] fps with a prediction speed of [Formula: see text] ms. Our system can automatically locate functional textile fabric defects with high confidence in real time.

show abstract

Section: Discussionmentioning

confidence: 67%

Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model

Dlamini

Kao²,

Su³

et al. 2021

Textile Research Journal

View full text Add to dashboard Cite

show abstract

“…In this section, the EPPAL-OCNN is implemented in MATLAB 2017b using The Irish Longitudinal Study on Ageing (TILDA) dataset [19] for evaluating its efficiency compared with the existing approaches: EPPAL-CNN [9], VG-RCNN [15], RefineDet [13], and PPAL-CNN [8]. In TILDA dataset, each image includes a text reporting defective area in it.…”

Section: Resultsmentioning

confidence: 99%

“…Xie & Wu [13] designed a robust FD identification model depending on the enhanced RefineDet. First, the RefineDet was utilized as the support framework for identifying the fault images.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimizing Gradients Weight of Enhanced Pairwise-Potential Activation Layer in CNN for Fabric Defect Detection

Vinothini¹,

Sheeja²

2022

INDJCSE

View full text Add to dashboard Cite

Imperfection classification is the most involved task in the cotton sector for finding Fabric Defects (FDs) and improving fiber productivity. Several approaches have been suggested in ancient times to automatically classify FDs. Presently, an Enhanced Pairwise-Potential Activation Layer in Convolutional Neural Network (EPPAL-CNN) approach depends on improved external memory and Dynamic Conditional Random Fields (DCRFs) to solve the complex pattern correlation of FDs and detect the defective fabrics from the given images. On the contrary, the gradient-based optimization schemes for learning the weights of CNN tend to unusual convergence nature, resulting in inefficient classification. Hence in this paper, an EPPAL-Optimized CNN (EPPAL-OCNN) approach is proposed which introduces an individual weight optimization scheme depending on NWM-Adam for solving the unwanted convergence of CNN. In this approach, a novel first-order gradient descent optimization method is introduced, which applies an adaptive exponential decay percentage for second-moment approximation rather than a preconfigured and constant one. Also, it can simply modify the grade to which how much the previous gradients weigh in the approximation. This novel exponential moving mean deviation is designed based on the fact that assigning additional memory to the previous gradients compared to the current gradients. Thus, it guarantees effective convergence and increases detection accuracy. At last, the testing results reveal that the EPPAL-OCNN achieves 94.64% of accuracy to different state-of-the-art approaches on the TILDA database.

show abstract

“…The four algorithms were the LBP and histogram of oriented gradients (HOG) to extract features and a fusion + SVM (LBP + HOG + SVM), GLCM to extract features + SVM (GLCM + SVM), ALEXNET featurization principal components + feature fusion + sparse representation-based classification (AFPC-SRC), and Resnet50 featurization principal components+ PCA dimensionality reduction + feature fusion + PMELM (RESNET50-PMELM). We also compared the algorithm proposed herein with the “VICSD” algorithm proposed by Xie and Wu 30 based on the precision, recall, F1-score, and mean average precision (mAP) values. The evaluation indicators for the various algorithms are presented in Tables 5 and 6.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…This method replaced the partial response normalization layer in the AlexNet network with a batch normalization layer and introduced a max pooling layer, dropout layer, and fully connected layer in the classification model to improve the accuracy of fabric defect classification. Xie and Wu 30 used RefineDet as a basic model, and combined it with a full convolutional channel attention block and bottom-up path augmentation transfer connection block (BA-TCB) to improve the defect location accuracy. Finally, an attention mechanism, distance intersection-over-union-non-maximum suppression (DIoU-NMS), and cosine annealing scheduler optimization methods were used to improve the defect detection performance.…”

mentioning

confidence: 99%

Fabric defect detection based on feature fusion of a convolutional neural network and optimized extreme learning machine

Zhou

Deng

Zhu

et al. 2021

Textile Research Journal

View full text Add to dashboard Cite

Aiming to accurately detect various defects in the fabric production process, we propose a fabric defect detection algorithm based on the feature fusion of a convolutional neural network (CNN) and optimized extreme learning machine (ELM). Firstly, we use transfer learning to transfer the parameters of the first 13 convolutional layers and first two fully connected layers of a VGG16 network model as pre-trained by ImageNet to the initial model and fine-tune the parameters. Subsequently, the fine-tuned model is used as a feature extractor to extract features of RGB images and their corresponding L-component images. A principal component analysis is used to reduce the dimensionality of the features and fuse the reduced features. The moth flame optimization (MFO) algorithm is used to initialize the optimization variables of a parallel chaotic search (PCS) algorithm, and the PCS algorithm (as optimized by the MFO algorithm) is used to optimize the input weight and bias of the ELM (i.e., the PCS-MFO-ELM (PMELM)). Finally, the PMELM is used to replace the softmax classifier of the CNN to classify and detect fabric defect features. The experimental results show that on the amplified TILDA dataset, the precision, recall, F1-score, and accuracy rates of this algorithm for fabric holes, stains, warp breaks, dragging, and folds in fabric can reach 98.57%, 98.52%, 98.52%, and 98.50%, respectively, that is, higher than those of other algorithms. Through a validity experiment, this method is shown to be suitable for defect detection for unpatterned fabrics, regular patterned fabrics, and irregularly patterned fabrics.

show abstract

A Robust Fabric Defect Detection Method Based on Improved RefineDet

Cited by 37 publications

References 44 publications

Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model

Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model

Optimizing Gradients Weight of Enhanced Pairwise-Potential Activation Layer in CNN for Fabric Defect Detection

Fabric defect detection based on feature fusion of a convolutional neural network and optimized extreme learning machine

Contact Info

Product

Resources

About