Image classification tasks become challenging when the number of categories increases and images within a category show significant variability. Such situations also require a larger number of samples so that features inherent in each category can be captured more accurately by the classification model. For example, a fashion retailer may have a large variety of fashion items and may be interested in developing a classification model from the image data of such fashion items. A special type of deep network, called a convolutional neural network (CNN), has proven to be highly effective in situations that call for large scale image classification and recognition tasks. CNNs are the most popular networks for such applications and are regarded as the gold standard for large-scale image classification problems. These networks are capable of capturing various minute details in an image with the help of different types of layers in the network. In Chapter 5, Image Classification Using Convolutional Neural Networks, we provide an illustration of applying a CNN to image classification using R.