INTELLIGENT FABRIC DEFECT DETECTION USINGDEEPLEARNINGANDREAL-TIME VISION SYSTEMSAPPLICATION

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: U. Satyanarayana, P. Sana Nawaz, P. Charmy, Sk. Md. Sana Gousebee, Sk. Vasiha Thapsum
Format: Recurso digital
Publié: Zenodo 2025
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901997035192320
author U. Satyanarayana, P. Sana Nawaz, P. Charmy, Sk. Md. Sana Gousebee, Sk. Vasiha Thapsum
author_facet U. Satyanarayana, P. Sana Nawaz, P. Charmy, Sk. Md. Sana Gousebee, Sk. Vasiha Thapsum
contents <p><strong>ABSTRACT- </strong>Fabric defect detection plays a vital role in quality control within the textile industry. Computer vision-basedinspection has become a key technology for enabling intelligent manufacturing. This study reviews advancementsin intelligent fabric defect detection, focusing on algorithms, datasets, and detection systems. Detectionmethodsare categorized into traditional and learning-based approaches. Traditional methods include model-based, spectral,statistical, and structural techniques, while learning-based methods are divided into classical machine learninganddeep learning techniques. The study compares deep learning models based on their principles, accuracy, real-timeperformance, and practical applicability. Additionally, it examines commonly used fabric defect datasets and deep learning frameworks, organizingpublicdatasets and widely adopted models. To improve real-time defect detection, the YOLOV8 algorithmis utilized,offering high speed and accuracy in identifying irregularities. YOLO’s efficiency in processing entire imagesinasingle pass makes it well-suited for rapid textile inspection.</p> <p> </p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17122279
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle INTELLIGENT FABRIC DEFECT DETECTION USINGDEEPLEARNINGANDREAL-TIME VISION SYSTEMSAPPLICATION
U. Satyanarayana, P. Sana Nawaz, P. Charmy, Sk. Md. Sana Gousebee, Sk. Vasiha Thapsum
<p><strong>ABSTRACT- </strong>Fabric defect detection plays a vital role in quality control within the textile industry. Computer vision-basedinspection has become a key technology for enabling intelligent manufacturing. This study reviews advancementsin intelligent fabric defect detection, focusing on algorithms, datasets, and detection systems. Detectionmethodsare categorized into traditional and learning-based approaches. Traditional methods include model-based, spectral,statistical, and structural techniques, while learning-based methods are divided into classical machine learninganddeep learning techniques. The study compares deep learning models based on their principles, accuracy, real-timeperformance, and practical applicability. Additionally, it examines commonly used fabric defect datasets and deep learning frameworks, organizingpublicdatasets and widely adopted models. To improve real-time defect detection, the YOLOV8 algorithmis utilized,offering high speed and accuracy in identifying irregularities. YOLO’s efficiency in processing entire imagesinasingle pass makes it well-suited for rapid textile inspection.</p> <p> </p>
title INTELLIGENT FABRIC DEFECT DETECTION USINGDEEPLEARNINGANDREAL-TIME VISION SYSTEMSAPPLICATION
url https://doi.org/10.5281/zenodo.17122279