Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data
As defect detection using machine vision is diversifying and expanding, approaches using deep learning are increasing. Recently, there have been much research for detecting and classifying defects using image segmentation, image detection, and image classification. These methods are effective but re...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/7/2511 |
| _version_ | 1797571402891526144 |
|---|---|
| author | Young-Joo Han Ha-Jin Yu |
| author_facet | Young-Joo Han Ha-Jin Yu |
| author_sort | Young-Joo Han |
| collection | DOAJ |
| description | As defect detection using machine vision is diversifying and expanding, approaches using deep learning are increasing. Recently, there have been much research for detecting and classifying defects using image segmentation, image detection, and image classification. These methods are effective but require a large number of actual defect data. However, it is very difficult to get a large amount of actual defect data in industrial areas. To overcome this problem, we propose a method for defect detection using stacked convolutional autoencoders. The autoencoders we proposed are trained by using only non-defect data and synthetic defect data generated by using the characteristics of defect based on the knowledge of the experts. A key advantage of our approach is that actual defect data is not required, and we verified that the performance is comparable to the systems trained using real defect data. |
| first_indexed | 2024-03-10T20:38:50Z |
| format | Article |
| id | doaj.art-7474d9b8d03d4c31b3de092ad3cd788e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T20:38:50Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7474d9b8d03d4c31b3de092ad3cd788e2023-11-19T20:48:10ZengMDPI AGApplied Sciences2076-34172020-04-01107251110.3390/app10072511Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect DataYoung-Joo Han0Ha-Jin Yu1R&D Center, Vieworks, Anyang-si 14055, KoreaSchool of Computer Science, University of Seoul, Seoul 02504, KoreaAs defect detection using machine vision is diversifying and expanding, approaches using deep learning are increasing. Recently, there have been much research for detecting and classifying defects using image segmentation, image detection, and image classification. These methods are effective but require a large number of actual defect data. However, it is very difficult to get a large amount of actual defect data in industrial areas. To overcome this problem, we propose a method for defect detection using stacked convolutional autoencoders. The autoencoders we proposed are trained by using only non-defect data and synthetic defect data generated by using the characteristics of defect based on the knowledge of the experts. A key advantage of our approach is that actual defect data is not required, and we verified that the performance is comparable to the systems trained using real defect data.https://www.mdpi.com/2076-3417/10/7/2511autoencodersCNNfabric defect detectionsynthetic defect generation |
| spellingShingle | Young-Joo Han Ha-Jin Yu Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data Applied Sciences autoencoders CNN fabric defect detection synthetic defect generation |
| title | Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data |
| title_full | Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data |
| title_fullStr | Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data |
| title_full_unstemmed | Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data |
| title_short | Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data |
| title_sort | fabric defect detection system using stacked convolutional denoising auto encoders trained with synthetic defect data |
| topic | autoencoders CNN fabric defect detection synthetic defect generation |
| url | https://www.mdpi.com/2076-3417/10/7/2511 |
| work_keys_str_mv | AT youngjoohan fabricdefectdetectionsystemusingstackedconvolutionaldenoisingautoencoderstrainedwithsyntheticdefectdata AT hajinyu fabricdefectdetectionsystemusingstackedconvolutionaldenoisingautoencoderstrainedwithsyntheticdefectdata |