TARGETED ADVERTISEMENT BASED ON FACE CLUSTERING FOR TIME-VARYING VIDEO

• US 20130111509A1
• Filed: 10/28/2011
• Published: 05/02/2013
• Est. Priority Date: 10/28/2011
• Status: Active Grant

• Current Assignee: Symbol Technologies, LLC (Zebra Technologies Corporation)
• Original Assignee: Motorola Solutions, Inc.
• Inventors: SUPER, BOAZ J., ARORA, HIMANSHU, GUO, FENG
• Granted Patent: US 8,769,556 B2
• Time in Patent Office: Days
• US Class Current: 725/12
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: H04H 60/45 for identifying users
• CPC Class Codes: H04H 60/65 for using the result on users' side
• CPC Class Codes: H04N 21/4223 Cameras H04N23/00 takes precedence
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/44226 on social networks
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

A method and apparatus for providing targeted advertisements is provided herein. In particular, targeted advertisements are provided to users based on face clustering for time-varying video. During operation video is continuously obtained of users of the system. Users'"'"' faces are detected and measured. Measurements of users'"'"' faces are then clustered. Once the clusters are available, advertisements are targeted at clusters rather than individual users.

Claims

1. A method for associating an action with facial data obtained from a video feed, the method comprising the steps of:

receiving the video feed;

detecting faces within the video feed;

representing the faces as data;

applying clustering techniques to the data to identify clusters of data; and

associating an action with the identified clusters.

2. The method of claim 1 wherein the step of associating the action based on the identified clusters comprises the step of associating an advertisement with the identified clusters.

3. The method of claim 1 further comprising the steps of:

during a viewing session determining if a face from the video feed belongs to a previously-identified cluster;

updating the previously-identified cluster if the face from the video feed belongs to the previously-identified cluster; and

creating a new cluster if the face from the video feed does not belong to the previously-identified cluster.

4. The method of claim 1 wherein the step of applying clustering techniques to the data to identify the clusters of data comprises the step of applying a k-means algorithm to identify the clusters of data.

5. The method of claim 1 further comprising the steps of:

receiving a video feed at a later time;

detecting faces from the video feed received at the later time;

determining what cluster (or clusters) from previously-identified clusters that the detected faces belong to; and

performing the action associated with the determined cluster or clusters.

6. A method for providing targeted advertisements to a user, the method comprising the steps of:

receiving a video feed;

detecting faces within the video feed;

representing the faces as data;

accessing a database of pre-identified clusters of data to determine what pre-identified clusters the detected faces belong to; and

accessing a database to determine targeted advertisements to play based on what pre-identified clusters the detected faces belong to.

7. The method of claim 6 wherein the pre-identified clusters are formed by applying clustering techniques to previously-obtained data to produce clusters of data.

8. An apparatus comprising:

a detector receiving a video feed, detecting faces within the video feed, representing the faces as data, applying clustering techniques to the data to identify clusters of data, and associating an action with the identified clusters; and

storage for storing the identified clusters and associated action.

9. The apparatus of claim 8 wherein the action comprises an advertisement to be played with the identified clusters.

10. The apparatus of claim 9 wherein the advertisements are associated with the identified clusters by determining programs watched by various clusters.

11. The apparatus of claim 9 wherein the advertisements are associated with the identified clusters by determining what advertisements are skipped for each cluster.

12. The apparatus of claim 9 wherein the advertisements are associated with the identified clusters by determining known physical or social traits typically associated with the cluster characteristics.

13. The apparatus of claim 8 wherein the detector additionally accesses the storage and determines if a face from the video feed belongs to an identified cluster, and updates the identified cluster if the face from the video feed belongs to the identified cluster, or creates a new cluster if the face from the video feed does not belong to the identified cluster.

14. The apparatus of claim 8 wherein the detector uses a k-means algorithm to identify the clusters of data.

15. The apparatus of claim 8 wherein the detector identifies faces from a later-received video feed, determines what clusters the identified faces belong to, and performs the action associated with the determined clusters.

16. The apparatus of claim 8 wherein the detector accumulates faces that do not belong to a cluster into the storage, and later creates additional clusters from the faces in the storage.