Sylvester Matrix‐Based Similarity Estimation Method for Automation of Defect Detection in Textile Fabrics

Abstract

Fabric defect detection is a crucial quality control step in the textile manufacturing industry. In this article, a machine vision system based on the Sylvester Matrix-Based Similarity Method (SMBSM) is proposed to automate the defect detection process. The algorithm involves six phases, namely, resolution matching, image enhancement using Histogram Specification and Median–Mean-Based Sub-Image-Clipped Histogram Equalization, image registration through alignment and hysteresis process, image subtraction, edge detection, and fault detection by means of the rank of the Sylvester matrix. The experimental results demonstrate that the proposed method is robust and yields an accuracy of 93.4%, a precision of 95.8%, and computational speed of 2275 ms.

Enhancing Textile Quality Control With Iot Sensors: A Case Study of Automated Defect Detection

“…Specifically, in the realm of quality inspection, IoT sensors are proving to be instrumental. Vision-based systems with high-resolution cameras and IoT connectivity can detect minute anomalies across various manufacturing processes, ensuring products meet quality standards (Kumari et al, 2021). Furthermore, integrating IoT sensors with machine learning algorithms enables adaptive, self-improving inspection processes, optimizing detection accuracy over time.…”

Defect detection algorithm for fabric based on deformable convolutional network

“…At present, the fabric defect detection methods proposed by domestic and foreign researchers mainly include five categories based on structural analysis, 16 statistical analysis, 17 frequency domain analysis, 18 learning analysis, 19 and model analysis. 20 The traditional fabric defect detection method based on image processing only realizes the detection of the defect but does not clearly detect the category of the detected defect.…”

A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection

“…Although this method outperformed support vector machines in experiments, it requires initial pre-processing through conversion and filtering techniques, which accounts for redundancy. Statistical analysis [6]-Kumari et al [7] extracted fabric defects based on the similarity estimation method of Sylvester matrix, which can process test images captured under various lighting conditions. However, it detected only three types of defects and its fitting ability was inadequate.…”