Training a classifier algorithm used for automatically generating tags to be applied to images

A method for automatically generating tags to be applied to a received image, the method comprising:

• accessing, by a processor, a classifier algorithm, wherein the classifier algorithm is trained to identify images as semantically similar to one another based on a set of similar training images being grouped into a cluster, wherein the set of similar training images are grouped into the cluster based on training images in the set of similar training images having respective tag vectors with respective magnitudes within a threshold distance of a centroid for the cluster, each tag vector having elements with respective values representing at least one of (i) a weight of a corresponding tag from the set of available tags or (ii) the corresponding tag being absent from a training image to which the tag vector is applied, each weight indicative of a respective number of occurrences of the corresponding tag in a set of tagged training images;
• executing, by the processor, the classifier algorithm to determine that an input image is semantically similar to an example tagged image;
• and
• generating, by the processor, a tag for the input image using tag content from the example tagged image based on determining that the input image is semantically similar to the example tagged image.

A system comprising:

• a processor;
• and
• a non-transitory computer-readable medium communicatively coupled to the processor,
• wherein the processor is configured to execute program code stored in the non-transitory computer-readable medium and thereby perform operations comprising:
• grouping first training images together based on the first training images having tags with similar rates of occurrence within a set of tagged training images that includes the first training images and second training images;
• training a classifier algorithm to identify, based on the first training images being grouped together, the first training images as semantically similar to one another and semantically different from the second training images;
• executing the trained classifier algorithm to determine that an input image is semantically similar to an example tagged image;
• and
• generating a tag for the input image using tag content from the example tagged image based on determining that the input image is semantically similar to the example tagged image.