Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images
dc.contributor.author | Schmitt, Thomas H. | |
dc.contributor.author | Bundscherer, Maximilian | |
dc.contributor.author | Bocklet, Tobias | |
dc.contributor.editor | Klein, Maike | |
dc.contributor.editor | Krupka, Daniel | |
dc.contributor.editor | Winter, Cornelia | |
dc.contributor.editor | Gergeleit, Martin | |
dc.contributor.editor | Martin, Ludger | |
dc.date.accessioned | 2024-10-21T18:24:16Z | |
dc.date.available | 2024-10-21T18:24:16Z | |
dc.date.issued | 2024 | |
dc.description.abstract | In the food industry, reprocessing returned products is a vital step to increase resource efficiency. [SBB23] presented an AI application that automates the tracking of returned bread buns. We extend their work by creating an expanded dataset comprising 2432 images and a wider range of baked goods. To increase model robustness, we use generative models pix2pix and CycleGAN to create synthetic images. We train state-of-the-art object detection models YOLOv9 and YOLOv8 on our detection task. Our overall best-performing model achieved an average precision AP 0.5 of 90.3% on our test set. | en |
dc.identifier.doi | 10.18420/inf2024_150 | |
dc.identifier.isbn | 978-3-88579-746-3 | |
dc.identifier.pissn | 1617-5468 | |
dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/45126 | |
dc.language.iso | en | |
dc.publisher | Gesellschaft für Informatik e.V. | |
dc.relation.ispartof | INFORMATIK 2024 | |
dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-352 | |
dc.subject | Schmitt | |
dc.subject | Thomas H. | |
dc.subject | Bundscherer | |
dc.subject | Maximilian | |
dc.subject | Bocklet | |
dc.subject | Tobias | |
dc.title | Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images | en |
dc.type | Text/Conference Paper | |
gi.citation.endPage | 1740 | |
gi.citation.publisherPlace | Bonn | |
gi.citation.startPage | 1731 | |
gi.conference.date | 24.-26. September 2024 | |
gi.conference.location | Wiesbaden | |
gi.conference.sessiontitle | Künstliche Intelligenz im Mittelstand / KI-KMU2024 |
Dateien
Originalbündel
1 - 1 von 1
Lade...
- Name:
- Schmitt_et_al_Training_a_Computer_Vision_Model.pdf
- Größe:
- 662.52 KB
- Format:
- Adobe Portable Document Format