Answers are grounded in this paper and cite their sources.
Fabric defect detection is a crucial part of the modern textile industry, which is of great significance for improving product quality, reducing production cost and enhancing production efficiency. However, most of the existing learning methods are difficult to fully capture the deep features of colour fabric images, and the generated feature representation ability is insufficient. Therefore, this paper proposes a focused convolution colour fabric defect detection method (MGRC‐Net) based on adaptive memory fusion for unsupervised colour fabric defect detection. In this method, memory unit is introduced into the skip connection to store, filter and update key historical information of colour fabric images, so as to enhance the information transmission ability of skip connection, so that the model can effectively capture the context information of colour fabric image. By adopting an adaptive fusion module, the effective fusion of local information and global information of colour fabric images is ensured. Experiments have shown that this method can effectively reconstruct coloured fabric images without requiring a large number of defected marking samples, so as to realise the detection and location of defect areas in coloured fabric patterns.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: