Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads.
Thesis (MEng)--Stellenbosch University, 2023.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614077846552576 |
|---|---|
| access_status_str | Open Access |
| author | Kleyn, Riaan |
| author2 | Von Leipzig, Konrad |
| author_browse | Kleyn, Riaan Von Leipzig, Konrad |
| author_facet | Von Leipzig, Konrad Kleyn, Riaan |
| author_sort | Kleyn, Riaan |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MEng)--Stellenbosch University, 2023. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/128996 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA en_ZA |
| last_indexed | 2026-06-10T12:46:18.613Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/128996 An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. Kleyn, Riaan Von Leipzig, Konrad Palm, Daniel Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Engineering Management (MEM). Computer vision Grapes -- Harvesting -- Machinery Wine industry -- Automation Matter other than grapes (MOG) Deep learning (Machine learning) Thesis (MEng)--Stellenbosch University, 2023. ENGLISH ABSTRACT: Mass wine production companies across the globe are provided with grapes from winegrowers that predominantly utilise mechanical harvesting machines to harvest wine grapes. Mechanical harvesting accelerates the rate at which grapes are harvested, allowing grapes to be delivered faster to meet the demands of wine cellars. The disadvantage of the mechanical harvesting method is the inclusion of material-other-than-grapes (MOG) in the harvested wine grape loads arriving at the cellar. The MOG degrades the quality of wine that can be produced while it is also costly to transport and discard and it can cause machine downtime. This paper seeks to find an optimal computer vision method capable of detecting the amount of MOG within a wine grape load. A MOG detection method will encourage winegrowers to deliver MOG-free wine grape loads to avoid penalties which will indirectly enhance the quality of the wine to be produced. Traditional image segmentation methods were compared to deep learning segmentation methods based on images of wine grape loads that were captured at a wine cellar. The Mask R-CNN model with a ResNet-50 convolutional neural network backbone emerged as the optimal method for this study to determine the amount of MOG in an image of a wine grape load. Furthermore, a statistical analysis was conducted to determine how the MOG on the surface of a grape load relates to the mass of MOG within the corresponding grape load. AFRIKAANSE OPSOMMING: Massawynproduksie maatskappye regoor die wêreld word voorsien van druiwe van wynboere wat hoofsaaklik meganiese oesmasjiene gebruik om wyndruiwe te oes. Meganiese oesmetodes versnel die tempo waarteen druiwe geoes word sodat druiwe vinniger aan wynkelders gelewer kan word om aan hul vereistes te voldoen. Die nadeel van die meganiese oesmetode is die insluiting van materiaal anders as druiwe (MOG) in die geoesde wyndruif vragte wat by die kelder aankom. Die MOG verswak die kwaliteit van wyn wat geproduseer kan word, terwyl dit ook duur is om te vervoer en weg te gooi en dit kan veroorsaak dat die masjiene tot stilstand kom. Hierdie navorsing poog om ’n optimale rekenaarvisiemetode te vind wat die hoeveelheid MOG binne ’n vrag wyndruiwe kan identifiseer. ’n MOG-identifiseringsmetode sal wynboere aan- moedig om MOG-vrye wyndruifvragte aan wynkelders te lewer om sodoende boetes te vermy wat indirek die kwaliteit van die wyn wat geproduseer kan word, sal verbeter. Tradisionele beeldsegmenteringsmetodes is vergelyk met diepleersegmenteringsmetodes gebaseer op beelde van wyndruifvragte wat by ’n wynkelder vasgevang is. Die Mask R-CNN model met ’n ResNet- 50 konvolusionele neurale netwerk ruggraat het na vore gekom as die optimale metode vir hierdie studie om die hoeveelheid MOG in ’n beeld van ’n wyndruiflading te bepaal. Verder is ’n statistiese analise uitgevoer om te bepaal hoe die MOG op die oppervlak van ’n druiwelading verband hou met die massa van die MOG binne in die ooreenstemmende druiflading. Masters 2023-11-13T15:16:19Z 2024-01-08T18:37:14Z 2023-11-13T15:16:19Z 2024-01-08T18:37:14Z 2023-12 Thesis https://scholar.sun.ac.za/handle/10019.1/128996 en_ZA en_ZA Stellenbosch University xx, 108 pages : illustrations application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Computer vision Grapes -- Harvesting -- Machinery Wine industry -- Automation Matter other than grapes (MOG) Deep learning (Machine learning) Kleyn, Riaan An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. |
| title | An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. |
| title_full | An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. |
| title_fullStr | An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. |
| title_full_unstemmed | An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. |
| title_short | An investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads. |
| title_sort | investigation into computer vision methods to identify material other than grapes in harvested red wine grape loads |
| topic | Computer vision Grapes -- Harvesting -- Machinery Wine industry -- Automation Matter other than grapes (MOG) Deep learning (Machine learning) |
| url | https://scholar.sun.ac.za/handle/10019.1/128996 |
| work_keys_str_mv | AT kleynriaan aninvestigationintocomputervisionmethodstoidentifymaterialotherthangrapesinharvestedredwinegrapeloads AT kleynriaan investigationintocomputervisionmethodstoidentifymaterialotherthangrapesinharvestedredwinegrapeloads |