SYSTEM AND METHODS FOR CREATING A COLLECTION OF IMAGES

• US 20130011083A1
• Filed: 02/17/2011
• Published: 01/10/2013
• Est. Priority Date: 02/17/2010
• Status: Active Grant

• Current Assignee: Shutterfly, LLC
• Original Assignee: Photoccino Ltd. (Shutterfly, LLC)
• Inventors: Kenis, Alexander, Cohen, Eran, Berkovich, Moshe
• Granted Patent: US 8,861,897 B2
• Time in Patent Office: Days
• 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 method for creating a collection of images, 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.

2. A method according to claim 1, wherein said processing further comprising grouping related clusters of related images to chapters, wherein said output collection of images further comprises chapters of related clusters.

3. A method according to claim 2, wherein said grouping related clusters of related images to chapters comprising:

calculating differences of parameters between subsequent clusters;

calculating a topological space based on said parameters;

calculating topological distance upon said topological space between subsequent clusters, based on the calculated differences; and

separating between chapters where the topological distance between subsequent clusters is larger than a certain determined threshold.

4. A method according to claim 2, wherein said processing further comprising ascribing name tags to chapters based on image analysis and data base of previous name tags provided by at least one user.

5. A method according to claim 1, wherein said processing comprises ranking the images, the ranking comprising:

learning ranking preferences of at least one user; and

ranking the images based on the learned ranking preferences.

6. A method according to claim 5, wherein said ranking further comprising:

determining a general rank of an image;

determining a rank of photographed objects of interest, the objects of interest are of a list comprising people, faces and objects; and

combining the rank of the photographed objects of interest with the general image rank to determine the image rank.

7. A method according to claim 5, wherein said ranking further comprising ranking at least one cluster according to the ranking of the images in the cluster.

8. A method according to claim 1, wherein said grouping to clusters comprises:

grouping the images to base clusters of time-related images, wherein, within a base cluster of time-related images, capture time difference between subsequent images is smaller than a predetermined threshold; and

dividing the base clusters to sub-clusters of related images according to image analysis parameters.

9. A method according to claim 1, wherein said grouping to clusters comprises:

grouping the images to sub-clusters of related images according to image analysis parameters; and

grouping subsequent sub-clusters to clusters of related images.

10. A method according to claim 5, wherein said selecting the preferred images in the clusters comprising:

determining the number of images to be selected from a certain cluster; and

identifying and selecting the suitable number of best-ranked images in the sub-cluster.

11. A system for creating a collection of images, the system 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, the output collection of images comprising the clusters of related images and indication of the preferred images in the clusters; and

a collection output medium for outputting the output collection of images.

12. A non-transitory processor-readable storage medium having instructions stored thereon that, when executed by a processor, result in:

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.

13. A non-transitory processor-readable storage medium according to claim 12, wherein said instructions stored thereon, when executed by a processor, further result in grouping related clusters of related images to chapters, wherein said output collection of images further comprises chapters of related clusters.

14. A non-transitory processor-readable storage medium according to claim 13, wherein said instructions stored thereon, when executed by a processor, further result in:

calculating differences of parameters between subsequent clusters;

calculating a topological space based on said parameters;

calculating topological distance upon said topological space between subsequent clusters, based on the calculated differences; and

separating between chapters where the topological distance between subsequent clusters is larger than a certain determined threshold.

15. A non-transitory processor-readable storage medium according to claim 13, wherein said instructions stored thereon, when executed by a processor, further result in ascribing name tags to chapters based on image analysis and data base of previous name tags provided by at least one user.

16. A non-transitory processor-readable storage medium according to claim 12, wherein said instructions stored thereon, when executed by a processor, further result in ranking the images, the ranking comprising:

learning ranking preferences of at least one user; and

ranking the images based on the learned ranking preferences.

17. A non-transitory processor-readable storage medium according to claim 16, wherein said instructions stored thereon, when executed by a processor, further result in:

determining a general rank of an image;

determining a rank of photographed objects of interest, the objects of interest are of a list comprising people, faces and objects; and

combining the rank of the photographed objects of interest with the general image rank to determine the image rank.

18. A non-transitory processor-readable storage medium according to claim 16, wherein said instructions stored thereon, when executed by a processor, further result in ranking at least one cluster according to the ranking of the images in the cluster.

19. A non-transitory processor-readable storage medium according to claim 12, wherein said instructions stored thereon, when executed by a processor, further result in:

grouping the images to base clusters of time-related images, wherein, within a base cluster of time-related images, capture time difference between subsequent images is smaller than a predetermined threshold; and

dividing the base clusters to sub-clusters of related images according to image analysis parameters.

20. A non-transitory processor-readable storage medium according to claim 12, wherein said instructions stored thereon, when executed by a processor, further result in:

grouping the images to sub-clusters of related images according to image analysis parameters; and

grouping subsequent sub-clusters to clusters of related images.

21. A non-transitory processor-readable storage medium according to claim 16, wherein said instructions stored thereon, when executed by a processor, further result in:

determining the number of images to be selected from a certain cluster; and

identifying and selecting the suitable number of best-ranked images in the sub-cluster.