A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles
The number of defect samples on the surface of aluminum profiles is small, and the distribution of abnormal visual features is dispersed, such that the existing supervised detection methods cannot effectively detect undefined defects. At the same time, the normal texture of the aluminum profile surf...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/14/1/386 |
_version_ | 1797359045635473408 |
---|---|
author | Shancheng Tang Ying Zhang Zicheng Jin Jianhui Lu Heng Li Jiqing Yang |
author_facet | Shancheng Tang Ying Zhang Zicheng Jin Jianhui Lu Heng Li Jiqing Yang |
author_sort | Shancheng Tang |
collection | DOAJ |
description | The number of defect samples on the surface of aluminum profiles is small, and the distribution of abnormal visual features is dispersed, such that the existing supervised detection methods cannot effectively detect undefined defects. At the same time, the normal texture of the aluminum profile surface presents non-uniform and non-periodic features, and this irregular distribution makes it difficult for classical reconstruction networks to accurately reconstruct the normal features, resulting in low performance of related unsupervised detection methods. Aiming at such problems, a feature-oriented reconstruction method of unsupervised surface-defect detection method for aluminum profiles is proposed. The aluminum profile image preprocessing stage uses techniques such as boundary extraction, background removal, and data normalization to process the original image and extract the image of the main part of the aluminum profile, which reduces the influence of irrelevant data features on the algorithm. The essential features learning stage precedes the feature-optimization module to eliminate the texture interference of the irregular distribution of the aluminum profile surface, and image blocks of the area images are reconstructed one by one to extract the features through the mask. The defect-detection stage compares the structural similarity of the feature images before and after the reconstruction, and comprehensively determines the detection results. The experimental results improve detection precision by 1.4% and the <i>F</i>1 value by 1.2% over the existing unsupervised methods, proving the effectiveness and superiority of the proposed method. |
first_indexed | 2024-03-08T15:10:57Z |
format | Article |
id | doaj.art-04f723c5714c40ac86c42b79ea28ee89 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-08T15:10:57Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-04f723c5714c40ac86c42b79ea28ee892024-01-10T14:51:57ZengMDPI AGApplied Sciences2076-34172023-12-0114138610.3390/app14010386A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum ProfilesShancheng Tang0Ying Zhang1Zicheng Jin2Jianhui Lu3Heng Li4Jiqing Yang5College of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaThe number of defect samples on the surface of aluminum profiles is small, and the distribution of abnormal visual features is dispersed, such that the existing supervised detection methods cannot effectively detect undefined defects. At the same time, the normal texture of the aluminum profile surface presents non-uniform and non-periodic features, and this irregular distribution makes it difficult for classical reconstruction networks to accurately reconstruct the normal features, resulting in low performance of related unsupervised detection methods. Aiming at such problems, a feature-oriented reconstruction method of unsupervised surface-defect detection method for aluminum profiles is proposed. The aluminum profile image preprocessing stage uses techniques such as boundary extraction, background removal, and data normalization to process the original image and extract the image of the main part of the aluminum profile, which reduces the influence of irrelevant data features on the algorithm. The essential features learning stage precedes the feature-optimization module to eliminate the texture interference of the irregular distribution of the aluminum profile surface, and image blocks of the area images are reconstructed one by one to extract the features through the mask. The defect-detection stage compares the structural similarity of the feature images before and after the reconstruction, and comprehensively determines the detection results. The experimental results improve detection precision by 1.4% and the <i>F</i>1 value by 1.2% over the existing unsupervised methods, proving the effectiveness and superiority of the proposed method.https://www.mdpi.com/2076-3417/14/1/386defect detectionaluminum profileunsupervised learningcomplex texture processing |
spellingShingle | Shancheng Tang Ying Zhang Zicheng Jin Jianhui Lu Heng Li Jiqing Yang A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles Applied Sciences defect detection aluminum profile unsupervised learning complex texture processing |
title | A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles |
title_full | A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles |
title_fullStr | A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles |
title_full_unstemmed | A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles |
title_short | A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles |
title_sort | feature oriented reconstruction method for surface defect detection on aluminum profiles |
topic | defect detection aluminum profile unsupervised learning complex texture processing |
url | https://www.mdpi.com/2076-3417/14/1/386 |
work_keys_str_mv | AT shanchengtang afeatureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT yingzhang afeatureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT zichengjin afeatureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT jianhuilu afeatureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT hengli afeatureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT jiqingyang afeatureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT shanchengtang featureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT yingzhang featureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT zichengjin featureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT jianhuilu featureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT hengli featureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles AT jiqingyang featureorientedreconstructionmethodforsurfacedefectdetectiononaluminumprofiles |