Representative image selection for image management using face recognition

Patent metadata

Field	Value
Publication number	US-9858296-B2
Application number	US-201615086642-A
Country	US
Kind code	B2
Filing date	Mar 31, 2016
Priority date	Mar 31, 2016
Publication date	Jan 2, 2018
Grant date	Jan 2, 2018

Abstract

A technique for selecting a representative image from a group of digital images includes extracting data representing an image of a face of a person from each image in the group using a face recognition algorithm, determining a score for each image based on one or more quality parameters that are satisfied for the respective image, and selecting the image having the highest score as the representative image for the group. The quality parameters may be based on any quantifiable characteristics of the data. Each of these quality parameters may be uniquely weighted, so as to define the relative importance of one parameter with respect to another. The score for determining the representative image of the group may be obtained by adding together the weights corresponding to each quality parameter that is satisfied for a given image. Once selected, the representative image may be displayed in a graphical user interface.

First claim

What is claimed is:

1. A computer-implemented method for selecting a representative image from a group of digital images of a particular person, the method comprising:
extracting, by a computing device and using a face recognition algorithm, data representing a facial expression of the particular person from each image in the group;
determining, by the computing device and using the data, a score for each image in the group based on one or more quality parameters that are satisfied for each image;
selecting, by the computing device, an image in the group having a maximum score as the representative image for the group;
adding, by the computing device, a new image of the particular person to the group, wherein the new image is acquired and added to the group after the representative image is selected;
extracting, by the computing device and using the face recognition algorithm, new data representing a new facial expression of the particular person from the new image;
determining, by the computing device and using the new data, a score of the new image based on one or more quality parameters that are satisfied for the new image;
determining that the score for the new image is greater than the maximum score associated with the representative image; and
selecting, by the computing device, the new image as a new representative image for the group.

2. The method of claim 1 , further comprising displaying the new representative image in a graphical user interface of a display device, wherein the graphical user interface is configured to provide user access to the images in the group.

3. The method of claim 1 , further comprising:
removing, from the group and by the computing device, the image in the group having the maximum score; and
selecting, by the computing device and subsequent to removing the image having the maximum score from the group, an image in the group having a new maximum score as a second new representative image for the group.

4. The method of claim 1 , wherein the score for each image in the group is determined by adding together weights associated with each of the quality parameters that are satisfied for the respective image.

5. The method of claim 4 , wherein each of the weights is a unique number in a sequence of numbers.

6. The method of claim 5 , wherein the sequence includes 2, 4, 8, 16, 32, 64, 128 and 256.

7. The method of claim 1 , wherein the quality parameters include at least one of:
image exposure is good;
color/gray scale profile;
eyes of subject are open;
mouth of the particular person is closed;
the particular person is not wearing eyeglasses;
the particular person is not wearing a hat;
the particular person is facing a camera;
an entire face of the particular person is visible;
focus of the image is good;
sharpness of facial features is good;
image resolution is high;
age of the image is low; and
only one face appears in the image.

8. A system for selecting a representative image from a group of digital images of a particular person, the system comprising:
a storage; and
a computer processor operatively coupled to the storage, the computer processor configured to execute instructions stored in the storage to perform a process that comprises:
extracting, using a face recognition algorithm, data representing a facial expression of the particular person from each image in the group;
determining, using the data, a score for each image in the group based on one or more quality parameters that are satisfied for each image;
selecting an image in the group having a maximum score as the representative image for the group;
adding a new image of the particular person to the group, wherein the new image is acquired and added to the group after the representative image is selected;
extracting, using the face recognition algorithm, new data representing a new facial expression of the particular person from the new image;
determining, using the new data, a score of the new image based on one or more quality parameters that are satisfied for the new image;
determining that the score for the new image is greater than the maximum score associated with the representative image; and
selecting the new image as a new representative image for the group.

9. The system of claim 8 , further comprising a display device operatively coupled to the computer processor and configured to display the new representative image in a graphical user interface, wherein the graphical user interface is configured to provide user access to the images in the group.

10. The system of claim 8 , wherein the computer processor is further configured to:
remove, from the group, the image in the group having the maximum score; and
select, subsequent to removing the image having the maximum score from the group, an image in the group having a new maximum score as a second new representative image for the group.

11. The system of claim 8 , wherein the score for each image in the group is determined by adding together weights associated with each of the quality parameters that are satisfied for the respective image.

12. The system of claim 11 , wherein each of the weights is a unique number in a sequence of numbers.

13. The system of claim 12 , wherein the sequence includes 2, 4, 8, 16, 32, 64, 128 and 256.

14. The system of claim 8 , wherein the quality parameters include at least one of:
image exposure is good;
color/gray scale profile;
eyes of subject are open;
mouth of the particular person is closed;
the particular person is not wearing eyeglasses;
the particular person is not wearing a hat;
the particular person is facing a camera;
an entire face of the particular person is visible;
focus of the image is good;
sharpness of facial features is good;
image resolution is high;
age of the image is low; and
only one face appears in the image.

15. A non-transitory computer program product having instructions encoded thereon that when executed by one or more computer processors cause the one or more computer processors to perform a process comprising:
extracting, using a face recognition algorithm, data representing a facial expression of a particular person from each image in a group of digital images;
determining, using the data, a score for each image in the group based on one or more quality parameters that are satisfied for each image;
selecting an image in the group having a maximum score as the representative image for the group;
adding a new image of the particular person to the group, wherein the new image is acquired and added to the group after the representative image is selected;
extracting, using the face recognition algorithm, new data representing a new facial expression of the particular person from the new image;
determining, using the new data, a score of the new image based on one or more quality parameters that are satisfied for the new image;
determining that the score for the new image is greater than the maximum score associated with the representative image; and
selecting the new image as a new representative image for the group.

16. The non-transitory computer program product of claim 15 , wherein the process further comprises displaying the new representative image in a graphical user interface of a display device, wherein the graphical user interface is configured to provide user access to the images in the group.

17. The non-transitory computer program product of claim 15 , wherein the score for each image in the group is determined by adding together weights associated with each of the

Assignees

• Adobe Systems Inc

Inventors

• Gupta Angad Kumar
• Singh Alok Kumar
• Purumala Ram Prasad

Classifications

• G06V10/772

  Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06V10/993

  Evaluation of the quality of the acquired pattern · CPC title

• G06T2207/30168

  Image quality inspection · CPC title

• G06F17/3028

  Physics · mapped topic