Algorithm 1: Ensemble Classification of pooled images
1:	Inputs: Preprocessed feature vector FE
2:	Outputs: Classification outcomes C1, and C2
3:		Let us us take a collection P = {P1, P2, P3, Pi} of image vector space, where i ≤ N
4:			Let us apply scaling, flipping, shearing, and zooming filters to n images from collection P∀ n ≤ N
5:			Let us extract the features by applying image embedding to extract F = {F1, F2, F3, Fi} features of images∀ i ≤ N
6:				Analyze Pi instances with features FE using AdaBoost classifier where each Pi in P
7:				Analyze Pi instances with features FE using the Decision tree classifier, each Pi in P
8:				Analyze Pi instances having features FE using Naïve Bayes classifier, each Pi in P
9:				Analyze Pi instances having features FE using Random Forest classifier, each Pi in P
10:				Analyze Pi instances with features FE using Logistic regression where each Pi in P
11:				Analyze the individual performance of all classifiers on Pi attributes of P for i ≤ N
12:				Output the classification as a result Y (Y ≤ 5) classifiers
13:			End
14:		End