Image restoration fabric defect detection based on the dual generative adversarial network patch model

Abstract

The training of supervised learning requires the use of ground truth, which is difficult to obtain in large quantities in production practice. Unsupervised learning requires only flawless and anomalous images of fabrics, but inevitably generates a great deal of background noise when performing result generation, which reduces the quality of results. To overcome these limitations, we propose a new approach: image restoration fabric defect detection based on the dual generative adversarial network patch model (DGPM). We train with a modified generative adversarial network using only flawless and anomalous images of the fabric. We propose the patch model to directly obtain specific information about fabric defects and add a self-attentive model to reduce the generation of background noise. The performance of the DGPM is evaluated on box-, star-, and dot-patterned fabric databases. The true positive rate (TPR) of the box type is 81.56% and the f-measure is 62.69%, the TPR of the dot type is 83.72% and the f-measure is 67.33%, and the TPR of the star type is 79.79% and the f-measure is 64.65%.

Multi-scale aware turbulence network for underwater object recognition

“…Sun et al (Sun et al, 2022) construct a novel bidirectional recursive VSR architecture to recover fine details by dividing the task into two subtasks and directing the attention to a motion compensation module that eliminates the effect of inter-frame misalignment. Cheng et al (Cheng et al, 2022) propose a dual generative adversarial network patch model (DGPM) based image recovery for structural defects detection. Jiang et al (Jiang et al, 2022b) proposed two restart nonlinear conjugate gradient method (CGM) with different restart degrees to solve the problem of unconstrained optimization and image restoration.…”

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

“…Li et al 12 proposed the FD-YOLOv5 model, which replaced bottleneck structures with Coordinate Attention (CA) attention and utilized Mish activation and SCYLLA-IoU (SIoU) loss functions to optimize non-linearity and convergence speed, achieving 65.1% mean average precision (mAP) on the Alibaba Cloud Tianchi dataset. Cheng et al 13 introduced a model based on dual GANs for fabric defect detection, reducing noise generation through self-attention mechanisms and obtaining an average True Positive Rate (TPR, Recall) of around 81.5% on various fabric pattern datasets. Zhang et al 14 presented an attention-based feature fusion GAN framework, using EfficientNetV2 as the feature fusion pyramid backbone and employing attention mechanisms to enhance channel and spatial features, thus improving the model's focus on texture details for unsupervised fabric defect detection.…”