COVID-19 (Coronavirus Disease 2019) is a severe global pandemic infection induced by a new coronavirus also known as SARS Coronavirus (SARS-CoV). It is a dynamic infection that affects different people in different ways; thus, a delay in the precise detection and treatment leads to the spread of the infection leading to more deaths. Automatic intelligent diagnostic models are thus needed to help detect such severe diseases at an early stage, thereby saving lives. For this, researchers developed a machine learning (ML) methodology for screening and COVID-19 classification using SARS-CoV2 CT scan images along with in-depth analysis of various features that is fascinating due to their better performance than conventional CT scan image classification for COVID-19. In addition, CT scan image feature extraction was measured using in-depth analysis with global and local feature descriptors. Principal component analysis (PCA) was employed to determine the optimal subset for COVID-19 recognition and classification. We compared and checked the best-in-class ML strategies on SARS-CoV2 CT scan images. The accuracy of training data was 98.78% and the accuracy of test data was 93.96% for a proposed model tested on the SARS-CoV2 CT scan images dataset. The findings of the experiment indicate a major improvement in COVID-19 classification, which aids in better COVID-19 investigation and disease prevention.