Project Description:

This project presents an AI-driven system for the automatic detection of malaria using Raspberry Pi. The core of the system is a machine learning model trained to detect malaria-infected cells in blood sample images. A custom web interface hosted on the Raspberry Pi allows users to upload blood smear images, which are then analyzed by the pre-trained AI model. The system provides an instant diagnosis, displaying the results on both the web interface and through connected hardware—activating a green LED for healthy samples and a red LED for malaria-positive samples. This low-cost, portable, and user-friendly system aims to aid remote clinics and under-resourced medical centers in early malaria detection.Malaria remains a major public health issue in many parts of the world, especially in developing countries. Traditional diagnosis involves microscopic analysis, which is time-consuming and requires trained professionals. Automating this process using image processing and machine learning not only reduces diagnostic time but also increases accessibility in rural areas. The Raspberry Pi, being a low-cost yet powerful computing device, serves as the central processing unit for this automated malaria detection system.