Deep Learning Methods for Automatic Identification of Male and Female Chickens in a Cage-Free Flock
Rooster behavior and activity are critical for egg fertility and hatchability in broiler and layer breeder houses. Desirable roosters are expected to have good leg health, reach sexual maturity, be productive, and show less aggression toward females during mating. However, not all roosters are desir...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/15/13/1862 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Rooster behavior and activity are critical for egg fertility and hatchability in broiler and layer breeder houses. Desirable roosters are expected to have good leg health, reach sexual maturity, be productive, and show less aggression toward females during mating. However, not all roosters are desirable, and low-productive roosters should be removed and replaced. The objectives of this study were to apply an object detection model based on deep learning to identify hens and roosters based on phenotypic characteristics, such as comb size and body size, in a cage-free (CF) environment, and to compare the performance metrics among the applied models. Six roosters were mixed with 200 Lohmann LSL Lite hens during the pre-peak phase in a CF research facility and were marked with different identifications. Deep learning methods, such as You Only Look Once (YOLO) models, were innovated and trained (based on a comb size of up to 2500 images) for the identification of male and female chickens based on comb size and body features. The performance matrices of the YOLOv5u and YOLOv11 models, including precision, recall, mean average precision (mAP), and F1 score, were statistically compared for hen and rooster detection using a one-way ANOVA test at a significance level of <i>p</i> < 0.05. For rooster detection based on comb size, YOLOv5lu, and YOLOv11x variants performed the best among the five variants of each model, with YOLOv5lu achieving a precision of 87.7%, recall of 56.3%, and mAP@0.50 of 60.1%, while YOLOv11x achieved a precision of 86.7%, recall of 65.3%, and mAP@0.50 of 61%. For rooster detection based on body size, YOLOv5xu, and YOLOv11m outperformed other variants, with YOLOv5xu achieving a precision of 88.9%, recall of 77.7%, and mAP@0.50 of 82.3%, while YOLOv11m achieved a precision of 89.0%, recall of 78.8%, and mAP@0.50 of 82.6%. This study provides a reference for automatic rooster monitoring based on comb and body size and offers further opportunities for tracking the activities of roosters in a poultry breeder farm for performance evaluation and genetic selection in the future. |
|---|---|
| ISSN: | 2076-2615 |