Automated Fabric Defect Detection and Classification: A Deep Learning Approach
A computer-based intelligent visual inspection system plays a major role in evaluating the quality of textile fabrics and its demand is continuously increasing in the textile industry, especially when the quality of textile is to be considered. In this paper, we propose an AI-based automated fabric...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
idd3
2021-12-01
|
| Series: | Textile & Leather Review |
| Subjects: | |
| Online Access: | https://www.tlr-journal.com/tlr-2021-sandhya/ |
| _version_ | 1798021160313552896 |
|---|---|
| author | NC Sandhya Nihal Mathew Sashikumar M Priyanka Sebastian Maria Wenisch Kunaraj Kumarasamy |
| author_facet | NC Sandhya Nihal Mathew Sashikumar M Priyanka Sebastian Maria Wenisch Kunaraj Kumarasamy |
| author_sort | NC Sandhya |
| collection | DOAJ |
| description | A computer-based intelligent visual inspection system plays a major role in evaluating the quality of textile fabrics and its demand is continuously increasing in the textile industry, especially when the quality of textile is to be considered. In this paper, we propose an AI-based automated fabric defect detection algorithm which utilizes pre-trained deep neural network models for classifying possible fabric defects. The fabric images are enhanced by pre-processing at various levels using conventional image processing techniques and they are used to train the networks. The Deep Convolutional Neural Network (DCNN) and a pre-trained network, AlexNet, are used to train and classify various fabric defects. With the exiting textile dataset, a maximum classification accuracy of 92.60% is achieved in the conducted simulations. With this accuracy, the detection and classification system based on this classifier model can aid the human to find faults in the fabric manufacturing unit. |
| first_indexed | 2024-04-11T17:09:22Z |
| format | Article |
| id | doaj.art-a374ead58f474a4f9f5227bac36bf9fb |
| institution | Directory Open Access Journal |
| issn | 2623-6281 |
| language | English |
| last_indexed | 2024-04-11T17:09:22Z |
| publishDate | 2021-12-01 |
| publisher | idd3 |
| record_format | Article |
| series | Textile & Leather Review |
| spelling | doaj.art-a374ead58f474a4f9f5227bac36bf9fb2022-12-22T04:12:56Zengidd3Textile & Leather Review2623-62812021-12-01431533510.31881/TLR.2021.24Automated Fabric Defect Detection and Classification: A Deep Learning ApproachNC Sandhya0Nihal Mathew Sashikumar1M Priyanka2Sebastian Maria Wenisch3Kunaraj Kumarasamy4Loyola-ICAM College of Engineering and Technology (LICET), Loyola Campus, Chennai-600034, IndiaLoyola-ICAM College of Engineering and Technology (LICET), Loyola Campus, Chennai-600034, IndiaLoyola-ICAM College of Engineering and Technology (LICET), Loyola Campus, Chennai-600034, IndiaLoyola-ICAM College of Engineering and Technology (LICET), Loyola Campus, Chennai-600034, IndiaLoyola-ICAM College of Engineering and Technology (LICET), Loyola Campus, Chennai-600034, IndiaA computer-based intelligent visual inspection system plays a major role in evaluating the quality of textile fabrics and its demand is continuously increasing in the textile industry, especially when the quality of textile is to be considered. In this paper, we propose an AI-based automated fabric defect detection algorithm which utilizes pre-trained deep neural network models for classifying possible fabric defects. The fabric images are enhanced by pre-processing at various levels using conventional image processing techniques and they are used to train the networks. The Deep Convolutional Neural Network (DCNN) and a pre-trained network, AlexNet, are used to train and classify various fabric defects. With the exiting textile dataset, a maximum classification accuracy of 92.60% is achieved in the conducted simulations. With this accuracy, the detection and classification system based on this classifier model can aid the human to find faults in the fabric manufacturing unit.https://www.tlr-journal.com/tlr-2021-sandhya/fabric defectsartificial intelligencedefect classifieralexnetdeep neural network |
| spellingShingle | NC Sandhya Nihal Mathew Sashikumar M Priyanka Sebastian Maria Wenisch Kunaraj Kumarasamy Automated Fabric Defect Detection and Classification: A Deep Learning Approach Textile & Leather Review fabric defects artificial intelligence defect classifier alexnet deep neural network |
| title | Automated Fabric Defect Detection and Classification: A Deep Learning Approach |
| title_full | Automated Fabric Defect Detection and Classification: A Deep Learning Approach |
| title_fullStr | Automated Fabric Defect Detection and Classification: A Deep Learning Approach |
| title_full_unstemmed | Automated Fabric Defect Detection and Classification: A Deep Learning Approach |
| title_short | Automated Fabric Defect Detection and Classification: A Deep Learning Approach |
| title_sort | automated fabric defect detection and classification a deep learning approach |
| topic | fabric defects artificial intelligence defect classifier alexnet deep neural network |
| url | https://www.tlr-journal.com/tlr-2021-sandhya/ |
| work_keys_str_mv | AT ncsandhya automatedfabricdefectdetectionandclassificationadeeplearningapproach AT nihalmathewsashikumar automatedfabricdefectdetectionandclassificationadeeplearningapproach AT mpriyanka automatedfabricdefectdetectionandclassificationadeeplearningapproach AT sebastianmariawenisch automatedfabricdefectdetectionandclassificationadeeplearningapproach AT kunarajkumarasamy automatedfabricdefectdetectionandclassificationadeeplearningapproach |