This paper investigates the use of artificial intelligence (AI) for the rapid and accurate detection of COVID-19 pneumonia from chest X-ray images. The authors propose a robust technique for automatic detection using pre-trained deep learning algorithms. A large public database was created by combining several public databases and collecting images from recently published articles. The database contains 423 COVID-19, 1485 viral pneumonia, and 1579 normal chest X-ray images. Transfer learning was used with image augmentation to train and validate several pre-trained deep convolutional neural networks (CNNs). The networks were trained to classify two schemes: i) normal and COVID-19 pneumonia; ii) normal, viral, and COVID-19 pneumonia with and without image augmentation. The classification accuracy, precision, sensitivity, and specificity for both schemes were 99.7%, 99.7%, 99.7% and 99.55% and 97.9%, 97.95%, 97.9%, and 98.8%, respectively. The high accuracy of this computer-aided diagnostic tool can significantly improve the speed and accuracy of COVID-19 diagnosis. The authors also evaluated the performance of eight different pre-trained CNN models, including MobileNetv2, SqueezeNet, ResNet18, ResNet101, DenseNet201, CheXNet, Inceptionv3, and VGG19. The results showed that CheXNet achieved the highest accuracy of 99.7% for two-class classification without image augmentation. DenseNet201 outperformed other models in three-class classification when image augmentation was used. The study found that deep networks perform better than shallow networks in classifying normal and viral images. The authors concluded that the proposed technique can reliably classify most of the COVID-19 X-ray images. The study also highlights the importance of using a large dataset for training AI models to ensure accurate and reliable results. The authors believe that this computer-aided diagnostic tool can significantly improve the speed and accuracy in the screening of COVID-19 positive cases.This paper investigates the use of artificial intelligence (AI) for the rapid and accurate detection of COVID-19 pneumonia from chest X-ray images. The authors propose a robust technique for automatic detection using pre-trained deep learning algorithms. A large public database was created by combining several public databases and collecting images from recently published articles. The database contains 423 COVID-19, 1485 viral pneumonia, and 1579 normal chest X-ray images. Transfer learning was used with image augmentation to train and validate several pre-trained deep convolutional neural networks (CNNs). The networks were trained to classify two schemes: i) normal and COVID-19 pneumonia; ii) normal, viral, and COVID-19 pneumonia with and without image augmentation. The classification accuracy, precision, sensitivity, and specificity for both schemes were 99.7%, 99.7%, 99.7% and 99.55% and 97.9%, 97.95%, 97.9%, and 98.8%, respectively. The high accuracy of this computer-aided diagnostic tool can significantly improve the speed and accuracy of COVID-19 diagnosis. The authors also evaluated the performance of eight different pre-trained CNN models, including MobileNetv2, SqueezeNet, ResNet18, ResNet101, DenseNet201, CheXNet, Inceptionv3, and VGG19. The results showed that CheXNet achieved the highest accuracy of 99.7% for two-class classification without image augmentation. DenseNet201 outperformed other models in three-class classification when image augmentation was used. The study found that deep networks perform better than shallow networks in classifying normal and viral images. The authors concluded that the proposed technique can reliably classify most of the COVID-19 X-ray images. The study also highlights the importance of using a large dataset for training AI models to ensure accurate and reliable results. The authors believe that this computer-aided diagnostic tool can significantly improve the speed and accuracy in the screening of COVID-19 positive cases.