Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model
As an important export, cleanliness control on edible bird’s nest (EBN) is paramount. Automatic impurities detection is in urgent need to replace manual practices. However, effective impurities detection algorithm is yet to be developed due to the unresolved inhomogeneous optical properties of EBN....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taiwan Association of Engineering and Technology Innovation
2021-04-01
|
| Series: | International Journal of Engineering and Technology Innovation |
| Subjects: | |
| Online Access: | https://ojs.imeti.org/index.php/IJETI/article/view/6891 |
| _version_ | 1797808622098448384 |
|---|---|
| author | Ying-Heng Yeo Kin-Sam Yen |
| author_facet | Ying-Heng Yeo Kin-Sam Yen |
| author_sort | Ying-Heng Yeo |
| collection | DOAJ |
| description |
As an important export, cleanliness control on edible bird’s nest (EBN) is paramount. Automatic impurities detection is in urgent need to replace manual practices. However, effective impurities detection algorithm is yet to be developed due to the unresolved inhomogeneous optical properties of EBN. The objective of this work is to develop a novel U-net based algorithm for accurate impurities detection. The algorithm leveraged the convolution mechanisms of U-net for precise and localized features extraction. Output probability tensors were then generated from the deconvolution layers for impurities detection and positioning. The U-net based algorithm outperformed previous image processing-based methods with a higher impurities detection rate of 96.69% and a lower misclassification rate of 10.08%. The applicability of the algorithm was further confirmed with a reasonably high dice coefficient of more than 0.8. In conclusion, the developed U-net based algorithm successfully mitigated intensity inhomogeneity in EBN and improved the impurities detection rate.
|
| first_indexed | 2024-03-13T06:40:22Z |
| format | Article |
| id | doaj.art-9967c1f9762b417c9ad3d9066d1414f3 |
| institution | Directory Open Access Journal |
| issn | 2223-5329 2226-809X |
| language | English |
| last_indexed | 2024-03-13T06:40:22Z |
| publishDate | 2021-04-01 |
| publisher | Taiwan Association of Engineering and Technology Innovation |
| record_format | Article |
| series | International Journal of Engineering and Technology Innovation |
| spelling | doaj.art-9967c1f9762b417c9ad3d9066d1414f32023-06-08T18:19:07ZengTaiwan Association of Engineering and Technology InnovationInternational Journal of Engineering and Technology Innovation2223-53292226-809X2021-04-0111210.46604/ijeti.2021.6891Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning ModelYing-Heng Yeo0Kin-Sam Yen1School of Mechanical Engineering, Universiti Sains Malaysia, Penang, MalaysiaSchool of Mechanical Engineering, Universiti Sains Malaysia, Penang, Malaysia As an important export, cleanliness control on edible bird’s nest (EBN) is paramount. Automatic impurities detection is in urgent need to replace manual practices. However, effective impurities detection algorithm is yet to be developed due to the unresolved inhomogeneous optical properties of EBN. The objective of this work is to develop a novel U-net based algorithm for accurate impurities detection. The algorithm leveraged the convolution mechanisms of U-net for precise and localized features extraction. Output probability tensors were then generated from the deconvolution layers for impurities detection and positioning. The U-net based algorithm outperformed previous image processing-based methods with a higher impurities detection rate of 96.69% and a lower misclassification rate of 10.08%. The applicability of the algorithm was further confirmed with a reasonably high dice coefficient of more than 0.8. In conclusion, the developed U-net based algorithm successfully mitigated intensity inhomogeneity in EBN and improved the impurities detection rate. https://ojs.imeti.org/index.php/IJETI/article/view/6891edible bird’s nestimpurities detectionintensity inhomogeneityU-netmachine vision |
| spellingShingle | Ying-Heng Yeo Kin-Sam Yen Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model International Journal of Engineering and Technology Innovation edible bird’s nest impurities detection intensity inhomogeneity U-net machine vision |
| title | Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model |
| title_full | Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model |
| title_fullStr | Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model |
| title_full_unstemmed | Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model |
| title_short | Impurities Detection in Intensity Inhomogeneous Edible Bird’s Nest (EBN) Using a U-Net Deep Learning Model |
| title_sort | impurities detection in intensity inhomogeneous edible bird s nest ebn using a u net deep learning model |
| topic | edible bird’s nest impurities detection intensity inhomogeneity U-net machine vision |
| url | https://ojs.imeti.org/index.php/IJETI/article/view/6891 |
| work_keys_str_mv | AT yinghengyeo impuritiesdetectioninintensityinhomogeneousediblebirdsnestebnusingaunetdeeplearningmodel AT kinsamyen impuritiesdetectioninintensityinhomogeneousediblebirdsnestebnusingaunetdeeplearningmodel |