Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images
- In the food industry, reprocessing returned product 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 model 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.
| Author: | Thomas Schmitt, Maximilian Bundscherer, Tobias BockletORCiD |
|---|---|
| DOI: | https://doi.org/10.48550/arXiv.2409.20122 |
| ArXiv Id: | http://arxiv.org/abs/2409.20122v1 |
| Document Type: | Article |
| Language: | English |
| Date of first Publication: | 2024/09/30 |
| Release Date: | 2024/10/17 |
| Tag: | machine learning, object detection, YOLOv9, image composition, baked goods, food industry, industrial automation |
| Pagenumber: | 10 |
| Konferenzangabe: | FZI Workshop - Künstliche Intelligenz im Mittelstand (KI-KMU 2024) |
| institutes: | Zentrum für Künstliche Intelligenz (KIZ) |
| Research Themes: | Digitalisierung & Künstliche Intelligenz |
| Licence (German): | Creative Commons - CC BY-NC-SA - Namensnennung - Nicht kommerziell - Weitergabe unter gleichen Bedingungen 4.0 International |

