Image recognition and classification refer to the task of inputting an image into a neural network and having it output some kind of label for that image
In order to carry out image recognition/classification, the neural network must carry out feature extraction. Features are the elements of the data that you care about which will be fed through the network. In the specific case of image recognition, the features are the groups of pixels, like edges and points, of an object that the network will analyze for patterns.