Image subset determination and processing

Patent metadata

Field	Value
Publication number	US-9311337-B2
Application number	US-201313743598-A
Country	US
Kind code	B2
Filing date	Jan 17, 2013
Priority date	Dec 20, 2012
Publication date	Apr 12, 2016
Grant date	Apr 12, 2016

Abstract

Aspects of a device, system, and method for subset determination and processing are described. In certain aspects, a process for subset determination includes determining a reference for correlation with at least one image and identifying a set of images for comparison with the reference. The reference for correlation may be specified by a user based on a desire to determine a subset of certain images from a larger group. The process further includes determining a subset of the set of images based on a correlation between the reference and the set of images. According to various features, a subset of images that not only includes certain images but also excludes certain images may be determined quickly.

First claim

The invention claimed is:

1. A method for subset determination, comprising:
monitoring a condition of an onset rule, the onset rule including a predetermined user condition;
selecting a plurality of portions of an image, each of the plurality of portions including a corresponding object;
determining, when the condition of the onset rule is satisfied, the corresponding objects in the image as references for correlation with at least one image;
identifying a set of images for comparison with the references;
identifying the corresponding objects within the set of images based on a correlation between the references and the set of images;
determining, by a processor, a subset of the set of images based on the correlation between the references and the set of images; and
processing the subset of the set of images according to application of a subset rule.

2. The method of claim 1 , wherein the references comprise an image reference metric from a database of predefined image references.

3. The method of claim 2 , further comprising:
receiving feedback based on an evaluation of subset accuracy; and
updating the database of the predefined image references according to the feedback.

4. The method of claim 1 , further comprising:
monitoring conditions of the onset rule; and
when the conditions of the onset rule are satisfied, prompting for selection of the references for correlation or identifying the references for correlation according to a parameter of a predetermined subset routine.

5. The method of claim 4 , wherein:
the onset rule comprises at least one of a timing-, location-, or resource-based rule,
the timing-based rule comprises one of a time of day, day of week, or predetermined date rule,
the location-based rule comprises one of a relative or absolute location rule, and
the resource-based rule comprises one of an available memory capacity, available battery level, or available communications signal strength rule.

6. The method of claim 1 , wherein the processing the subset comprises transferring the subset of the set of images to a predetermined destination according to a parameter of a predetermined subset routine.

7. The method of claim 1 , wherein the determining the subset of the set of images comprises, for each image of the set of images, correlating the image of the set of images with the references for correlation to determine whether a portion of the image of the set of images correlates with the references by at least a predetermined correlation threshold.

8. The method of claim 1 , wherein the determining the subset of the set of images further comprises determining the subset based in part on metadata of the set of images.

9. The method of claim 1 , wherein:
the references for correlation comprise a reference for inclusion and a reference for exclusion, and
the determining the subset of the set of images comprises, for each image of the set of images:
correlating the image of the set of images with the references for inclusion and exclusion;
adding the image of the set of images to the subset of the set of images when the image of the set of images correlates with the reference for inclusion and does not correlate with the reference for exclusion; and
excluding the image of the set of images from the subset of the set of images when the image of the set of images correlates with the reference for exclusion.

10. The method of claim 1 , further comprising:
determining whether the subset of the set of images is assigned the subset rule prior to processing the subset of the set of images according to application of the subset rule.

11. A non-transitory computer-readable medium storing computer readable instructions thereon that, when executed by a processor, direct the processor to perform a method for subset determination, comprising:
selecting a plurality of portions of an image, each of the plurality of portions including a corresponding object;
monitoring a condition of an onset rule, the onset rule including a predetermined user condition;
determining, when the condition of the onset rule is satisfied, the corresponding objects in the image as references for correlation with at least one image;
identifying the corresponding objects within a set of images based on a correlation between the references and the set of images;
determining a subset of the set of images based on the correlation between the references and the set of images; and
processing the subset of the set of images according to application of a subset rule.

12. The non-transitory computer-readable medium of claim 11 , further comprising:
receiving feedback based on an evaluation of subset accuracy; and
updating a database of predefined image references according to the feedback.

13. The non-transitory computer-readable medium of claim 11 , further comprising, when conditions of the onset rule are satisfied, prompting for selection of the references for correlation or identifying the references for correlation according to a parameter of a predetermined subset routine.

14. The non-transitory computer-readable medium of claim 11 , wherein:
the onset rule comprises at least one of a timing-, location-, or resource-based rule,
the timing-based rule comprises one of a time of day, day of week, or predetermined date rule,
the location-based rule comprises one of a relative or absolute location rule, and
the resource-based rule comprises one of an available memory capacity, available battery level, or available communications signal strength rule.

15. The non-transitory computer-readable medium of claim 11 , wherein:
the references for correlation comprise a reference for inclusion and a reference for exclusion, and
the determining the subset of the set of images comprises, for each image of the set of images:
correlating the image of the set of images with the references for inclusion and exclusion;
adding the image of the set of images to the subset of the set of images when the image of the set of images correlates with the reference for inclusion and does not correlate with the reference for exclusion; and
excluding the image of the set of images from the subset of the set of images when the image of the set of images correlates with the reference for exclusion.

16. An apparatus for subset determination, comprising:
a memory that stores data and images; and
a processor communicatively coupled to the memory and configured to:
select a plurality of portions of an image, each of the plurality of portions including a corresponding object;
monitor a condition of an onset rule, the onset rule including a predetermined user condition;
determine, when the condition of the onset rule is satisfied, the corresponding objects in the image as references for correlation with at least one image;
identify the corresponding objects within a set of images based on a correlation between the references and the set of images; and
determine a subset of the set of images based on the correlation between the references and the set of images.

17. The apparatus of claim 16 , wherein the processor is further configured to:
receive feedback based on an evaluation of subset accuracy, and
update a database of predefined image references according to the feedback.

18. The apparatus of claim 16 , wherein the processor is further configured to, when conditions of the onset rule are satisfied, prompt for selection of the references for correlation or identify the references for correlation according to a parameter of a predetermined subs

Assignees

• Broadcom Corp

Inventors

• Mese Murat

Classifications

• G06F16/583 Primary

  using metadata automatically derived from the content · CPC title

• G06F17/30247 Primary

  Physics · mapped topic