Home / Current Issue / Paper 1714986
AI-Based Poultry Disease Detection Using Fecal Image Classification with EfficientNetV2
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence and Machine Learning
Abstract
In this paper, an AI-based poultry disease detection system is presented using fecal image classification. Four poultry health conditions, such as Coccidiosis, Healthy, Newcastle Disease, and Salmonella, are classified using the transfer learning method with EfficientNetV2B0. In the experiment, the model achieved an approximate 98 percent accuracy with high precision and recall values for the classes. The proposed system is beneficial to the farming community as it is cost-effective and allows the detection of poultry diseases in their early stages. Farmers can use the proposed system to diagnose their poultry diseases by uploading the images of their feces into the proposed system.
Keywords
Deep Learning, EfficientNetV2, Poultry Disease Detection, Transfer Learning, Image Classification
References
[1] D. Machuve, E. Nwankwo, N. Mduma, and J. Mbelwa, “Poultry diseases diagnostics models using deep learning,” Frontiers in Artificial Intelligence, vol. 5, pp. 733345, 2022.
[2] K. K. Yogi and S. P. Yadav, “Chicken diseases detection and classification based on fecal images using EfficientNetB7 model,” in Proc. Conference Paper, 2024.
[3] M. Zhou, J. Zhu, Z. Cui, H. Wang, and X. Sun, “Detection of abnormal chicken droppings based on improved Faster R-CNN,” International Journal of Agricultural and Biological Engineering, vol. 16, no. 1, pp. 243–249, 2023.
[4] A. Tasdelen and Y. Arslan, “Detection of high-risk diseases in poultry feces through transfer learning,” Engineering Science and Technology, an International Journal, vol. 64, p. 102002, 2025.
[5] B. S. Akbudak, “Disease detection from chicken feces on a mobile platform using deep learning methods,” Young Scientist Research, vol. 6, no. 1, pp. 17–23, 2022.
[6] M. Z. Degu and G. L. Simegn, “Smartphone based detection and classification of poultry diseases from chicken fecal images using deep learning techniques,” Smart Agricultural Technology, vol. 4, p. 100221, 2023.
[7] H. K. Joy, N. Sandhyana, and M. R. Kounte, “Advanced poultry disease detection with deep convolutional neural networks,” in Proc. ICTACS, IEEE, 2024.
[8] G. Li, R. S. Gates, and B. C. Ramirez, “An on-site feces image classifier system for chicken health assessment: A proof of concept,” Applied Engineering in Agriculture, vol. 39, no. 4, pp. 417–426, 2023.
How to cite this paper
@article{1714986,
author = {Naren TNJ, Anjali K, Sandesh S, Ajaykumar B},
title = {AI-Based Poultry Disease Detection Using Fecal Image Classification with EfficientNetV2},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {9},
pages = {897-901},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1714986.pdf},
abstract = {In this paper, an AI-based poultry disease detection system is presented using fecal image classification. Four poultry health conditions, such as Coccidiosis, Healthy, Newcastle Disease, and Salmonella, are classified using the transfer learning method with EfficientNetV2B0. In the experiment, the model achieved an approximate 98 percent accuracy with high precision and recall values for the classes. The proposed system is beneficial to the farming community as it is cost-effective and allows the detection of poultry diseases in their early stages. Farmers can use the proposed system to diagnose their poultry diseases by uploading the images of their feces into the proposed system.},
keywords = {Deep Learning, EfficientNetV2, Poultry Disease Detection, Transfer Learning, Image Classification},
month = {March},
doi = {https://doi.org/10.64388/IREV9I9-1714986}
}