Malaria, which is the most terrible illness worldwide, generates a substantial amount of administrative work for the health sector. The customary approach for detecting malaria involves an optical examination of human blood smears through a microscope by trained laboratory staff to identify red blood cells that are infected with parasites. This project is focused on developing a system that utilizes convolutional neural networks (CNNs) and visual geometry group (VGG) models for precise classification of malaria diseases. To achieve this objective, the proposed system employs image-based diagnosis using CNNs and VGG models, resulting in a high accuracy of 95.6% and precision in identifying infected and uninfected cells. The proposed system offers numerous benefits, such as enhanced accuracy and efficiency in malaria diagnosis, reduced workload for medical professionals, and increased access to reliable diagnosis in low-resource settings. The system can also be expanded to other medical imaging applications and can serve as a foundation for further research in the area of deep learning for medical diagnosis. Overall, the successful implementation of this project will be a significant contribution to the fight against malaria, which continues to be a significant global health challenge.