Abstract
The true significance of a particular photograph (or video) to a user is difficult to discern in an automatic manner directly from photo pixels (and/or metadata) because there is context beyond the photograph that cannot be determined from pixels alone. This disclosure describes techniques, implemented with user permission, that provide a reliable indicator for the significance of an image using the statistics, telemetry, and metadata relating to action categories such as the capture, curation, consumption, connection, and culling of the image. The techniques generate a personal significance score (PSS) normalized to the range (0.0, 1.0) leverage user behavior with reference to an image (or set of images) to determine the importance of the image, without specifically needing to perform computationally intense pixel-level analysis of the image.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Goyal, Ashwin, "Personal Significance Scores for Images", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/10127