Real ID and enhanced id detection by artificial intelligence

A method of using artificial intelligence to identify visual indicators on identification cards and driver's licenses, the method comprising the steps of:

• receiving, by an artificial intelligence system via upload, a digital file, wherein the digital file comprises a document that is either an identification card or driver's license from one of the states of the United States;
• transforming the digital file into a tensor;
• applying a deep learning model to the tensor, wherein the deep learning model has been trained to identify visual indicator candidate locations, each visual indicator candidate location having a visual indicator type and a confidence value;
• wherein the visual indicator type is a Real ID visual indicator or an Enhanced ID visual indicator;
• identifying, by applying the deep learning model, a set of visual indicator candidate locations on the document;
• applying non-maximum suppression to filter the set of visual indicator candidate locations, resulting in a final visual indicator location having a final confidence value and a final visual indicator type;
• and
• confirming the final visual indicator type associated with the final visual indicator location by determining that the final confidence value exceeds a confidence value threshold.