<![CDATA[One of the ways to detect coronavirus disease of 2019 (COVID-19) is X-rays, computerized tomography (CT). This paper aims to detect COVID-19 from CT images without any user intervention. The proposed algorithm consists of 5 stages. These stages include; the first stage aims to collect data from hospitals and internet websites, the second stage is pre-processing stage to remove noise and convert it from red green blue (RGB) to grayscale and then improve image quality, the third is the segmentation stage which included threshold and region-growing segmentation methods. The fourth stage is used to extract important characteristics, and the last stage is classification CT images using feed forward back propagation network (FFBPN) and support vector machines (SVM) and compare the results between them and see if the person is infected or healthy. This study was implemented in MATLAB software. The results showed that the noise cancellation technology using anisotropic filtering gave the best results. Region-growing method was reliable to separate COVID-19 infected from healthy regions. The FFBPN has given the best results for detecting and classifying COVID-19. The results of the proposed methodology are rapid and accurate in detecting COVID-19. The output from classifier is displayed on the Rasbperry Pi that included weather if patient is infected or not and the severity of COVID-19 infection.]]>
Copyrights © 2022
