Lightweight Model for Poultry Disease Detection from Fecal Images Using Multi-Color Space Feature Optimization and Machine Learning

TL;DR

This paper presents a lightweight machine learning approach using multi-color space features for accurate and resource-efficient poultry disease detection from fecal images, suitable for low-resource settings.

Contribution

The study introduces a novel, resource-efficient machine learning model utilizing multi-color space features and feature selection for poultry disease detection, achieving high accuracy with minimal computational resources.

Findings

Achieved 95.85% accuracy in disease detection.

Model requires no GPU and has low execution time.

Comparable performance to deep learning models with fewer resources.

Abstract

Poultry farming is a vital component of the global food supply chain, yet it remains highly vulnerable to infectious diseases such as coccidiosis, salmonellosis, and Newcastle disease. This study proposes a lightweight machine learning-based approach to detect these diseases by analyzing poultry fecal images. We utilize multi-color space feature extraction (RGB, HSV, LAB) and explore a wide range of color, texture, and shape-based descriptors, including color histograms, local binary patterns (LBP), wavelet transforms, and edge detectors. Through a systematic ablation study and dimensionality reduction using PCA and XGBoost feature selection, we identify a compact global feature set that balances accuracy and computational efficiency. An artificial neural network (ANN) classifier trained on these features achieved 95.85% accuracy while requiring no GPU and only 638 seconds of execution time in Google Colab. Compared to deep learning models such as Xception and MobileNetV3, our proposed model offers comparable accuracy with drastically lower resource usage. This work demonstrates a cost-effective, interpretable, and scalable alternative to deep learning for real-time poultry disease detection in low-resource agricultural settings.