A focused convolutional colour fabric defect detection network based on adaptive memory fusion

Abstract 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.

Authors

Institutions

Publication Details

Journal
Coloration Technology
Published
2026-11-17
DOI
https://doi.org/10.1111/cote.70120
Primary Topic
Industrial Vision Systems and Defect Detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A focused convolutional colour fabric defect detection network based on adaptive memory fusion

Shuai Lu, Mengdan Chen, Hongwei Zhang, Huanhuan Zhang et al.
Coloration Technology
Industrial Vision Systems and Defect Detection
article

A focused convolutional colour fabric defect detection network based on adaptive memory fusion

Shuai Lu, Mengdan Chen, Hongwei Zhang, Huanhuan Zhang, Siwei Sun
article en

Abstract

Abstract 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.

Coloration Technology
Beijing Institute of Technology (CN), Xi'an Polytechnic University (CN)
National Natural Science Foundation of China
Industrial Vision Systems and Defect Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon