Advertising targeting based on image-derived metrics

Abstract

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.

We claim: 
     
         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; and 
 display, after the selecting, the selected digital media on the physical display device. 
   
     
     
         2 . The computing device of  claim 1 , wherein the one or more computer-readable media comprise further computer-executable instructions, which, when executed by the one or more processing units, cause the computing device to request, after the selecting, the selected digital media from a remote computing device. 
     
     
         3 . The computing device of  claim 1 , further comprising a video camera, wherein at least some of the two or more non-public digital images were captured by the video camera. 
     
     
         4 . The computing device of  claim 3 , wherein the at least some of the two or more non-public digital images are from a video conference in which the user is engaging concurrently with execution of the computer-executable instructions. 
     
     
         5 . The computing device of  claim 1 , wherein the selected digital media were selected from locally cached digital media that were provided to the computing device because targeting metrics associated with the provided digital media were similar to physical attributes of the user or identified preferences of the user as derived from the public images associated with the user. 
     
     
         6 . The computing device of  claim 1 , wherein the identified physical attributes of the user that are matched to the targeting metrics of the selected digital media comprise physical attributes of the user that have changed across multiple ones of the filtered digital images. 
     
     
         7 . The computing device of  claim 1 , wherein the digital image analysis algorithms that are applied to identify the at least some preferences of the user comprise digital image analysis algorithms that analyze environments of the filtered digital images and identify the at least some preferences of the user based upon an environment common to more than a threshold quantity of the filtered digital images. 
     
     
         8 . The computing device of  claim 1 , wherein the digital image analysis algorithms that are applied to identify the at least some preferences of the user comprise digital image analysis algorithms that analyze image metadata of the filtered digital images. 
     
     
         9 . The computing device of  claim 1 , wherein the identified physical attributes of the user and the identified preferences of the user that are matched to the targeting metrics of the selected digital media comprise physical attributes of the user and identified preferences of the user that are prioritized to assign greater importance to the digital image analysis of more recent digital images, among the filtered digital images, as determined by reference to the image metadata. 
     
     
         10 . A method of increasing relevance of digital media visually presented to a user by a computing device on a physical display device communicationally coupled to the computing device, the method comprising:
 performing, on the computing device, facial recognition on two or more non-public digital images stored on the computing device 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;   identifying, 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 filtering, on the computing device, 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;   applying, on the computing device, digital image analysis algorithms to the filtered digital images to identify physical attributes of the user;   applying, on the computing device, digital image analysis algorithms to the filtered digital images to identify at least some preferences of the user;   selecting, by the computing device, 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; and   displaying, by the computing device, after the matching, the selected digital media on the physical display device.   
     
     
         11 . The method of  claim 10 , further comprising: requesting, by the computing device, after the selecting, the selected digital media from a remote computing device. 
     
     
         12 . The method of  claim 10 , wherein at least some of the two or more non-public digital images were captured by a video camera of the computing device. 
     
     
         13 . The method of  claim 12 , wherein the at least some of the two or more non-public digital images are from a video conference in which the user is engaging concurrently with the performance of the method. 
     
     
         14 . The method of  claim 10 , wherein the selected digital media were selected from locally cached digital media that were provided to the computing device because targeting metrics associated with the provided digital media were similar to physical attributes of the user or identified preferences of the user as derived from the public images associated with the user. 
     
     
         15 . The method of  claim 10 , wherein the identified physical attributes of the user that are matched to the targeting metrics of the selected digital media comprise physical attributes of the user that have changed across multiple ones of the filtered digital images. 
     
     
         16 . The method of  claim 10 , wherein the digital image analysis algorithms that are applied to identify the at least some preferences of the user comprise digital image analysis algorithms that analyze environments of the filtered digital images and identify the at least some preferences of the user based upon an environment common to more than a threshold quantity of the filtered digital images. 
     
     
         17 . The method of  claim 10 , wherein the digital image analysis algorithms that are applied to identify the at least some preferences of the user comprise digital image analysis algorithms that analyze image metadata of the filtered digital images. 
     
     
         18 . The method of  claim 10 , wherein the identified physical attributes of the user and the identified preferences of the user that are matched to the targeting metrics of the selected digital media comprise physical attributes of the user and identified preferences of the user that are prioritized to assign greater importance to the digital image analysis of more recent digital images, among the filtered digital images, as determined by reference to the image metadata. 
     
     
         19 . A method of increasing relevance of digital media visually presented to a user by a computing device on a physical display device communicationally coupled to the computing device, the method comprising:
 performing, on the computing device, facial recognition on digital images captured by a video camera that is communicationally coupled to the computing device;   identifying, as a face of the user, a face detected by the facial recognition;   applying, on the computing device, digital image analysis algorithms to the digital images to identify physical attributes of the user;   applying, on the computing device, digital image analysis algorithms to the digital images to identify at least some preferences of the user;   selecting, by the computing device, 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; and   displaying, by the computing device, after the matching, the selected digital media on the physical display device.   
     
     
         20 . The method of  claim 10 , further comprising:
 digitally filtering, on the computing device, the digital images to apply the digital image analysis algorithms on only those digital images that are determined to comprise the user based on the facial recognition detecting the identified face of the user in those digital images;   wherein the digital images are being captured by the video camera concurrently with the performance of the method; and   wherein further the identifying the face of the user comprises identifying, as the face of the user, the face most recently detected by the facial recognition.