Photographs taken using mobile devices are uploaded to image storage and sharing services at a resolution, server location, and upload priority that is blind to the importance of the photo to the user. This is sub-optimal, as there are images of great importance to a user (e.g., wedding photos) that are better uploaded at high priority and resolution. Similarly, there are images (e.g., screenshots, photos of receipts, etc.) that are not very important and can be uploaded at lower priority and resolution.
With user permission, the techniques of this disclosure use machine learning to predict the importance of an image captured by a user. The predicted importance is used to select a resolution, server location, and upload priority for the image in an online image-sharing service.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Witkowski, Mary; Bohl, Kristina; and Ayyagar, Raja Ratna Murthy, "Using machine learning to improve image storage and recall", Technical Disclosure Commons, (January 02, 2019)