A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification
Defect inspection is an important issue in the field of industrial automation. In general, defect-inspection methods can be categorized into supervised and unsupervised methods. When supervised learning is applied to defect inspection, the large variation of defect patterns can make the data coverag...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/4/1883 |
| _version_ | 1797483099601240064 |
|---|---|
| author | Cheng-Chang Lien Yu-De Chiu |
| author_facet | Cheng-Chang Lien Yu-De Chiu |
| author_sort | Cheng-Chang Lien |
| collection | DOAJ |
| description | Defect inspection is an important issue in the field of industrial automation. In general, defect-inspection methods can be categorized into supervised and unsupervised methods. When supervised learning is applied to defect inspection, the large variation of defect patterns can make the data coverage incomplete for model training, which can introduce the problem of low detection accuracy. Therefore, this paper focuses on the construction of a defect-inspection system with an unsupervised learning model. Furthermore, few studies have focused on the analysis between the reconstruction error on the normal areas and the repair effect on the defective areas for unsupervised defect-inspection systems. Hence, this paper addresses this important issue. There are four main contributions to this paper. First, we compare the effects of SSIM (Structural Similarity Index Measure) and MSE (Mean Square Error) functions on the reconstruction error. Second, various kinds of Autoencoders are constructed by referring to the Inception architecture in GoogleNet and DEC (Deep Embedded Clustering) module. Third, two-stage model training is proposed to train the Autoencoder models. In the first stage, the Autoencoder models are trained to have basic image-reconstruction capabilities for the normal areas. In the second stage, the DEC algorithm is added to the training of the Autoencoder model to further strengthen feature discrimination and then increase the capability to repair defective areas. Fourth, the multi-thresholding image segmentation method is applied to improve the classification accuracy of normal and defect images. In this study, we focus on the defect inspection on the texture patterns. Therefore, we select the nanofiber image database and carpet and grid images in the MVTec database to conduct experiments. The experimental results show that the accuracy of classifying normal and defect patch nanofiber images is about 86% and the classification accuracy can approach 89% and 98% for carpet and grid datasets in the MVTec database, respectively. It is obvious that our proposed defect-inspection and classification system outperforms the methods in MVTec. |
| first_indexed | 2024-03-09T22:43:03Z |
| format | Article |
| id | doaj.art-e9b8e179bb5f407f90809c74f7398dbc |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:43:03Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e9b8e179bb5f407f90809c74f7398dbc2023-11-23T18:35:40ZengMDPI AGApplied Sciences2076-34172022-02-01124188310.3390/app12041883A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding ClassificationCheng-Chang Lien0Yu-De Chiu1Department of Computer Science & Information Engineering, Chung Hua University, Hsinchu 30012, TaiwanDepartment of Computer Science & Information Engineering, Chung Hua University, Hsinchu 30012, TaiwanDefect inspection is an important issue in the field of industrial automation. In general, defect-inspection methods can be categorized into supervised and unsupervised methods. When supervised learning is applied to defect inspection, the large variation of defect patterns can make the data coverage incomplete for model training, which can introduce the problem of low detection accuracy. Therefore, this paper focuses on the construction of a defect-inspection system with an unsupervised learning model. Furthermore, few studies have focused on the analysis between the reconstruction error on the normal areas and the repair effect on the defective areas for unsupervised defect-inspection systems. Hence, this paper addresses this important issue. There are four main contributions to this paper. First, we compare the effects of SSIM (Structural Similarity Index Measure) and MSE (Mean Square Error) functions on the reconstruction error. Second, various kinds of Autoencoders are constructed by referring to the Inception architecture in GoogleNet and DEC (Deep Embedded Clustering) module. Third, two-stage model training is proposed to train the Autoencoder models. In the first stage, the Autoencoder models are trained to have basic image-reconstruction capabilities for the normal areas. In the second stage, the DEC algorithm is added to the training of the Autoencoder model to further strengthen feature discrimination and then increase the capability to repair defective areas. Fourth, the multi-thresholding image segmentation method is applied to improve the classification accuracy of normal and defect images. In this study, we focus on the defect inspection on the texture patterns. Therefore, we select the nanofiber image database and carpet and grid images in the MVTec database to conduct experiments. The experimental results show that the accuracy of classifying normal and defect patch nanofiber images is about 86% and the classification accuracy can approach 89% and 98% for carpet and grid datasets in the MVTec database, respectively. It is obvious that our proposed defect-inspection and classification system outperforms the methods in MVTec.https://www.mdpi.com/2076-3417/12/4/1883defect inspectionautoencoderSSIMDEC clustering algorithm |
| spellingShingle | Cheng-Chang Lien Yu-De Chiu A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification Applied Sciences defect inspection autoencoder SSIM DEC clustering algorithm |
| title | A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification |
| title_full | A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification |
| title_fullStr | A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification |
| title_full_unstemmed | A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification |
| title_short | A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification |
| title_sort | defect inspection system constructed by applying autoencoder with clustered latent vectors and multi thresholding classification |
| topic | defect inspection autoencoder SSIM DEC clustering algorithm |
| url | https://www.mdpi.com/2076-3417/12/4/1883 |
| work_keys_str_mv | AT chengchanglien adefectinspectionsystemconstructedbyapplyingautoencoderwithclusteredlatentvectorsandmultithresholdingclassification AT yudechiu adefectinspectionsystemconstructedbyapplyingautoencoderwithclusteredlatentvectorsandmultithresholdingclassification AT chengchanglien defectinspectionsystemconstructedbyapplyingautoencoderwithclusteredlatentvectorsandmultithresholdingclassification AT yudechiu defectinspectionsystemconstructedbyapplyingautoencoderwithclusteredlatentvectorsandmultithresholdingclassification |