Maximizing a neural network's accuracy and boosting the learning process for detecting the absolute colour similarity based on the centroids of normal distributions

Abstract

Our aim is to demonstrate that the ANN is prone to converge faster and with a higher level of accuracy using training data where tuples of triplets also represents the centroids of those 12 colour classes, considering each centroid as a pixel for a colour class, and as a mean, mode, and median for a normal gaussian distribution, instead of using the training data consisting from tuples of triplets randomly chosen.