Method and apparatus for processing digital images using face recognition

• US 9,600,712 B2
• Filed: 08/25/2014
• Issued: 03/21/2017
• Est. Priority Date: 08/30/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Jin, Hyun-sung
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): YOUSSEF, MENATOALLAH M
• Application Number:
  US14/467,456
• Publication Number:
  US 20150063636A1
• Time in Patent Office: 939 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 10/803 of input or preprocessed data
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/64 Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
• CPC Class Codes: H04N 5/2621 Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability

Abstract

A method and apparatus for processing digital images are provided. The method includes: recognizing faces from a plurality of images of a jumping subject; determining respective priorities for the plurality of images of the jumping subject, wherein an index of the priorities is based on face recognition information; and aligning the plurality of images of the jumping subject based on the priorities.

Claims

1. A method of processing digital images, the method comprising:

recognizing faces from a plurality of images of jumping subjects, wherein the plurality of images are continuously captured at a predetermined frame rate;

determining respective priorities for the plurality of images of the jumping subjects, wherein an index of the priorities is based on face recognition information, and wherein the priorities are based on an image of the jumping subjects having the largest average of positions of faces, an image of the jumping subjects having the smallest deviation of average of positions of faces, and an image of the jumping subjects having the largest number of faces; and

aligning the plurality of images of the jumping subjects based on the priorities.

2. The method of claim 1, wherein the aligning of the plurality of images of the jumping subject comprises deleting images of the plurality of images of the jumping subject other than a predetermined number of images of the plurality of images of the jumping subject in a priority descending order.

3. The method of claim 1, further comprising:

analyzing a priority selection reference preferred by a user based on face recognition information of images of the plurality of images of the jumping subject selected by the user from the plurality of images of the jumping subject; and

storing a result of analyzing of the priority selection reference in a database.

4. The method of claim 3, wherein the determining of the priorities comprises determining respective priorities for the plurality of images of the jumping subject based on the priority selection reference extracted from the database.

5. The method of claim 3, wherein the priority selection reference includes weights for statistical values of the face recognition information.

6. The method of claim 1, wherein the face recognition information comprises one or more of positions of the faces, the number of the faces, or facial expressions of the faces.

7. The method of claim 1, further comprising generating, based on a user'"'"'s image synthesis request, a synthesized image obtained by synthesizing images of the plurality of images of the jumping subject having the highest priorities based on persons within the images.

8. The method of claim 1, wherein the recognizing of the faces comprises predicting positions of omitted faces if omission of the faces is detected.

9. The method of claim 8, wherein the positions of the omitted faces are predicted using a shutter speed and gravitational acceleration of an image sensor.

10. The method of claim 1, wherein the determining of the priorities comprises determining respective priorities for the plurality of images of the jumping subject based on a priority selection reference input by a user.

11. An apparatus for processing digital images, the apparatus comprising:

a face recognition unit that recognizes faces from a plurality of images of jumping subjects, wherein the plurality of images are continuously captured at a predetermined frame rate;

a priority determination unit that determines respective priorities for the plurality of images of the jumping subjects, wherein an index of the priorities is based on face recognition information, and wherein the priorities are based on an image of the jumping subjects having the largest average of positions of faces, an image of the jumping subjects having the smallest deviation of average of positions of faces, and an image of the jumping subjects having the largest number of faces; and

an image alignment unit that aligns the plurality of images of the jumping subjects based on the priorities.

12. The apparatus of claim 11, wherein the image alignment unit deletes images of the plurality of images of the jumping subject other than a predetermined number of images of the plurality of images of the jumping subject in a priority descending order.

13. The apparatus of claim 11, wherein the priority determination unit analyzes a priority selection reference preferred by a user based on face recognition information of images of the plurality of images of the jumping subject selected by the user from the plurality of images of the jumping subject and stores a result of analyzing the priority selection reference in a database.

14. The apparatus of claim 13, wherein the priority determination unit determines respective priorities for the plurality of images of the jumping subject based on the priority selection reference extracted from the database.

15. The apparatus of claim 14, wherein the priority selection reference includes weights for statistical values of the face recognition information.

16. The apparatus of claim 11, wherein the face recognition information comprises one or more of positions of the faces, the number of the faces, or facial expressions of the faces.

17. The apparatus of claim 11, further comprising a synthesization unit that generates, based on a user'"'"'s image synthesis request, a synthesized image obtained by synthesizing images of the plurality of images of the jumping subject having the highest priorities based on persons within the images.

18. The apparatus of claim 11, wherein the face recognition unit predicts positions of omitted faces if omission of the faces is detected.

19. The apparatus of claim 18, wherein the positions of the omitted faces are predicted based on shutter speed and gravitational acceleration of an image sensor.

20. The apparatus of claim 11, wherein the priority determination unit determines respective priorities for the plurality of images of the jumping subject based on a priority selection reference input by a user.