This study focuses on the classification of chest X-ray (CXR) images into three distinct categories: normal, pneumonia, and COVID-19, utilizing deep learning methodologies. A convolutional neural network (CNN) was designed and trained on a dataset of grayscale images. The architecture includes several convolutional layers, followed by max-pooling layers, and concludes with fully connected layers. Training was conducted using the Adam optimizer and sparse categorical cross-entropy loss function over 20 epochs with a batch size of 32. Preprocessing involved resizing images and applying histogram equalization to improve image quality. The model demonstrated a high-test accuracy of 99.01%, with precision, recall, and F1-scores nearing 99% for all categories. Analysis through confusion matrices and classification reports validated the model’s efficacy, underscoring the potential of deep learning in automating the diagnosis of COVID-19 from CXR images, thereby offering a swift and reliable tool for healthcare professionals.