Malaria remains one of the most serious infectious diseases, especially in tropical and developing regions where access to advanced healthcare facilities is limited. Early and accurate diagnosis is essential to prevent complications and reduce mortality. Traditional diagnostic methods rely on manual microscopic examination of blood smears, which is time-consuming, requires skilled personnel, and is prone to human error. This project presents an automated malaria detection system using Raspberry Pi and artificial intelligence-based image processing techniques. The system utilizes a pre-trained Convolutional Neural Network (CNN) model to analyze blood smear images and classify them as infected or uninfected. A Flask-based web interface is developed to allow users to upload images easily through a local network. Once the image is submitted, it is processed using OpenCV for preprocessing, followed by classification using the trained AI model. The Raspberry Pi acts as the central processing unit, handling image processing, model inference, and hardware control. Based on the result, a red LED indicates malaria-positive samples, while a green LED indicates healthy samples. The system operates offline, making it suitable for rural and resource-limited environments. This solution is cost-effective, portable, and user-friendly, enabling rapid and reliable malaria diagnosis. It reduces dependency on skilled technicians and supports early detection, contributing to improved healthcare accessibility and disease management.
Phatangare et al. (Wed,) studied this question.