ENABLING PERSISTENT RECOGNITION OF INDIVIDUALS IN IMAGES

• US 20090185723A1
• Filed: 01/21/2008
• Published: 07/23/2009
• Est. Priority Date: 01/21/2008
• Status: Active Grant

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Kurtz, Andrew Frederick, Das, Madirakshi
• Granted Patent: US 8,180,112 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/178 estimating age from face image; using age information for improving recognition
• CPC Class Codes: G06V 40/50 Maintenance of biometric data or enrolment thereof

Abstract

A method and system for accumulating and using images of individuals, and associated image-derived data, on an continuous basis to create recognition models that facilitate ongoing recognition of individuals in images or photo collections.

Claims

1. A computer implemented method for enabling computer recognition of a particular person in images, comprising the steps of:

analyzing a plurality of facial images of a person using a facial recognition model of the person to identify changes in facial appearance by comparing the facial images to the recognition model;

calculating subject recognition confidence values for the facial images;

comparing the subject recognition confidence values for the facial images to prior subject recognition confidence values associated with the facial recognition model to identify changes in the confidence values;

analyzing the identified changes in the subject recognition confidence values to determine whether a new facial recognition model is required for the person;

generating the new facial recognition model from current or subsequent images of the person if it is so determined by the step of analyzing the identified changes; and

using the new facial recognition model for subsequent person recognition tasks.

2. The method according to claim 1 wherein the step of analyzing the identified changes includes tracking changes in the subject recognition confidence values over time to identify significant changes in the confidence values.

3. The method according to claim 2 further comprising the step of measuring significant changes in the subject recognition confidence values relative to change detection criteria including total change, percent change, threshold change, rate of change, or duration of change.

4. The method according to claim 1 further comprising the step of calculating the subject recognition confidence values including using normalized ratios of probabilities calculated from similarity score distributions, wherein the similarity score distributions are probability distributions indicative of a matching of a known face and an unrecognized face.

5. The method according to claim 4 further comprising the step of calculating similarity score distributions for a population comprising only members of a household.

6. The method according to claim 5 wherein the step of calculating similarity in score distributions includes using pair-wise metrics.

7. The method according to claim 1 further comprising the step of analyzing the facial images relative to one or more defined facial metrics, wherein the facial metrics are associated with predetermined facial features that are tracked using a facial recognition model.

8. The method according to claim 1 further comprising the step of acquiring the plurality of facial images of the person from an image capture device, an image collection, or a combination thereof.

9. The method according to claim 1 wherein the facial recognition model is selected from a 3-D composite model, an active shape model, or an active appearance model.

10. The method according to claim 1 further comprising the step of identifying whether the person is a subject for whom a facial recognition model exists or a non-subject for whom a facial recognition model does not exist.

11. The method according to claim 1 further comprising the step of using the method for one or more persons that comprise a household to enable recognition of the persons in images associated with the household.

12. A computer implemented method for enabling computer recognition of a particular person in digital images, comprising the steps of:

acquiring at least one digital facial image of the person using an image capture device;

analyzing the at least one digital facial image of the person relative to a predetermined facial recognition model of the person to identify changes in facial appearance between the at least one image and the model;

calculating a subject recognition confidence value for each of the at least one facial image;

comparing the subject recognition confidence value for each of the at least one image to a subject recognition confidence value associated with the predetermined facial recognition model to identify a change in the values;

analyzing the identified change in the subject recognition confidence values to determine whether a new facial recognition model is required for the person;

acquiring at least one further facial image of the person using the image capture device to compile a complete set of images needed to generate the new facial recognition model;

generating the new facial recognition model from the complete set of images; and

using the new facial recognition model for person-in-picture recognition tasks.

13. The method according to claim 12 wherein the step of analyzing the identified change includes tracking changes in the subject recognition confidence values over time to identify significant changes in the confidence values.

14. The method according to claim 12 farther comprising the step of calculating the subject recognition confidence values using normalized ratios of probabilities calculated from similarity score distributions, wherein the similarity score distributions are probability distributions indicative of a matching of a known face and an unrecognized face.

15. The method according to claim 12 further comprising the step of analyzing the facial images relative to one or more defined facial metrics, wherein the facial metrics are associated with predetermined facial features that are tracked using a facial recognition model.

16. The method according to claim 12, wherein the image capture device is a device selected from an electronic picture frame, a video phone, a web camera, or a digital camera.

17. The method according to claim 12 wherein the step of generating the new facial recognition model comprises the step of normalizing the facial images acquired by the image capture device relative to grey scale and size.

18. The method according to claim 12 wherein the complete set of images of the person comprises a series of facial images spanning different facial poses.

19. The method according to claim 12 wherein the facial recognition model is selected from a 3-D composite model, an active shape model, or an active appearance model.

20. The method according to claim 12 further comprising the step of identifying whether the person is a subject for whom a facial recognition model exists or a non-subject for whom a facial recognition model does not exist.

21. The method according to claim 20 wherein the step of identifying whether the person is a subject or non-subject includes the step of utilizing a reference image comprising selected facial features to represent the facial appearance.

22. The method according to claim 20 further comprising the steps of providing the image capture device with a microphone that enables capture of voice characteristics of the person, and analyzing the voice characteristics to provide recognition cues for the person.

23. A computer implemented method for enabling computer recognition of a particular individual in images, comprising the steps of:

providing a facial recognition model of the individual which is capable of being used in people-in-image recognition tasks, wherein the facial recognition model is derived from one or more facial images of the individual;

providing a subject recognition confidence value linked to the facial recognition model;

tracking the subject recognition confidence value over time;

analyzing the time tracked confidence values to identify changes in confidence values indicative of significant changes in a facial appearance of the individual;

determining a need for at least one new facial recognition model for the individual based on the significant changes in the facial appearance of the individual; and

in response to the determined need, generating the at least one new facial recognition model for the individual using current or subsequently acquired facial images of the individual.

24. The method according to claim 23 further comprising the step of calculating the subject recognition confidence value including using normalized ratios of probabilities calculated from similarity score distributions, wherein the similarity score distributions are probability distributions indicative of a matching of a known face and an unrecognized face.

25. The method according to claim 23 wherein the facial recognition model is selected from a 3-D composite model, an active shape model, or an active appearance model.

26. The method according to claim 23 wherein the need for at least one new facial recognition model for the individual is determined according to an age-based schedule.

27. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for enabling machine recognition of a particular person in images, said method steps comprising:

analyzing a plurality of facial images of the person using a facial recognition model of the person to identify changes in facial appearance of the person between the recognition model and the facial images;

calculating subject recognition confidence values for the facial images;

comparing the subject recognition confidence values for the facial images to subject recognition confidence values associated with the facial recognition model to identify changes in the confidence values;

analyzing the identified changes in the subject recognition confidence values to determine whether a new facial recognition model is required for the person;

generating the new facial recognition model from current or subsequent images of the person if it is so determined by the step of analyzing the identified changes; and

using the new facial recognition model for subsequent person recognition tasks.

28. A system comprising:

an image capture device for capturing a plurality of facial images of a person;

storage coupled to the image capture device for storing the plurality of facial images of the person and a previously generated facial recognition model of the person, the facial recognition model including a model confidence value;

means for identifying differences between the facial images and the facial recognition model including means for calculating subject recognition model confidence values for the facial images;

means for comparing the subject recognition confidence values for the facial images to the model confidence value; and

means for generating a new facial recognition model if a difference between the subject recognition confidence values for the facial images and the model confidence value is significant.