Abstract: Examples herein describe a product scan system for identifying packaged items in an image. The product scan system accesses image frames, detects a packaged item in the image frames, generates text feature data by extracting text features from the packaged item in the image frames, generates image feature data by extracting image features from the packaged item in the image frames, generates a first ranked set of query results using the generated text feature data, generates a second ranked set of query results using the generated image feature data, generates a final ranked set of query results, presents a subset of the final ranked set of query results on a graphical user interface of the computing device.

Abstract: Methods and systems are disclosed for performing optical character recognition on augmented images. The system accesses an image depicting a real-world environment augmented with a graphical element. The system recognizes the graphical element in the image by applying a machine learning (ML) model to the image. The system stores a standard code representing the graphical element that has been recognized in association with the image.