Identification of Toxins and Pathogen in Foods Using ML and CV

Food safety is a pressing global concern due to the potential health risks associated with toxins and pathogens in food. Traditional detection methods are often slow, resource-intensive, and require specialized equipment. This study introduces a novel approach utilizing machine learning (ML) and computer vision (CV) techniques to enhance the efficiency, accuracy, and accessibility of food safety analysis. By employing the CatBoost algorithm, this methodology allows for accurate identification of common toxins and pathogens through hyperspectral image analysis. OpenCV is used for image preprocessing, feature extraction, and advanced image augmentation, while CatBoost's superior handling of categorical data improves detection reliability. The model is evaluated on a diverse dataset, demonstrating strong performance across metrics such as accuracy, precision, and recall. Furthermore, a real-time detection system is developed using Streamlit, offering a user-friendly interface for food manufacturers and regulators. This research provides a scalable, cost-effective solution to improve food safety standards and contribute to public health..