IMAGE CAPTURING APPARATUS AND METHOD

• US 20160300100A1
• Filed: 11/10/2014
• Published: 10/13/2016
• Est. Priority Date: 11/10/2014
• Status: Abandoned Application

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: ZHANG, Lidan, ZENG, Fucen, SHEN, Xiaolu, LI, Wenlong, DU, Yangzhou, LI, Qiang, TONG, Xiaofeng
• Application Number:
  US14/775,387
• Publication Number:
  US 20160300100A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/67 by interactive indications to the user

Abstract

Apparatuses, methods and storage medium associated with capturing images are disclosed herein. In embodiments, the apparatus may include a face tracker to receive an image frame, analyze the image frame for a face, and on identification of a face in the image frame, evaluate the face to determine whether the image frame comprises an acceptable or unacceptable face pose. Further, the face tracker may be configured to provide instructions for taking another image frame, on determination of the image frame having an unacceptable face pose, with the instructions designed to improve likelihood that the other image frame will comprise an acceptable face pose. Other embodiments may be described and/or claimed.

Claims

1. An apparatus for capturing or generating image, comprising:

an image capturing engine; and

a face tracker coupled with the image capturing engine to receive an image frame from the image capturing engine, analyze the image frame for a face, and on identification of a face in the image frame, evaluate the face to determine whether the image frame comprises an acceptable or unacceptable face pose;

wherein on determination of the image frame having an unacceptable face pose, the face tracker is to further provide instructions for taking another image frame, with the instructions designed to improve likelihood that the other image frame will comprise an acceptable face pose.

2. The apparatus of claim 1, wherein the face tracker, as part of evaluation of the face pose, is to first determine a plurality of landmarks of the face, second determine a plurality of translation positions or the plurality of angles of the face pose, based at least in part on the determined landmarks;

then third determine whether the plurality of translation positions or the plurality of angles for the face pose are within corresponding ranges for the translation positions and the angles.

3. The apparatus of claim 2, wherein the face tracker is to provide the instructions, on determination that at least one of the plurality of translation positions or the plurality of angles is out of a corresponding range for the translation position or angle.

4. The apparatus of claim 1, wherein the face tracker is to instruct rotating the apparatus towards or away from a user, in a clockwise or counterclockwise direction, or to a left or right direction, prior to taking another image frame;

or to instruct moving the apparatus along an X-axis, a Y-axis or a Z-axis, in a positive or negative direction, prior to taking another image frame.

5. The apparatus of claim 1, wherein the face tracker is to further receive a second image frame from either the image capturing engine or an image generating engine, analyze the second image frame for a second face, and on identification of a second face in the second image frame, extract a face shape of the second face or determine a facial expression of the second face, and make a determination on whether to automatically add the second image frame or an avatar image generated based at least in part on the second image frame to a collection of snapshots;

wherein the determination is based at least in part of the extracted face shape or the determined facial expression of the second face in the second image frame.

6. An apparatus for capturing or generating image, comprising:

an image capturing or generating engine; and

a face tracker coupled with the image capturing or generating engine to receive an image frame from the image capturing or generating engine, analyze the image frame for a face, and on identification of a face in the image frame, extract a face shape of the face or determine a facial expression of the face;

wherein the face tracker is to further make a determination on whether to automatically add the image frame or an avatar image generated based at least in part on the image frame to a collection of snapshots, and wherein the determination is based at least in part of the extracted face shape or the determined facial expression of the face in the image frame.

7. The apparatus of claim 6, wherein the face tracker, on identification of a face in the image frame, is to extract a face shape of the face;

wherein the face tracker is also to initialize the collection of snapshots with a snapshot having a face with a neutral face shape.

8. The apparatus of claim 7, wherein the face tracker, as part of making the determination, is to select a snapshot within the collection of snapshots that has a face that is closest to the face in the image frame.

9. The apparatus of claim 8, wherein the face tracker, as part of making the determination, is to further compute a dissimilarity measure between the face shape of the face in the image frame, and the face shape of the face in the selected snapshot.

10. The apparatus of claim 9, wherein the face tracker, as part of making the determination, is to further determine whether the dissimilarity measure exceeds a threshold.

11. The apparatus of claim 10, wherein the face tracker automatically adds the image frame or an avatar image generated based at least in part on the image frame to the collection of snapshots on determination that the dissimilarity measure exceeded the threshold.

12. The apparatus claim 6, wherein the face tracker, on identification of a face in the image frame, is to determine a facial expression of the face;

wherein the face tracker is also to determine whether the determined facial expression of the face is a facial expression of interest.

13. The apparatus of claim 12, wherein the face tracker automatically adds the image frame or an avatar image generated based at least in part on the image frame to the collection of snapshots on determination that the determined facial expression is a facial expression of interest.

14. A method for capturing or generating an image, comprising:

receiving, by a face tracker of an image capturing or generating apparatus, an image frame;

analyzing the image frame, by the face tracker, for a face;

on identification of a face in the image frame, evaluating the face, by the face tracker, to determine whether the image frame comprises an acceptable or unacceptable face pose; and

on determination of the image frame having an unacceptable face pose, providing, by the face tracker, instructions for taking another image frame, with the instructions designed to improve likelihood that the other image frame will comprise an acceptable face pose.

15. The method of claim 14, further comprising receiving, by the face tracker, a second image frame;

analyzing, by the face tracker, the second image frame for a second face;

on identification of a second face in the second image frame, extracting, by the face tracker, a face shape of the second face or determining, by the face tracker, a facial expression of the second face; and

determining, by the face tracker, whether to automatically add the second image frame or an avatar image generated based at least in part on the second image frame to a collection of snapshots;

wherein determining is based at least in part of the extracted face shape or the determined facial expression of the second face in the second image frame.

16. A method for capturing or generating an image, comprising:

receiving, by a face tracker of an image capturing or generating apparatus, an image frame;

analyzing, by the face tracker, the image frame for a face;

on identification of a face in the image frame, extracting, by the face tracker, a face shape of the face or determining, by the face tracker, a facial expression of the face; and

determining, by the face tracker, whether to automatically add the image frame or an avatar image generated based at least in part on the image frame to a collection of snapshots, wherein the determination is based at least in part of the extracted face shape or the determined facial expression of the face in the image frame.

17. The method of claim 16, further comprising, initializing, by the face tracker, the collection of snapshots with a snapshot having a face with a neutral face shape;

and on identification of a face in the image frame, extracting, by the face tracker, a face shape of the face;

wherein determining whether to automatically add the second image frame or an avatar image generated based at least in part on the second image frame to a collection of snapshots further comprises selecting a snapshot within the collection of snapshots that has a face that is closest to the face in the image frame;

computing a dissimilarity measure between the face shape of the face in the image frame, and the face shape of the face in the selected snapshot;

determining whether the dissimilarity measure exceeds a threshold; and

adding, by the face tracker, the image frame to the collection of snapshots on determining that the dissimilarity measure exceeded the threshold.

19. The method of claim 16, further comprising, on identification of a face in the image frame, determining, by the face tracker, a facial expression of the face;

wherein the face tracker is also to determine whether the determined facial expression of the face is a facial expression of interest; and

automatically adding, by the face tracker, the image frame or an avatar image generated based at least in part on the image frame to the collection of snapshots on determination that the determined facial expression is a facial expression of interest.

18. (canceled)

20. At least one computer-readable medium having instructions to cause an image capturing or generating apparatus, in response to execution of the instructions by the apparatus, to implement a face tracker to receive an image frame from the image capturing engine, analyze the image frame for a face, and on identification of a face in the image frame, evaluate the face to determine whether the image frame comprises an acceptable or unacceptable face pose;

wherein on determination of the image frame having an unacceptable face pose, the face tracker is to further provide instructions for taking another image frame, with the instructions designed to improve likelihood that the other image frame will comprise an acceptable face pose.

31. The computer-readable medium of claim 20, wherein the face tracker, as part of evaluation of the face pose, is to first determine a plurality of landmarks of the face;

second determine the plurality of translation positions or the plurality of angles of the face pose, based at least in part on the determined landmarks;

third determine whether the plurality of translation positions or the plurality of angles for the face pose are within corresponding ranges for the translation positions and the angles; and

provide the instructions, on determination that at least one of the plurality of translation positions or the plurality of angles is out of a corresponding range for the translation position or angle.

32. The computer-readable medium of claim 20, wherein the face tracker is to instruct rotating the apparatus towards or away from a user, in a clockwise or counterclockwise direction, or to a left or right direction, prior to taking another image frame;

or to instruct moving the apparatus along an X-axis, a Y-axis or a Z-axis, in a positive or negative direction, prior to taking another image frame.

33. The computer-readable medium of claim 20, wherein the face tracker is to further receive a second image frame from either the image capturing engine or an image generating engine, analyze the second image frame for a second face, and on identification of a second face in the second image frame, extract a face shape of the second face or determine a facial expression of the second face, and make a determination on whether to add the second image frame to a collection of snapshots;

wherein the determination is based at least in part of the extracted face shape or the determined facial expression of the second face in the second image frame.

21. (canceled)

22. (canceled)

23. (canceled)

24. (canceled)

25. (canceled)

26. (canceled)

27. (canceled)

28. (canceled)

29. (canceled)

30. (canceled)

34. At least one computer-readable medium having instructions to cause an image capturing or generating apparatus, in response to execution of the instructions by the apparatus, to implement a face tracker to receive an image frame from the image capturing or generating engine, analyze the image frame for a face, and on identification of a face in the image frame, extract a face shape of the face or determine a facial expression of the face;

wherein the face tracker is to further make a determination on whether to add the image frame to a collection of snapshots, and wherein the determination is based at least in part of the extracted face shape or the determined facial expression of the face in the image frame.

35. The computer-readable medium of claim 34, wherein the face tracker, on identification of a face in the image frame, is to extract a face shape of the face;

wherein the face tracker is also to initialize the collection of snapshots with a snapshot having a face with a neutral face shape; and

wherein the face tracker, as part of making the determination, is to select a snapshot within the collection of snapshots that has a face that is closest to the face in the image frame, compute a dissimilarity measure between the face shape of the face in the image frame, and the face shape of the face in the selected snapshot, determine whether the dissimilarity measure exceeds a threshold; and

wherein the face tracker adds the image frame to the collection of snapshots on determination that the dissimilarity measure exceeded the threshold.

36. The computer-readable medium of claim 34, wherein the face tracker, on identification of a face in the image frame, is to determine a facial expression of the face;

wherein the face tracker is also to determine whether the determined facial expression of the face is a facial expression of interest; and

wherein the face tracker adds the image frame to the collection of snapshots on determination that the determined facial expression is a facial expression of interest.