Detection and Classification of Fabric Defects  Using Deep Learning Algorithms

Recep Ali Geze; Ayhan Akbaş

Article Details

Detection and Classification of Fabric Defects Using Deep Learning Algorithms

Authors:

Recep Ali Geze | Ayhan Akbaş

Publisher:

Gazi University

Main Topics:

Derin Öğrenme

Journal:

Politeknik Dergisi Vol.27 Issue 1, pp.371-378

Document Type:

Article

Publication Date:

2/2024

Document Language:

English

Document ID (Org No.):

2001312559

pISSN:

2147-9429

Keywords:

Abstract:

 The textile industry primarily relies on fabric as a crucial raw material, the production of which involves multiple complex stages. Due to the multitude and complexity of these stages, fabric defects can frequently occur. With the modern fabric production process being nearly fully automated, and given the variety of potential defects, detecting errors on fabrics has become increasingly challenging. The rapid pace of production and the substantial market share of the sector mean that relying on human inspection for error detection can lead to significant time losses and can reduce the accuracy of defect detection to around 60. Consequently, recent years have seen a shift towards the development of intelligent systems for fabric defect detection in parallel with technological advancements. With the rapid progression of artificial intelligence, the application of image processing techniques has commenced in this field. This study has developed a real-time defect detection system for fabrics using deep learning techniques. Initially, a network model was created using an open-source neural network library, CNN, achieving 89 accuracy. Subsequent implementations using the VGG16 and InceptionV3 architectures reached accuracies of 89 and 86, respectively. To further improve the study, fabrics were classified into two categories: defective and non-defective, and the pre-trained Convolutional Neural Networks model ResNet50-v2 was employed as a feature extractor. This approach yielded an approximate accuracy of 95.

 The textile industry primarily relies on fabric as a crucial raw material, the production of which involves multiple complex stages. Due to the multitude and complexity of these stages, fabric defects can frequently occur. With the modern fabric production process being nearly fully automated, and given the variety of potential defects, detecting errors on fabrics has become increasingly challenging. The rapid pace of production and the substantial market share of the sector mean that relying on human inspection for error detection can lead to significant time losses and can reduce the accuracy of defect detection to around 60. Consequently, recent years have seen a shift towards the development of intelligent systems for fabric defect detection in parallel with technological advancements. With the rapid progression of artificial intelligence, the application of image processing techniques has commenced in this field. This study has developed a real-time defect detection system for fabrics using deep learning techniques. Initially, a network model was created using an open-source neural network library, CNN, achieving 89 accuracy. Subsequent implementations using the VGG16 and InceptionV3 architectures reached accuracies of 89 and 86, respectively. To further improve the study, fabrics were classified into two categories: defective and non-defective, and the pre-trained Convolutional Neural Networks model ResNet50-v2 was employed as a feature extractor. This approach yielded an approximate accuracy of 95.

 The textile industry primarily relies on fabric as a crucial raw material, the production of which involves multiple complex stages. Due to the multitude and complexity of these stages, fabric defects can frequently occur. With the modern fabric production process being nearly fully automated, and given the variety of potential defects, detecting errors on fabrics has become increasingly challenging. The rapid pace of production and the substantial market share of the sector mean that relying on human inspection for error detection can lead to significant time losses and can reduce the accuracy of defect detection to around 60. Consequently, recent years have seen a shift towards the development of intelligent systems for fabric defect detection in parallel with technological advancements. With the rapid progression of artificial intelligence, the application of image processing techniques has commenced in this field. This study has developed a real-time defect detection system for fabrics using deep learning techniques. Initially, a network model was created using an open-source neural network library, CNN, achieving 89 accuracy. Subsequent implementations using the VGG16 and InceptionV3 architectures reached accuracies of 89 and 86, respectively. To further improve the study, fabrics were classified into two categories: defective and non-defective, and the pre-trained Convolutional Neural Networks model ResNet50-v2 was employed as a feature extractor. This approach yielded an approximate accuracy of 95.

 Tekstil sektörünün en önemli ham maddesi olan kumaşın üretimi birçok aşamadan meydana gelmektedir. Bu üretim aşamalarının fazlalığı ve karmaşıklığından dolayı kumaşlarda bazı hatalar meydana gelebilmektedir. Günümüzde kumaş üretim süreci neredeyse tamamen otomasyon ile olduğundan ve kumaş üzerinde oluşan hata çeşitliliğinin fazlalığından dolayı kumaş üzerinde oluşabilecek hataları tespit etmek oldukça zordur. Hataların tespit edilmesinde; sektörün pazar payının büyüklüğü ve üretimin çok hızlı olmasının nedeniyle insan kontrolü ile tespit etmek hem zaman kaybına hem de hata tespit oranının 60 seviyelerine kadar düşmesine neden olmaktadır. Bundan dolayı son yıllarda teknolojinin gelişmesiyle paralel kumaşların hata tespitinde daha çok akıllı sistemler geliştirilmeye başlanmıştır. Günümüzde yapay zekâ teknolojisinin hızla gelişmesiyle bu sektörde de görüntü işleme teknikleri uygulamalar başlamıştır. Bu çalışmada derin öğrenme teknikleri kullanarak kumaş üzerinde gerçek zamanlı hata tespit sistemi geliştirilmiştir. Yapılan çalışmada ilk olarak açık kaynaklı bir sinir ağı kütüphanesi olan CNN ile bir ağ modeli oluşturulmuş ve bu yöntemle 89 doğruluk elde edilmiştir. Sonra VGG16 mimarisi ile 89 ve IneptionV3mimarisi ile 86 oranında doğruluğa ulaşılmıştır. Çalışmayı daha iyi hale getirmek için kumaşları hatalı ve hatasız başlığı altında iki sınıfta sınıflandırıp önceden eğitilmiş Evrişimsel Sinir Ağları modellerinden olan ResNet50-v2 özellik çıkarıcı olarak kullanılmıştır. Bu şekilde yaklaşık 95 doğruluk elde edilmiştir.

Article Details

Detection and Classification of Fabric Defects Using Deep Learning Algorithms

Authors:

Recep Ali Geze | Ayhan Akbaş

Publisher:

Gazi University

Main Topics:

Derin Öğrenme

Journal:

Politeknik Dergisi Vol.27 Issue 1, pp.371-378

Document Type:

Article

Publication Date:

2/2024

Document Language:

English

Document ID (Org No.):

2001312559

pISSN:

2147-9429

mage Processing

Fabric Defect Detection

Textiles

Deep LearningGörüntü İşleme

Kumaş Hatası Tespiti

Tekstil

Derin Öğrenme

Issues

Article Details

Authors: Recep Ali Geze | Ayhan Akbaş

Publisher: Gazi University

Main Topics: Derin Öğrenme

Journal: Politeknik Dergisi Vol.27 Issue 1, pp.371-378

Document Type: Article

Publication Date: 2/2024

Document Language: English

Document ID (Org No.): 2001312559

pISSN: 2147-9429

Issues

Authors:

Recep Ali Geze | Ayhan Akbaş

Publisher:

Gazi University

Main Topics:

Derin Öğrenme

Journal:

Politeknik Dergisi Vol.27 Issue 1, pp.371-378

Document Type:

Article

Publication Date:

2/2024

Document Language:

English

Document ID (Org No.):

2001312559

pISSN:

2147-9429