 Pneumonia is one of the leading causes of death globally, with viruses, bacteria and fungi being responsible for its development. It is difficult to diagnose pneumonia based solely on chest x-rays, so researchers have developed a new deep learning framework for detecting pneumonia. This framework uses pre-trained models from ImageNet to extract features from images, which are then fed into a classifier for prediction. Five different models were tested, and an ensemble model was created that combined the output of each model. This model achieved an accuracy of 96.4%, with a recall of 99.62%. This model has the potential to improve the speed and accuracy of pneumonia detection, making it more accessible to both experts and novices. This article was authored by Vikas Chahan, Sanjay Kumar Singh, Aditya Kamparya, and others.