| Title: | OPTIFARM: Benchmarking YOLO architectures for location-robust potato quality detection |
|---|
| Authors: | ID Peršak, Tadej (Author)
ID Simonič, Marko (Author)
ID Hernavs, Jernej (Author)
ID Ficko, Mirko (Author)
ID Klančnik, Simon (Author) |
|---|
| Files: |  https://www.mdpi.com/2304-8158/15/12/2121
 foods-15-02121.pdf (3,85 MB)
MD5: C59C3D5200DDDBD60BFA4A0A823A682D
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FS - Faculty of Mechanical Engineering
|
|---|
| Abstract: | Potato sorting in post-harvest processing relies heavily on manual visual inspection, which is physically demanding, subjective, and insufficiently scalable for modern packing lines. This study investigates the feasibility of a low-cost RGB-based optical inspection system for automated potato quality detection using deep learning-based object detection. A controlled imaging platform was constructed using commodity hardware, and a dataset of 19,805 manually annotated instances across 1361 images was collected from two geographically distinct farm locations in Slovenia. A systematic benchmark of 25 model configurations spanning five YOLO architecture families—YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLO26—was conducted across three practical quality classes (Edible, Feed, Rotten) using a strict cross-location evaluation protocol in which models were trained on one location and tested on a completely unseen second location. All models achieved strong in-distribution performance (F1 ≥ 0.906), but showed considerable variation under cross-location conditions, with external F1 ranging from 0.792 to 0.918. The yolo26_l configuration achieved the best cross-location performance (F1 = 0.918, mAP@0.5:0.95 = 0.816, ΔF1 = 0.029), demonstrating that transferable representations are achievable under a standard supervised training protocol. Per-class analysis identified feed detection as the primary generalization bottleneck. The results confirm that affordable RGB-based sorting systems are technically feasible and highlight cross-location evaluation as an essential protocol for assessing real-world deployment readiness. |
|---|
| Keywords: | potato sorting, object detection, YOLO, cross-location generalization, food quality and safety, intelligent inspection, non-destructive testing |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 05.05.2026 |
|---|
| Article acceptance date: | 10.06.2026 |
|---|
| Publication date: | 12.06.2026 |
|---|
| Publisher: | MDPI |
|---|
| Year of publishing: | 2026 |
|---|
| Number of pages: | 29 str. |
|---|
| Numbering: | Vol. 15, iss. 12, [article no.] 2121 |
|---|
| PID: | 20.500.12556/DKUM-98499  |
|---|
| UDC: | 681.5:004.9 |
|---|
| ISSN on article: | 2304-8158 |
|---|
| COBISS.SI-ID: | 281687811 |
|---|
| DOI: | 10.3390/foods15122121 |
|---|
| Publication date in DKUM: | 17.06.2026 |
|---|
| Views: | 228 |
|---|
| Downloads: | 6 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
