Deep Learning Approach for the Classification of Caprine Parasites

The increasing prevalence of parasitic infections in caprine populations poses a significant challenge to livestock health and productivity. Early detection and classification of parasitic eggs are crucial for effective disease management. This study presents a deep learning-based approach for the classification of 11 different types of caprine parasitic eggs using the YOLOv12 (You Only Look Once) model, a state-of-the-art object detection algorithm. The dataset used for training consists of 11 parasitic egg categories, with each category containing 1,000 images. The categories include: Ascaris lumbricoides, Capillaria philippinensis, Enterobius vermicularis, Fasciolopsis buski, Hookworm egg, Hymenolepis diminuta, Hymenolepis nana, Opisthorchis viverrine, Paragonimus spp., Taenia spp. egg, and Trichuris trichiura. The proposed model is designed to detect and classify the parasitic eggs efficiently, ensuring rapid identification and accurate classification, which is vital for facilitating early intervention and improving animal health management. The YOLOv12 model's performance is evaluated based on key metrics, including accuracy, precision, recall, and F1 score, demonstrating its potential for deployment in veterinary diagnostics. This research aims to contribute to the development of automated parasitic detection systems that can assist veterinarians in providing timely treatments and reducing the impact of parasitic diseases in caprines.

Keywords: Caprine parasites, YOLOv12, deep learning, parasitic egg classification, veterinary diagnostics, object detection, parasitic infections, image classification, livestock health, machine learning.