ADVERTISING TARGETING BASED ON IMAGE-DERIVED METRICS

摘要

Advertising targeting metrics for individuals can be derived from images associated with those individuals. Such advertising targeting metrics can include physical attributes, as well as preferences based on prior activity, or history. Public images associated with specific user identities can be processed and advertising targeting metrics can be derived therefrom to more accurately tailor the advertisements displayed to the individuals associated with those user identities. Additionally, non-public images can be likewise processed, either remotely or, for greater privacy, locally if so allowed by the user. Advertisers can then utilize the greater breath of advertising targeting metrics that can be derived from images to more accurately target advertisements to specific groups. In doing so, advertisers can submit their own images of exemplary targeted users, and the targeting metrics for those advertisers' advertisements can be automatically derived from the submitted images utilizing equivalent algorithms.

主权项

1. A computing device comprising:
one or more processing units; a physical display device and one or more computer-readable media comprising computer-executable instructions, which, when executed by the one or more processing units, cause the computing device to:
perform facial recognition on two or more non-public digital images stored on the computer-readable media and associated with a user of the computing device, the non-public digital images being exclusive of public digital images available from image-centric websites;identify, as a face of the user, a face detected by the facial recognition in a greater quantity of the two or more non-public digital images than any other face detected in those digital images by the facial recognition;digitally filter the two or more non-public digital images associated with the user to retain only those digital images that are either determined to comprise the user, based on the facial recognition detecting the identified face of the user in those digital images, or that are determined to have been taken by the user;apply digital image analysis algorithms to the filtered digital images to identify physical attributes of the user;apply digital image analysis algorithms to the filtered digital images to identify at least some preferences of the user;select a digital media based on the digital media having associated with it targeting metrics matching the identified physical attributes of the user or the identified preferences of the user; anddisplay, after the selecting, the selected digital media on the physical display device.