Malaria Blood Cell Image Classification using Transfer Learning with Fine-Tune ResNet50 and Data Augmentation

Based on the WHO Report related to malaria, it is estimated that there will be 241 million malaria cases and 627,000 deaths from this disease globally in 2020 with number of increasing yearly. Preventing conditions through early detection. A more quick precise diagnosis method was required simplify reduce detection process. Medical image classification could carried out rapidly precisely using machine learning or deep techniques. This research aims diagnose by classifying images blood cells Deep Learning a Transfer approach. By utilizing various fine-tuning procedures implementing data augmentation proposed develops previous studies. Two types models Frozen ResNet50 Fine-Tune are being tested. The dataset utilized augmented improve model performance. study makes use "NIH Malaria Cell Images Dataset" contains total 27,660 data. It divided into two classes: parasitized uninfected. results improved fine-tuned VGG16 an accuracy 96% compared which achieved score 98%.