Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM
Modern production lines for molded plastic parts often have automated inspection systems to detect defective parts reliably and efficiently. However, these conventional inspection systems have low flexibility and versatility, leading to difficulties when dealing with complicated requests such as whe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10050847/ |
| _version_ | 1811160951313924096 |
|---|---|
| author | Taiga Eguchi Wen Liang Yeoh Hiroshi Okumura Nobuhiko Yamaguchi Osamu Fukuda |
| author_facet | Taiga Eguchi Wen Liang Yeoh Hiroshi Okumura Nobuhiko Yamaguchi Osamu Fukuda |
| author_sort | Taiga Eguchi |
| collection | DOAJ |
| description | Modern production lines for molded plastic parts often have automated inspection systems to detect defective parts reliably and efficiently. However, these conventional inspection systems have low flexibility and versatility, leading to difficulties when dealing with complicated requests such as when small quantities of many different parts are manufactured on the same production line. The proposed system can be implemented quickly using low-cost off-the-shelf components and does not require accurate alignment of production parts, reducing the need for manual inspections and increasing work efficiency when handling complex workloads. The inspection algorithm combines higher-order local auto correlation (HLAC) features with one-class support vector machine (one-class SVM) and principal component analysis (PCA) to extract, transform, and classify the differential feature vector between conforming and nonconforming plastic parts. To verify its validity and effectiveness, we compared defect detection accuracy and speed between the developed inspection system and manual inspection experimentally. Extremely high accuracy (Recall = 0.93, Specificity = 1.00) and speed (10 inspections in 30[sec]) was obtained with 7 types (1 conforming type, 6 nonconforming types) of sample parts (30 samples each). We demonstrated a 400 % increase in speed can be gained relative to manual inspection. |
| first_indexed | 2024-04-10T06:06:23Z |
| format | Article |
| id | doaj.art-9da4f2694dc348f19a251ea36db3f4a2 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T06:06:23Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9da4f2694dc348f19a251ea36db3f4a22023-03-03T00:01:27ZengIEEEIEEE Access2169-35362023-01-0111195791959010.1109/ACCESS.2023.324823810050847Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVMTaiga Eguchi0https://orcid.org/0000-0002-3248-6418Wen Liang Yeoh1https://orcid.org/0000-0003-1272-9010Hiroshi Okumura2Nobuhiko Yamaguchi3https://orcid.org/0000-0001-6172-4238Osamu Fukuda4https://orcid.org/0000-0002-8022-7314Department of Information Science, Graduate School of Science and Engineering, Saga University, Saga, JapanDepartment of Information Science, Graduate School of Science and Engineering, Saga University, Saga, JapanDepartment of Information Science, Graduate School of Science and Engineering, Saga University, Saga, JapanDepartment of Information Science, Graduate School of Science and Engineering, Saga University, Saga, JapanDepartment of Information Science, Graduate School of Science and Engineering, Saga University, Saga, JapanModern production lines for molded plastic parts often have automated inspection systems to detect defective parts reliably and efficiently. However, these conventional inspection systems have low flexibility and versatility, leading to difficulties when dealing with complicated requests such as when small quantities of many different parts are manufactured on the same production line. The proposed system can be implemented quickly using low-cost off-the-shelf components and does not require accurate alignment of production parts, reducing the need for manual inspections and increasing work efficiency when handling complex workloads. The inspection algorithm combines higher-order local auto correlation (HLAC) features with one-class support vector machine (one-class SVM) and principal component analysis (PCA) to extract, transform, and classify the differential feature vector between conforming and nonconforming plastic parts. To verify its validity and effectiveness, we compared defect detection accuracy and speed between the developed inspection system and manual inspection experimentally. Extremely high accuracy (Recall = 0.93, Specificity = 1.00) and speed (10 inspections in 30[sec]) was obtained with 7 types (1 conforming type, 6 nonconforming types) of sample parts (30 samples each). We demonstrated a 400 % increase in speed can be gained relative to manual inspection.https://ieeexplore.ieee.org/document/10050847/Higher-order local auto-correlation featureinteractiveone-class support vector machineplastic partsrough alignmentvisual inspection |
| spellingShingle | Taiga Eguchi Wen Liang Yeoh Hiroshi Okumura Nobuhiko Yamaguchi Osamu Fukuda Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM IEEE Access Higher-order local auto-correlation feature interactive one-class support vector machine plastic parts rough alignment visual inspection |
| title | Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM |
| title_full | Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM |
| title_fullStr | Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM |
| title_full_unstemmed | Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM |
| title_short | Interactive Visual Inspection of a Rough-Alignment Plastic Part Based on HLAC Features and One-Class SVM |
| title_sort | interactive visual inspection of a rough alignment plastic part based on hlac features and one class svm |
| topic | Higher-order local auto-correlation feature interactive one-class support vector machine plastic parts rough alignment visual inspection |
| url | https://ieeexplore.ieee.org/document/10050847/ |
| work_keys_str_mv | AT taigaeguchi interactivevisualinspectionofaroughalignmentplasticpartbasedonhlacfeaturesandoneclasssvm AT wenliangyeoh interactivevisualinspectionofaroughalignmentplasticpartbasedonhlacfeaturesandoneclasssvm AT hiroshiokumura interactivevisualinspectionofaroughalignmentplasticpartbasedonhlacfeaturesandoneclasssvm AT nobuhikoyamaguchi interactivevisualinspectionofaroughalignmentplasticpartbasedonhlacfeaturesandoneclasssvm AT osamufukuda interactivevisualinspectionofaroughalignmentplasticpartbasedonhlacfeaturesandoneclasssvm |