Pneumonia is a dangerous disease which is brought about by various viral factors. It is often challenging to diagnose and treat pneumonia because it can be caused by the same bacteria that produce other lung diseases; the use of chest X-rays helps in an early detection of the diseases. In this study, we present a comprehensive approach that uses convolutional neural networks (CNNs) to identify pneumonia based on images of the chest in conjunction with well-known pre-trained models like VGG16 and ResNet152V2, DenseNet121, as well as combination of base CNN model and VGG. A dataset consisting of 2,635 annotated images gathered from various sources is used to train and test the models. This system employs various deep learning models to enhance its capability to distinguish between pneumonia patients and healthy cases by automatically extracting features from the chest X-ray images. For the given dataset, the result provides accuracy of 99.61%, 99.22%, 99.9%, 99.6%, and 99.78% for CNN, VGG16, ResNet151V2, DenseNet121, and CNN + VGG, respectively. Therefore, this framework will facilitate the detection of lung disease for experts and doctors as well.