Image recognition is a crucial task in the field of computer vision, with applications ranging from autonomous vehicles to medical imaging. This research paper explores the use of the ResNet-50 model, a deep learning architecture, for image recognition tasks. The objective is to assess the model's performance and compare it with baseline models. A comprehensive dataset is used for training and validation, and evaluation metrics such as accuracy, precision, and recall are employed to analyse the results. The findings demonstrate the effectiveness and efficiency of ResNet-50 in achieving state- of-the-art performance in image recognition tasks.