Object oriented image editing

Patent metadata

Field	Value
Publication number	US-9569697-B1
Application number	US-201514626063-A
Country	US
Kind code	B1
Filing date	Feb 19, 2015
Priority date	Feb 19, 2015
Publication date	Feb 14, 2017
Grant date	Feb 14, 2017

Abstract

Implementations generally relate to object based image editing. In some implementations, a method includes segmenting an image into object data by identifying one or more object classifications in the image and storing at least one locator for one or more regions of the image corresponding to each instance of the object classification. The method further includes receiving a selection of a representative portion of the segmented image from a user, and matching the representative portion with the object data to determine at least one matched object classification associated with the representative portion. The method further includes presenting the user with one or more of the matched object classifications for the user to instruct one or more edit operations to be applied to at least one object represented by the matched object classification.

First claim

What is claimed is:

1. A computer implemented method comprising:
segmenting an image into regions of one or more objects in the image and storing object locator information for the regions of the image corresponding to each instance of the one or more objects;
subsegmenting at least one of the one or more objects into component regions and storing sub-object locator information for the respective component regions;
classifying the component regions into respective sub-object classifications;
receiving a selection of a representative portion of the image from a user;
matching the representative portion with the sub-object locator information to determine at least one-matched sub-object classification from the sub-object classifications;
presenting the user with one or more of the at least one matched sub-object classification; and
receiving a user request to apply one or more edit operations to at least one sub-object represented by the matched sub-object classification.

2. The method of claim 1 , further including generating a mask corresponding to the at least one matched sub-object classification, wherein the mask is based on the at least one sub-object locator information for the respective at least one matched sub-object classification, and wherein presenting the at least one matched sub-object classification is by displaying the mask.

3. The method of claim 1 , wherein presenting the at least one matched sub-object classification is in hierarchical sequential order in response to a user request.

4. The method of claim 1 , further including presenting to the user the one or more object classifications identified in the image, and wherein selecting the representative portion is in response to presenting the one or more object classifications.

5. The method of claim 1 , further including storing the one or more edit operations and storing the at least one matched sub-object classification.

6. The method of claim 5 , further including providing a second image and applying the edit operations to at least one second image sub-object identified by the at least one matched sub-object classification stored.

7. The method of claim 1 , further including presenting the user with one or more recommended edit operations based on the at least one matched sub-object classification.

8. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
segmenting an image into regions of one or more objects in the image and storing object locator information for the regions of the image corresponding to each instance of the one or more objects;
subsegmenting at least one of the one or more objects into component regions and storing sub-object locator information for the respective component regions;
classifying the component regions into respective sub-object classifications;
receiving a selection of a representative portion of the image from a user;
matching the representative portion with the sub-object locator information to determine at least one matched sub-object classification representing at least one respective sub-object in the image, from the sub-object classifications;
presenting the user with one or more of the at least one matched sub-object classification;
receiving a user request to apply one or more edit operations to at least one sub-object represented by the matched sub-object classification; and
applying the one or more edit operations to the at least one respective sub-object in the image.

9. The computer-readable medium of claim 8 , further including generating a mask corresponding to the at least one matched sub-object classification, wherein the mask is based on the at least sub-object locator information for the respective at least one matched sub-object classification, and wherein presenting the at least one matched sub-object classification is by displaying the mask.

10. The computer-readable medium of claim 8 , wherein presenting the at least one matched sub-object classification is in hierarchical sequential order in response to a user request.

11. The computer-readable medium of claim 8 , further including presenting to the user the one or more object classifications identified in the image, and wherein selecting the representative portion is in response to presenting the one or more object classifications.

12. The computer-readable medium of claim 8 , further including storing the one or more edit operations and storing the at least one matched sub-object classification.

13. The computer-readable medium of claim 12 , further including providing a second image and applying the edit operations to at least one second image sub-object identified by at least one the matched sub-object classification stored.

14. The computer-readable medium of claim 8 , further including presenting the user with one or more recommended edit operations based on the at least one matched sub-object classification.

15. A system comprising:
one or more processors; and
one or more computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
segmenting an image into regions of one or more objects in the image and storing object locator information for the regions of the image corresponding to each instance of the one or more objects;
subsegmenting at least one of the one or more objects into component regions and storing sub-object locator information for the respective component regions;
classifying the component regions into respective sub-object classifications;
receiving a selection of a representative portion of the image from a user;
matching the representative portion with the sub-object locator information to determine at least one-matched sub-object classification from the sub-object classifications;
presenting the user with one or more of the at least one matched sub-object classification; and
receiving a user request to apply one or more edit operations to at least one sub-object represented by the matched sub-object classification.

16. The system of claim 15 , further including generating a mask corresponding to the at least one matched sub-object classification, wherein the mask is based on the at least one sub-object locator information for the respective at least one matched sub-object classification, and wherein presenting the at least one matched sub-object classification is by displaying the mask.

17. The system of claim 15 , further including presenting to the user the one or more object classifications identified in the image, and wherein selecting the representative portion is in response to presenting the one or more object classifications.

Assignees

• Google Inc

Inventors

• McNerney Peter Joseph
• Miller Nolan Andrew

Classifications

• G06T7/11

  Region-based segmentation · CPC title

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06K9/6267 Primary

  Physics · mapped topic