Deep Learning-Based Multiple Detection Techniques of Covid-19 Disease From Chest X-Ray Images Using Advanced Image Processing Methods and Transfer Learning

The 2019 new coronavirus (COVID-19), which originally surfaced in the Chinese city of Wuhan in December 2019, expanded quickly, and caused a pandemic. It has created a terrible influence on daily lives, public health, and the global economy. To stop the pandemic from spreading further and to treat the affected individuals as soon as feasible, it is essential to identify positive cases as soon as possible. One of the primary issues in the present COVID-19 pandemic is the early detection and diagnosis of COVID-19, as well as the precise separation of non-COVID-19 cases at the lowest cost and in the early stages of the disease. This study compares the usage of the most recent Convolutional Neural Network (CNN), a deep learning methodology employing networks, with a transfer learning technique using VGG and ResNet. With their assistance, we created models that can recognize COVID-19 in X-Ray photos. We have applied techniques of image preprocessing using Contrast Limited Adaptive Histogram Equalization (CLAHE) and Adaptive Histogram Equalization (AHE). We built the model by applying CNN. We have also applied transfer learning techniques using Visual Geometry Group (VGG16) and Residual Network (ResNet50) after image preprocessing using CLAHE and AHE. We have compared the accuracy of all models. The CLAHE technique along with ResNet50 works well as we achieve an accuracy of 0.99 It can be stated that ResNet50 with CLAHE played a very significant role in determining the covid-19 in X-ray images.