A Method and System for Fabric Surface Defect Detection Based on Deep Convolutional Neural Networks

By combining deep convolutional neural networks with physical principles, the problem of extracting minute defect features in complex backgrounds during high-density fabric defect detection has been solved. This enables accurate identification and physical strength assessment of fabric surface defects, improving the accuracy and reliability of detection.

CN122134674APending Publication Date: 2026-06-02HUAIBIN WALTAI WEAVING CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HUAIBIN WALTAI WEAVING CO LTD
Filing Date
2026-02-25
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively distinguish between texture fluctuations and defects in high-density fabric defect detection, and the assessment results fail to accurately reflect the physical strength risk of the fabric. In particular, the extraction of minute defect features is difficult in complex backgrounds, and existing evaluation indicators lack the quantification of the spatial distribution impact.

Method used

By employing a deep convolutional neural network-based approach, and combining convolutional neural networks with physical principles, we can achieve accurate identification and assessment of surface defects in fabrics through guided weight smoothing reconstruction, gradient field evaluation of texture uniformity, structural defect index, feature saliency, and geometric interaction potential.

Benefits of technology

It improves the recognition accuracy of minor defects in complex backgrounds, reduces mechanical vibration interference, accurately assesses the impact of the spatial distribution of defects on the overall strength of the fabric, and achieves high-precision defect detection and closed-loop control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122134674A_ABST
    Figure CN122134674A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of image data processing technology, specifically relating to a method and system for detecting surface defects in fabrics based on a deep convolutional neural network. The method includes: acquiring an original fabric image and performing adaptive bilateral guided preprocessing to obtain a preprocessed fabric image; obtaining a structural breakage index for evaluating texture uniformity based on the gradient field distribution of the preprocessed fabric image; inputting the structural breakage index into a convolutional neural network to obtain a deep feature image, and using the Hessian matrix to evaluate the curvature abrupt changes in the feature distribution to obtain feature saliency; performing centroid aggregation on the feature saliency, and combining the spatial distribution and geometric shape between defect areas to obtain geometric interaction potential energy; and driving the loom to execute deceleration commands and physical markers based on the geometric interaction potential energy. This invention solves the problem of defect identification in high-density fabrics by assessing the spatial clustering risk of defects, thus achieving precise control of fabric quality.
Need to check novelty before this filing date? Find Prior Art