Algorithm 1: Pseudo Code of Proposed Method
		Require: number of covid-19 images n; number of healthy images m; number of GAN epochs p; transfer model T= {AlexNet, GoogleNet, VGG-19, Shufflenet V2, DenseNet-121, DenseNet-201}; number of transfer epochs q.
		Input: Chest X-ray Images$I$
		Output: Binary Classifier
1	First Step // Preparing Data
2	Split I into two subfolders (${\mathit{X}}_{\mathit{i}},{\mathit{Y}}_{\mathit{i}}$), where ${\mathit{X}}_{\mathit{i}}(i=1,\cdots ,n)$ and ${\mathit{Y}}_{\mathit{j}}(j=1,\cdots ,m)$ represent covid-19 and non-covid-19 folders, respectively.
3	Split data directory into training, validation, and test sets
4	Second Step // Data Augmentation
5	for$i<n$do // Traditional Augmentation
6		${\mathit{R}}_{\mathit{i}}\leftarrow$Rotate ($X_i$)
7		${\mathit{C}}_{\mathit{i}}\leftarrow$Crop ($X_i$)
8		${\mathit{F}}_{\mathit{i}}\leftarrow$Flip ($X_i$)
9		${\mathit{S}}_{\mathit{i}}\leftarrow$Scale ($X_i$)
10		${\mathit{T}}_{\mathit{i}}\leftarrow$Translate ($X_i$)
11	end for
12	${\mathit{T}\mathit{r}}_{\mathit{k}}=({{\mathit{R}}_{\mathit{i}},\mathit{C}}_{\mathit{i}},{\mathit{F}}_{\mathit{i}},{\mathit{S}}_{\mathit{i}},{\mathit{T}}_{\mathit{i}})$
13	for$i<p$do // Generative adversarial networks
14		Update discriminator network
15		Train with real batch
16		Calculate loss on real batch
17		Calculate gradients for discriminator
18		Train with fake batch
19		Generate fake image batch with generator
20		Classify all fake batch with discriminator
21		Calculate discriminator’s loss on the fake batch
22		Update and Calculate gradients for generator
23	end for
24	Third Step // Applying Block Filter
25	for$i<n$do
26		Convert $X_i$from RGB to Gray scale
27		imfilter ($X_i$ , fspecial ('LoG')) // apply Laplacian of Gaussian filter
28		imfilter ($X_i$ , fspecial ('Sobel')) // apply Sobel filter
29		globalgaborfeatures ($X_i$, gaborfilters, Output); // apply Gabor filter
30	end for
31	Fourth Step // Training Model
32	Loading all X-ray training data
33	Resize Images
34	for epochs = 1 to qdo
35		Train the AlexNet model
36		Train the GoogleNet model
37		Train the VGG-19 model
38		Train the ShuffleNet V2 model
39		Train the DenseNet-121 model
40		Train the DenseNet-201 model
41	end for
42	Test and evaluate model
43	Compare results