What question did this study set out to answer?

To establish and benchmark an automated deep learning framework using lightweight YOLO models for wheat-seed detection and counting from standard RGB images.

September 17, 2026International Journal of Applied and Experimental BiologyOpen Access

Deep learning-based detection and counting of wheat seeds: Comparative benchmarking of YOLO models

View Full Paper

Ask AI

Bookmark

Authors

FSFaisal Shahzad HAHafiza Ayesha Arshad HAHabib‐ur‐Rehman Athar

Discussion

Member takes

Overview

Comparative study demonstrates high-accuracy detection and counting of wheat seeds using lightweight YOLO architectures, indicating strong potential for automated plant phenotyping.

Key Points

To establish and benchmark an automated deep learning framework using lightweight YOLO models for wheat-seed detection and counting from standard RGB images.
Created an image dataset containing 832 RGB images and 3,649 manually annotated wheat-seed bounding boxes, representing one to ten seeds per image.
Trained and evaluated two lightweight single-class object detection models, YOLOv8n and YOLO11n, under identical experimental parameters.
Evaluated model outcomes using precision, recall, mAP@0.5, mAP@0.5:0.95, loss curves, and confusion matrices.
YOLOv8n achieved a precision of 0.9947, recall of 0.9963, mAP@0.5 of 0.9940, and mAP@0.5:0.95 of 0.5284.
YOLO11n outperformed YOLOv8n across all evaluation metrics, achieving a precision of 0.9988, recall of 0.9984, mAP@0.5 of 0.9950, and mAP@0.5:0.95 of 0.5385.

Cite This Study

Shahzad et al. (2026) studied this question.

synapsesocial.com/papers/6aabb61e5f706d05830e498e https://doi.org/10.56612/ijaaeb.v6i1.249

View Full Paper

Ask AI

Bookmark

September 17, 2026International Journal of Applied and Experimental BiologyOpen Access

Deep learning-based detection and counting of wheat seeds: Comparative benchmarking of YOLO models

View Full Paper

Ask AI

Bookmark

Authors

FSFaisal Shahzad HAHafiza Ayesha Arshad HAHabib‐ur‐Rehman Athar

Discussion

Member takes

Overview

Comparative study demonstrates high-accuracy detection and counting of wheat seeds using lightweight YOLO architectures, indicating strong potential for automated plant phenotyping.

Key Points

To establish and benchmark an automated deep learning framework using lightweight YOLO models for wheat-seed detection and counting from standard RGB images.
Created an image dataset containing 832 RGB images and 3,649 manually annotated wheat-seed bounding boxes, representing one to ten seeds per image.
Trained and evaluated two lightweight single-class object detection models, YOLOv8n and YOLO11n, under identical experimental parameters.
Evaluated model outcomes using precision, recall, mAP@0.5, mAP@0.5:0.95, loss curves, and confusion matrices.
YOLOv8n achieved a precision of 0.9947, recall of 0.9963, mAP@0.5 of 0.9940, and mAP@0.5:0.95 of 0.5284.
YOLO11n outperformed YOLOv8n across all evaluation metrics, achieving a precision of 0.9988, recall of 0.9984, mAP@0.5 of 0.9950, and mAP@0.5:0.95 of 0.5385.

Cite This Study

Shahzad et al. (2026) studied this question.

synapsesocial.com/papers/6aabb61e5f706d05830e498e https://doi.org/10.56612/ijaaeb.v6i1.249

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark