COVID-19 Infected Lung Image Classification using Inception-ResNet
Keywords:
Convolutional Neural Networks (CNNs), COVID-19, Feature extraction, Inception-ResNet V2, X-rayAbstract
This project focuses on applying the Inception-ResNet V2 model for the automated classification of X-ray images, aiming to aid in the early diagnosis of COVID-19. The primary objective is to eliminate human error in the diagnostic process by leveraging the advanced capabilities of the Inception- ResNet V2 model, which accurately assesses the severity of the condition. The model has been meticulously trained using a comprehensive dataset of X-ray images sourced from various online repositories. This approach facilitates timely treatment of COVID-19 and enhances the identification of complications associated with the illness. Adopting this automated method can improve the efficiency and accuracy of X-ray-based COVID-19 diagnoses. The network's performance is rigorously evaluated through accuracy calculations and subsequent testing, ensuring the minimization of diagnostic errors. This innovative approach could revolutionize the diagnostic landscape, providing a reliable tool for healthcare professionals in the battle against COVID-19.
