Fresnel lens defect classification using deep learning technique
Plastic injection molded Fresnel lens is one of the important components for illumination in smart devices. To perform inspection on this type of optical component is challenging for machine vision due to the presence of groove pattern and texture. This paper discusses the limitation of classical im...
| Main Authors: | , , |
|---|---|
| Format: | Book Section |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Subjects: |
| _version_ | 1796866889957244928 |
|---|---|
| author | Loo, Kean Li Saw, Chong Keat Ibrahim, M. H. |
| author_facet | Loo, Kean Li Saw, Chong Keat Ibrahim, M. H. |
| author_sort | Loo, Kean Li |
| collection | ePrints |
| description | Plastic injection molded Fresnel lens is one of the important components for illumination in smart devices. To perform inspection on this type of optical component is challenging for machine vision due to the presence of groove pattern and texture. This paper discusses the limitation of classical image analysis for defect inspection and proposes a Deep Convolutional Neural Network (CNN) with Transfer Learning for defect classification. This paper also presents a Hybrid CycleGAN and geometric augmentation to expand image dataset for model training. |
| first_indexed | 2024-03-05T21:18:57Z |
| format | Book Section |
| id | utm.eprints-100489 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T21:18:57Z |
| publishDate | 2022 |
| publisher | Springer Science and Business Media Deutschland GmbH |
| record_format | dspace |
| spelling | utm.eprints-1004892023-04-14T02:13:49Z http://eprints.utm.my/100489/ Fresnel lens defect classification using deep learning technique Loo, Kean Li Saw, Chong Keat Ibrahim, M. H. TK Electrical engineering. Electronics Nuclear engineering Plastic injection molded Fresnel lens is one of the important components for illumination in smart devices. To perform inspection on this type of optical component is challenging for machine vision due to the presence of groove pattern and texture. This paper discusses the limitation of classical image analysis for defect inspection and proposes a Deep Convolutional Neural Network (CNN) with Transfer Learning for defect classification. This paper also presents a Hybrid CycleGAN and geometric augmentation to expand image dataset for model training. Springer Science and Business Media Deutschland GmbH 2022 Book Section PeerReviewed Loo, Kean Li and Saw, Chong Keat and Ibrahim, M. H. (2022) Fresnel lens defect classification using deep learning technique. In: Proceedings of the 8th International Conference on Computational Science and Technology ICCST 2021, Labuan, Malaysia, 28–29 August. Lecture Notes in Electrical Engineering, 835 (NA). Springer Science and Business Media Deutschland GmbH, Singapore, pp. 547-561. ISBN 978-981168514-9 http://dx.doi.org/10.1007/978-981-16-8515-6_42 DOI:10.1007/978-981-16-8515-6_42 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Loo, Kean Li Saw, Chong Keat Ibrahim, M. H. Fresnel lens defect classification using deep learning technique |
| title | Fresnel lens defect classification using deep learning technique |
| title_full | Fresnel lens defect classification using deep learning technique |
| title_fullStr | Fresnel lens defect classification using deep learning technique |
| title_full_unstemmed | Fresnel lens defect classification using deep learning technique |
| title_short | Fresnel lens defect classification using deep learning technique |
| title_sort | fresnel lens defect classification using deep learning technique |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| work_keys_str_mv | AT lookeanli fresnellensdefectclassificationusingdeeplearningtechnique AT sawchongkeat fresnellensdefectclassificationusingdeeplearningtechnique AT ibrahimmh fresnellensdefectclassificationusingdeeplearningtechnique |