Automatic selection of digital images with an apparatus

• US 9,268,792 B2
• Filed: 03/05/2011
• Issued: 02/23/2016
• Est. Priority Date: 01/24/2011
• Status: Active Grant

• Current Assignee: T-Mobile USA, Inc. (Deutsche Telekom AG)
• Original Assignee: T-Mobile USA, Inc. (Deutsche Telekom AG)
• Inventors: Morrison, Andrew, Park, Chris, Lau, Kevin, Kishen, Parthu, Smith, Desmond, Bibik, Michael
• Primary Examiner(s): Tran, Nhan T
• Assistant Examiner(s): YODER III, CHRISS S
• Application Number:
  US13/041,361
• Publication Number:
  US 20120188405A1
• Time in Patent Office: 1,816 Days
• Field of Search: 348/231.2, 348/231.3, 348/231.5, 348/231.6, 348/231.99, 707/722, 707/723, 707732-734, 707/736, 707/737
• US Class Current: 1/1
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content

Abstract

Described herein are techniques related to automatic selection of a group of one or more digital images from a set of digital images based, at least in part, upon weighted criteria regarding properties (e.g., metadata or content) of the digital images. This Abstract is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Claims

1. An image-capturing apparatus comprising:

an image-capturing unit configured to capture digital images;

an image-storage unit configured to store captured digital images;

an image-selection unit configured to select a subset of digital images of a set of stored images, wherein the selected subset of digital images includes a group of digital images that are selected in accordance with a binary selection filter and subsequently ranked according to a weighted selection criteria, the binary selection filter to select a pre-subset of digital images to be operated on by the weighted selection criteria to determine the selected subset of digital images;

an image-presentation unit configured to present the selected subset of digital images to a user of the image-capturing apparatus; and

a user-interaction unit configured to attain feedback from the user regarding user-acceptability of the selected subset of digital images presented to the user via the image-presentation unit, the attained feedback being a user initiated removal of a digital image from the selected subset of digital images; and

wherein the image-selection unit is further configured to perform, in response to attained user-feedback indicating a lack of user-acceptability of the selected subset of digital images, a reweighted selection of at least one updated subset of digital images of the set, the reweighted selection including using at least one or more update of the weighted selection criteria, the at least one or more update of the weighted selection criteria having at least one updated weight value compared to at least one weight value associated with the weighted selection criteria, the at least one update weight value established based on the user initiated removal of a digital image from the selected subset of digital images.

2. An image-capturing apparatus as recited in claim 1, wherein the image-selection unit is further configured to perform, in response to attained user-feedback indicating user-acceptability of the selected subset of digital images, one or more defined actions upon the digital images of the confirmed selected subset.

3. An image-capturing apparatus as recited in claim 1 ,wherein each digital image in the pre-subset of digital images includes one or more content properties including an absence of shakiness, an absence of redeye, or an image resolution that is greater than a predefined threshold resolution.

4. One or more non-transitory processor-readable storage devices having processor-executable instructions embodied thereon, the processor-executable instructions, when executed by one or more processors, direct the one or more processors to perform operations comprising:

obtaining a set of digital images; and

selecting at least one subset of digital images of the set based upon a binary selection filter followed by a weighted selection criteria, the binary selection filter to determine a pre-subset of digital images that is operated on by the weighted selection criteria to determine the selected subset of digital images, wherein the selecting includes at least;

grouping the set of digital images into an intermediate grouping that includes two or more of the digital images of the set;

ranking the digital images of the intermediate grouping based upon multiple weighted criteria;

designating an allotment of ranked digital images of the intermediate grouping as the selected subset of digital images;

making the selected subset of digital images accessible by a user;

attaining feedback from the user regarding user-acceptability of the selected subset of digital images, the attained feedback a user initiated removal of a digital image from the selected subset of digital images; and

in response to attained user-feedback indicating a lack of user-acceptability of the selected subset of digital images, performing a reweighted selection of at least one updated subset of digital images of the set, the reweighted selection including using at least one or more update of the multiple weighted criteria, the at least one or more update of the multiple weighted criteria having at least one updated weight value compared to at least one weight value associated with the multiple weighted criteria, the at least one update weight value established based on the user initiated removal of a digital image from the selected subset of digital images.

5. One or more non-transitory processor-readable storage devices as recited in claim 4, further comprising:

responding upon obtaining the user-feedback regarding the user-acceptability of the selected subset of digital images.

6. One or more non-transitory processor-readable storage devices as recited in claim 4, further comprising clustering the set of digital images into multiple clusters, the selected subset of digital images being selected from one of the multiple clusters.

7. A method comprising:

obtaining a set of digital images;

selecting at least one subset of digital images from the set of digital images based upon a binary selection filter followed by a weighted selection criteria, the binary selection filter to select a pre-subset of digital images based at least on one or more of technical metadata, descriptive metadata, or administrative metadata of individual digital images in the set of digital images, the pre-subset of digital images to be operated on by the weighted selection criteria to determine the selected subset of digital images;

attaining feedback from the user regarding user-acceptability of the selected subset of digital images, the attained feedback being a user initiated removal of a digital image from the selected subset of digital images; and

in response to attained user-feedback indicating a lack of user-acceptability of the selected subset of digital images, performing a reweighted selection of at least one updated subset of digital images of the set, the reweighted selection including using at least one or more update of the weighted selection criteria, the at least one or more update of the weighted selection criteria having at least one updated weight value compared to at least one weight value associated with the weighted selection criteria, the at least one update weight value established based the user initiated removal of a digital image from the selected subset of digital images.

8. A method as recited in claim 7, wherein the selecting includes:

segregating the set of digital images into an intermediate grouping based upon whether the digital images match one or more specified criteria;

ranking the digital images of the segregated intermediate grouping based upon multiple weighted criteria; and

designating an allotment of similarly ranked digital images of the segregated intermediate grouping as the selected subset of digital images.

9. A method as recited in claim 8, wherein the designated allotment includes digital images that are ranked amongst the segregated intermediate grouping.

10. A method as recited in claim 8, wherein the designated allotment includes digital images that are bottom ranked amongst the segregated intermediate grouping.

11. A method as recited in claim 8, further comprising calculating a cardinality of the designated allotment based upon a percentage of the segregated intermediate grouping.

12. A method as recited in claim 7, wherein the performance of reweighted selection includes:

adjusting one or more weight values of the weighted criteria;

updating the subset of digital images of the set by reselecting a collection

of digital images from the set based upon the adjusted weighted criteria.

13. A method as recited in claim 7, further comprising, in response to attained user-feedback indicating user-acceptability of the selected subset of digital images, performing one or more defined actions upon the digital images of the confirmed selected subset.

14. A method as recited in claim 13, wherein the defined actions performed on the digital images of the confirmed selected subset is selected from a group consisting of archiving, sharing, and printing.

15. A method as recited in claim 13, wherein the defined actions performed on the digital images of the confirmed selected subset is selected from a group consisting of deleting or recycling.

16. A method as recited in claim 7, wherein the weighted criteria are selected from a group of digital-image properties consisting of image-acquisition location, focus, contrast, shake, red-eye, image content includes a person designated as a favorite of the user, image content includes a person in a list of contacts of the user, photo is tagged, user-added criteria, photo was auto-corrected, photo was post-processed, flash was used, and social-network ranking of a digital image.

17. A method as recited in claim 7, further comprising clustering the set of digital images into multiple clusters, wherein the selected subset of digital images is selected from one or more of the multiple clusters.

18. A method as recited in claim 7, further comprising clustering the subset of digital images into multiple clusters.

19. A method as recited in claim 7, wherein the administrative metadata includes a licensing term, a rights usage term, a specific digital image use restriction, a model release, an identity of an digital image creator, or contact information for a digital image owner.