Image Classification and Labeling

A computer implemented method of training an image classification model, the method comprising:

• obtaining training images associated with labels, wherein two or more labels of the labels are associated with each of the training images and wherein each label of the two or more labels corresponds to an image classification class;
• classifying training images into one or more classes using a deep convolutional neural network;
• comparing the classification of the training images against labels associated with the training images;
• and
• updating parameters of the deep convolutional neural network based on the comparison of the classification of the training images against the labels associated with the training images.

A system for classifying images using one or more image classification models, the system comprising:

• a training image source comprising training images associated with labels, wherein two or more labels of the labels are associated with each of the training images;
• an image processing device communicably coupled to the training image source, wherein the image processing device is configured to obtain the training images from the training image source and to train a deep convolutional neural network using the training images and the labels associated with the training images;
• and
• an input image source comprising input images to be classified into classes, wherein classifying an input image into multiple classes associates the input image with multiple classes corresponding to the multiple classes.