Egg fertility assessment system using deep learning technology.
4 affiliations
- 1School of Mechatronics Engineering, College of IT Engineering, Gyeongsang National University, Jinju, Korea.
- 2HenTech, Jinju, Korea.
- 3Department of Automation Machine Maintenance, Suncheon Campus of Korea Polytechnics, Suncheon, Korea.
- 4Division of Animal Science, College of Agriculture and Life Science, Gyeongsang National University, Jinju, Korea.
Abstract
In the poultry industry, accurate distinction between fertilized, unfertilized, and hatching failure eggs is a key factor for improving hatching efficiency and reducing resource waste. This study comprehensively evaluated 12 CNN architectures for non-destructive egg fertility classification based on candling-style images captured on days 5-6 of incubation, under four experimental scenarios: Case A (image-level random split, three classes), Case B (egg-level separation, three classes), Case C (image-level random split, two classes), and Case D (egg-level separation, two classes). In Cases A and B, overall accuracy ranged from 93.65%-98.65% and 90.82%-95.79%, respectively. Per-class recall for fertilized eggs exceeded 98% across all models, while hatching failure egg recall was highly variable (5.88%-76.47% in Case A; 0%-27.78% in Case B), reflecting severe class imbalance and visual ambiguity. In Cases C and D (fertilized vs. unfertilized only), overall accuracy improved to 97.02%-99.80% and 95.84%-98.81%, respectively, with unfertilized egg recall ranging from 74.47%-97.87% (Case C) and 58.33%-87.50% (Case D). Egg-level evaluation (Cases B and D) consistently yielded lower accuracy than image-level splitting (Cases A and C), confirming that image-level splitting overestimates real-world generalization performance. CNN selection should be guided by the balance between computational resources and required accuracy: lightweight models (SqueezeNet: 4.7 MB; ShuffleNet: 5.5 MB) suit resource-constrained deployments, while larger models (Inception-v3, VGG-16, VGG-19) offer superior accuracy for high-performance applications. Classification of hatching failure eggs remains challenging due to their visual similarity to both fertilized and unfertilized eggs depending on the timing of developmental arrest, and represents an important direction for future research.
Related
- Automated assessment of the ulcerative colitis endoscopic index of severity using a multi-task deep learning model
- AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts.
- Monocular Deep Learning Pipeline for 3D Bird Collision Risk Assessment on Power Transmission Lines
- Deep learning-based assessment of ulcerative colitis activity from full-length endoscopic videos with spatial characterisation and histological correlation
- AgroXAI: a multi-XAI deep learning system for explainable multi-species plant disease classification
BibTeX
@article{park2026fertility,
title = {{Egg fertility assessment system using deep learning technology.}},
author = {Jin-Hyun Park and Sea Hwan Sohn and Hee-Mun Park and Sang-Hyon Oh},
journal = {Journal of animal science and technology},
year = {2026},
month = jul,
doi = {10.5187/jast.2600100},
url = {https://europepmc.org/article/MED/42898847},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Egg fertility assessment system using deep learning technology.
AU - Jin-Hyun Park
AU - Sea Hwan Sohn
AU - Hee-Mun Park
AU - Sang-Hyon Oh
PY - 2026
DA - 2026/07/31
JO - Journal of animal science and technology
DO - 10.5187/jast.2600100
UR - https://europepmc.org/article/MED/42898847
AB - In the poultry industry, accurate distinction between fertilized, unfertilized, and hatching failure eggs is a key factor for improving hatching efficiency and reducing resource waste. This study comprehensively evaluated 12 CNN architectures for non-destructive egg fertility classification based on candling-style images captured on days 5-6 of incubation, under four experimental scenarios: Case A (image-level random split, three classes), Case B (egg-level separation, three classes), Case C (image-level random split, two classes), and Case D (egg-level separation, two classes). In Cases A and B, overall accuracy ranged from 93.65%-98.65% and 90.82%-95.79%, respectively. Per-class recall for fertilized eggs exceeded 98% across all models, while hatching failure egg recall was highly variable (5.88%-76.47% in Case A; 0%-27.78% in Case B), reflecting severe class imbalance and visual ambiguity. In Cases C and D (fertilized vs. unfertilized only), overall accuracy improved to 97.02%-99.80% and 95.84%-98.81%, respectively, with unfertilized egg recall ranging from 74.47%-97.87% (Case C) and 58.33%-87.50% (Case D). Egg-level evaluation (Cases B and D) consistently yielded lower accuracy than image-level splitting (Cases A and C), confirming that image-level splitting overestimates real-world generalization performance. CNN selection should be guided by the balance between computational resources and required accuracy: lightweight models (SqueezeNet: 4.7 MB; ShuffleNet: 5.5 MB) suit resource-constrained deployments, while larger models (Inception-v3, VGG-16, VGG-19) offer superior accuracy for high-performance applications. Classification of hatching failure eggs remains challenging due to their visual similarity to both fertilized and unfertilized eggs depending on the timing of developmental arrest, and represents an important direction for future research.
SN - 2055-0391
ER -