Purpose: Pandemic condition almost everywhere due to COVID-19. The health and life of people have been severely impacted globally and derails the physical activities. Early detection of the infected persons for special care is crucial step to sustain in such situation. One of the fastest ways to diagnose the patients is to detect the disease from radiography and radiology images. Earlier studies have shown that patients infected with COVID19 have specific abnormalities in the chest radiograms. Radiologists certify the presence of COVID-19 by observing the images. Method: In this paper, the deep learning model is utilized by consideration of CT images to detect COVID19 infection in the patients. Initially, a dataset of 746 CT images from the publicly available datasets is prepared. Transfer learning is used to train “Convolutional Neural Networks (CNN)” using VGG19, to identify COVID-19 disease in the analyzed CT scan images. Further it has been framed with IoT based application and verified. Result: The model is evaluated with 521 images as training,112 images for validation, and the rest 113 for testing. The precision, recall, F-Score, and confusion matrix parameters are considered to evaluate the efficiency of the model. Conclusion: The work is implemented and verified successfully. The result found is excellent as compared to earlier work and shown in result section. Even though the performance of the model is very encouraging, to have a more reliable estimation of the accuracy rates, further analysis is required on a larger set of COVID-19 images