Identification and Classification of Intestinal Parasitic Eggs in Animals Through Microscopic Image Analysis

Intestinal parasitic infections in animals can cause a range of symptoms, including diarrhea, weight loss, anemia, and malnutrition. This project aims to classify parasitic eggs belonging to the Monezia and Strongyles species using microscopic images from a veterinary hospital. The dataset consisted of stool samples from animals infected with these parasites. Image processing and machine learning techniques, including data preprocessing, feature extraction, and feature selection are used to detect and classify the eggs. The goal was to accurately classify the eggs into either the Monezia or Strongyles species. To achieve the goal, two classification algorithms: K-Nearest Neighbors (KNN) and Decision Tree have been used. Using these algorithms, the model achieved accuracies of 91% and 60%, respectively. However, by incorporating Alyuda NeuroIntelligence for classification, a significantly improved accuracy of 92% was obtained. The results demonstrate that the use of Alyuda NeuroIntelligence in conjunction with machine learning techniques can greatly enhance the accuracy of parasitic egg classification. This approach can aid in the diagnosis and treatment of animal infections, improving animal health and well-being.