System and methods for creating a collection of images

• US 8,861,897 B2
• Filed: 02/17/2011
• Issued: 10/14/2014
• Est. Priority Date: 02/17/2010
• Status: Active Grant

• Current Assignee: Shutterfly, LLC
• Original Assignee: Shutterfly Incorporated (Shutterfly, LLC)
• Inventors: Bercovich, Moshe, Kenis, Alexander, Cohen, Eran
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): RIVERA-MARTINEZ, GUILLERMO M
• Application Number:
  US13/520,325
• Publication Number:
  US 20130011083A1
• Time in Patent Office: 1,335 Days
• Field of Search: None
• US Class Current: 382/305
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/53 Querying
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions
• CPC Class Codes: G06F 18/24 Classification techniques

Abstract

System and method for creating a collection of images are described, the method comprising: receiving images from at least one source of images; processing the images to produce an output collection of images, the processing comprising grouping the images to clusters of related images and selecting the preferred images in the clusters; and outputting the output collection of images, the output collection of images comprising the clusters of related images and indication of the preferred images in the clusters. The system for creating a collection of images comprising: a storage medium to receive images from at least one source of images; a processor to produce an output collection of images by grouping the images to clusters of related images and selecting the preferred images in the clusters; and a collection output medium for outputting the output collection of images.

Claims

1. A computer implemented method for grouping and selecting images, comprising:

determining capture times of a set of images;

chronologically ordering the images in the set of images;

calculating capture time differences dT between capture times of successive images in the set of chronologically ordered images;

identifying a maximum capture time difference dTmax in the capture time differences dT between successive images in the set of images;

determining a cluster-splitter range of time differences at least in part based on the maximum capture time difference dTmax; and

dividing a plurality of images, based on the cluster-splitter range of time differences, into multiple base clusters each comprising successive images.

2. The computer implemented method of claim 1, wherein the step of determining a cluster-splitter range of time differences comprises:

identifying, in the set of images, capture time differences dT that are within a range between A*dTmax and dTmax, wherein A is a constant factor between 0 and 1; and

calculating a standard deviation S of the capture time differences dT that are within a range between A*dTmax and dTmax,

wherein the cluster-splitter range of time differences in part based on the standard deviation S of the capture time differences dT that are within a range between A*dTmax and dTmax.

3. The computer implemented method of claim 2, wherein A is between 0.3 and 0.8.

4. The computer implemented method of claim 2, wherein the step of determining a cluster-splitter range of time differences comprises:

calculating a mean capture time difference B for the capture time differences dT that are within a range between A*dTmax and dTmax,

wherein the cluster-splitter range of time differences is defined between B-M*S and dTmax, wherein M is a constant factor between 1 and 3.

5. The computer implemented method of claim 1, wherein successive base clusters in the multiple of base clusters are separated by capture time differences in the cluster-splitter range of time differences.

6. The computer implemented method of claim 1, wherein image capture time differences be successive images in each of the base clusters are smaller compared to capture time differences between successive base clusters.

7. The computer implemented method of claim 1, further comprising:

dividing one of the multiple base clusters into multiple sub-clusters of image if the one of the multiple base clusters includes more than a predetermined number of images.

8. The computer implemented method of claim 1, further comprising:

dividing one of the multiple base clusters into multiple sub-clusters of image if two successive images in the one of the multiple base clusters have a capture time difference that is larger than a predefined threshold value.

9. The computer implemented method of claim 1, further comprising:

calculating differences between at least two successive base clusters; and

grouping the two successive base clusters into a chapter if the difference is smaller than a predetermined threshold.

10. The computer implemented method of claim 1, further comprising:

ranking images in at least one of the base clusters to produce image ranks; and

selecting images in the one of the base clusters.

11. The computer implemented method of claim 10, further comprising:

ranking the multiple base clusters at least in part based on the image ranks in the respective base clusters.

12. A computer implemented method for grouping and selecting images, comprising:

determining capture times of a set of images;

chronologically ordering the images in the set of images;

calculating capture time differences dT between capture times of successive images in the set of chronologically ordered images;

calculating a standard deviation S of the capture time differences dT in at least a portion of the set of images;

determining a cluster-splitter range of time differences at least in part based on the standard deviation S; and

dividing a plurality of images, based on the cluster-splitter range of time differences, into multiple base clusters each comprising successive images.

13. The computer implemented method of claim 12, wherein the step of determining a cluster-splitter range of time differences comprises:

identifying a maximum capture time difference dTmax in the capture time differences dT between successive images in the set of images; and

identifying, in the set of images, capture time differences dT that are within a range between A*dTmax and dTmax, wherein A is a constant factor between 0 and 1,

wherein the standard deviation S is calculated using the capture time differences dT that are within a range between A*dTmax and dTmax.

14. The computer implemented method of claim 13, wherein the step of determining a cluster-splitter range of time differences comprises:

calculating a mean capture time difference B for the capture time differences dT that are within a range between A*dTmax and dTmax,

wherein the cluster-splitter range of time differences is defined between B-M*S and dTmax, wherein M is a constant factor between 1 and 3.

15. The computer implemented method of claim 12, wherein successive base clusters in the multiple of base clusters are separated by capture time differences in the cluster-splitter range of time differences.

16. The computer implemented method of claim 12, further comprising:

dividing one of the multiple base clusters into multiple sub-clusters of image if the one of the multiple base clusters includes more than a predetermined number of images.

17. The computer implemented method of claim 12, further comprising:

dividing one of the multiple base clusters into multiple sub-clusters of image if two successive images in the one of the multiple base clusters have a capture time difference that is larger than a predefined threshold value.

18. The computer implemented method of claim 12, further comprising:

ranking images in at least one of the base clusters to produce image ranks; and

selecting images in the one of the base clusters.

19. A computer implemented method for grouping and selecting images, comprising:

determining capture times of a set of images;

chronologically ordering the images in the set of images;

calculating capture time differences dT between capture times of successive images in the set of chronologically ordered images;

calculating a mean capture time difference B for at least a portion of the set of images;

determining a cluster-splitter range of time differences at least in part based on the mean capture time difference B; and

dividing a plurality of images, based on the cluster-splitter range of time differences, into multiple base clusters each comprising successive images.

20. The computer implemented method of claim 19, wherein the step of determining a cluster-splitter range of time differences comprises:

identifying a maximum capture time difference dTmax in the capture time differences dT between successive images in the set of images;

identifying, in the set of images, capture time differences dT that are within a range between A*dTmax and dTmax, wherein A is a constant factor between 0 and 1; and

calculating a standard deviation S of the capture time differences dT that are within a range between A*dTmax and dTmax.

21. The computer implemented method of claim 20, wherein the mean capture time difference B is calculated for the capture time differences dT that are within a range between A*dTmax and dTmax, wherein the cluster-splitter range of time differences is defined between B-M*S and dTmax, wherein M is a constant factor between 1 and 3.