Algorithm 1 The algorithm used to implement proposed Exemplar COVID-19FclNet9 model

Input: X-ray image database

Output: Results

00: Load X-ray image database.

01: for k = 1 to dim do // Herein, dim is number of images.

02:    Read each image

03:    Divide X-ray image into exemplars/patches

04:    for j = 1 to 9 do

05:      Generate deep features from X-ray images and patches using fully connected layers.

06:      Merge generated features.

07:      Create jth feature ($X^j$) vector of the kth.

08:    end for j

09: end for k

10: for j = 1 to 9 do

11:    Apply NCA to $X^j$ and calculate indexes ($inx$).

12:    Select top 1000 features using $inx$.

13:    Calculate misclassification rates of the chosen 1000 features.

14: end for j

15: Select the best three chosen feature vectors.

16: Merge the best three vectors.

17: Employ iterative NCA to the merged features.

18: Fed the chosen final feature vector to SVM classifier.

19: Tune the parameters of the SVM classifier.

20: Obtain results using the tuned SVM with 10-fold cross-validation.