Abstract :

Malaria remains a major global health challenge, particularly in developing countries where access to skilled medical professionals is limited. Traditional malaria diagnosis relies on manual microscopic examination of blood smears, which is time-consuming and prone to human error. Automated malaria detection using deep learning offers a promising alternative by providing fast, accurate, and scalable diagnosis. This project proposes a deep learning–based system for automated detection of malaria and classification of parasite stages from microscopic blood smear images. Convolutional Neural Networks (CNNs) are employed to learn discriminative features directly from images without manual feature engineering. The system identifies infected and uninfected red blood cells and further classifies infected cells into different developmental stages of the Plasmodium parasite. Image preprocessing techniques such as normalization and augmentation are applied to enhance model performance. The pro