Understanding how noise affects the accuracy of CNN image classification

Image classification by using Convolutional Neural Network (CNN) has been a popular method in image processing. This is because this model produces high accuracy of output with efficient amount of work. There are a lot of factors that could affect the performance of CNN in image processing such as image resolution, size of data, quality of image, kernel size and so on. The purpose of this research is to test the accuracy of CNN in training and testing with and without the presence of noise augmentation.