Electronic display viewing verification
Techniques for performing viewing verification using a plurality of classifiers are disclosed. Images of an individual may be obtained concurrently with an electronic display presenting one or more images. Image classifiers for facial and head pose analysis may be obtained. The images of the individual may be analyzed to identify a face of the individual in one of the plurality of images. A viewing verification metric may be calculated using the image classifiers and a verified viewing duration of the screen images by the individual may be calculated based on the plurality of images and the analyzing. Viewing verification can involve determining whether the individual is in front of the screen, facing the screen, and gazing at the screen. A viewing verification metric can be generated in order to determine a level of interest of the individual in particular media and images.
1. A computer-implemented method for viewing verification comprising:
obtaining a plurality of images of an individual captured concurrently with an electronic display presenting one or more screen images;
obtaining a plurality of image classifiers for facial and head pose analysis;
analyzing the plurality of images, using one or more processors, to identify a face of the individual in one of the plurality of images, wherein the one of the plurality of images contains an image of the face captured while the individual is facing the electronic display and wherein the analyzing is accomplished using one or more image classifiers from the plurality of image classifiers;
analyzing an identity of the individual based on the face of the individual, wherein the analyzing comprises producing an anonymous viewer identifier, and using the anonymous viewer identifier to track viewing habits of the individual; and
calculating a viewing verification metric using the plurality of image classifiers wherein the calculating evaluates a verified viewing duration of the screen images by the individual based on the plurality of images and the analyzing.
2. The method of claim 1 further comprising determining an engagement score based on the analyzing.
3. The method of claim 2 further comprising determining an emotional response score based on the analyzing.
4. The method of claim 1 further comprising tracking viewing by the individual using the identity and updating the viewing verification metric.
5. The method of claim 1 wherein the calculating the viewing verification metric, using the plurality of image classifiers, evaluates an amount of time the individual looks away from the electronic display while the electronic display shows the one or more screen images.
6. The method of claim 1 wherein the calculating the viewing verification metric, using the plurality of image classifiers, evaluates an amount of time eyes are closed for the individual while the electronic display shows the one or more screen images.
7. The method of claim 1 wherein the obtaining is in response to tags associated with media rendered on the electronic display.
8. The method of claim 1 wherein the viewing verification metric is used in determining a viewership score.
9. The method of claim 1 wherein the electronic display renders an object and the viewing verification metric includes scoring viewing of the object.
10. The method of claim 1 wherein the viewing verification metric of the individual enables determining viewability of digital media content from the electronic display.
11. The method of claim 10 wherein viewability includes evaluation of presence of digital media content and whether the digital media content is viewable by the individual.
12. The method of claim 10 further comprising modifying the digital media content based on the viewing verification metric.
13. The method of claim 10 wherein the determining includes scoring the digital media content.
14. The method of claim 1 wherein the one or more image classifiers is used to evaluate head pose orientation for the individual.
15. The method of claim 1 further comprising performing eye gaze detection using the plurality of image classifiers.
16. The method of claim 1 wherein the analyzing the plurality of images is accomplished without eye tracking.
17. The method of claim 1 wherein the analyzing is used as part of a viewership determination across a plurality of people.
18. The method of claim 1 further comprising:
obtaining a second plurality of images of a second individual;
analyzing the second plurality of images, using the one or more processors, to identify a face of the second individual in one of the second plurality of images, wherein the one of the second plurality of images contains an image of the face of the second individual captured while the second individual is facing the electronic display and wherein the analyzing is accomplished using one or more image classifiers from the plurality of image classifiers; and
calculating a viewing verification metric for the second individual using the plurality of image classifiers wherein the calculating evaluates a verified viewing duration of the screen images by the second individual based on the second plurality of images and the analyzing the second plurality of images.
19. The method of claim 18 further comprising combining the viewing verification metric for the individual with the viewing verification metric for the second individual into an aggregated viewing verification metric.
20. The method of claim 1 further comprising opting in by the individual for collection of the plurality of images.
21. The method of claim 1 wherein the calculating is performed using deep learning.
22. The method of claim 21 wherein the deep learning is performed using a deep neural network.
23. The method of claim 21 wherein the deep learning is performed using a convolutional neural network.
24. A computer program product embodied in a non-transitory computer readable medium for viewing verification, the computer program product comprising code which causes one or more processors to perform operations of:
obtaining a plurality of images of an individual captured concurrently with an electronic display presenting one or more screen images;
obtaining a plurality of image classifiers for facial and head pose analysis;
analyzing the plurality of images to identify a face of the individual in one of the plurality of images, wherein the one of the plurality of images contains an image of the face captured while the individual is facing the electronic display and wherein the analyzing is accomplished using one or more image classifiers from the plurality of image classifiers;
analyzing an identity of the individual based on the face of the individual, wherein the analyzing comprises producing an anonymous viewer identifier, and using the anonymous viewer identifier to track viewing habits of the individual; and
calculating a viewing verification metric using the plurality of image classifiers wherein the calculating evaluates a verified viewing duration of the screen images by the individual based on the plurality of images and the analyzing.
25. A computer system for viewing verification comprising:
a memory which stores instructions; and
one or more processors coupled to the memory, wherein the one or more processors, when executing the instructions which are stored, are configured to:
obtain a plurality of images of an individual captured concurrently with an electronic display presenting one or more screen images;
obtain a plurality of image classifiers for facial and head pose analysis;
analyze the plurality of images to identify a face of the individual in one of the plurality of images, wherein the one of the plurality of images contains an image of the face captured while the individual is facing the electronic display and wherein the analysis is accomplished using one or more image classifiers from the plurality of image classifiers;
analyze an identity of the individual based on the face of the individual, wherein the analyzing comprises producing an anonymous viewer identifier, and using the anonymous viewer identifier to track viewing habits of the individual; and
calculate a viewing verification metric using the plurality of image classifiers wherein the calculation evaluates a verified viewing duration of the screen images by the individual based on the plurality of images and the analysis.