Optimizing a visual perspective of media

• US 9,626,768 B2
• Filed: 09/30/2014
• Issued: 04/18/2017
• Est. Priority Date: 09/30/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Tumanov, Ilya, Lee, David Benjamin, Halberstam, Jennifer Michelstein, Freier, Nathaniel George, Farouki, Karim T.
• Primary Examiner(s): Liu, Li
• Application Number:
  US14/503,192
• Publication Number:
  US 20160093059A1
• Time in Patent Office: 931 Days
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models

Abstract

One or more signals are used to identify regions of interest of an image. The signals are applied to the image to generate one or more models that are based on the regions of interest. The models may present different perspectives of the image by emphasizing various features and focal points. The models may be ranked and displayed according to a scoring paradigm that is based on one or more signals. Multi-tiered feedback mechanisms allow for the collection of user intent and/or other forms of explicit input. Feedback associated to the models may be obtained and used to generate additional models that are based on one or more signals and the feedback. The feedback may also be stored and utilized for machine learning purposes.

Claims

1. A computer-implemented method comprising:

obtaining data defining an intended use of an image;

determining a plurality of salient regions or a plurality of invariant regions of the image by applying a plurality of signals to the image;

determining a confidence score for at least one salient region or at least one invariant region of the plurality of salient regions or the plurality of invariant regions, wherein the confidence score is based, at least in part on at least one of a size of an identifiable object in the image, a depth of a color or a luminance variation of the image, an existence of identifiable features of the identifiable object, and an image quality of the image; and

generating a plurality of models, wherein individual models of the plurality of models focus on the at least one salient region or the at least one invariant region of the image, and wherein a selection of the at least one salient region or the at least one invariant region is based on, at least in part, the intended use and the confidence score for the at least one salient region or the at least one invariant region

displaying a transformation of individual models of the plurality of models on an interface;

receiving, at the interface, a gesture input indicating an intent directed toward one or more regions associated with at least one model; and

in response to the gesture input, generating additional models based on the intent.

2. The computer-implemented method of claim 1, wherein individual models of the plurality of models are generated by applying one or more signals to the image to define the at least one salient region or the at least one invariant region of the image, and wherein the computer-implemented method further comprises:

determining a signal score for individual models of the plurality of models;

filtering individual models based on the signal score to determine selected models; and

displaying a transformation of the selected models, wherein an order of the display of the selected models is based on the signal score.

3. The computer-implemented method of claim 2, wherein the signal score is based on a success rating for the plurality of signals that are applied to the image.

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

displaying a transformation of individual models of the plurality of models; and

receiving a selection of a single model of the plurality of models.

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

displaying a transformation of individual models of the plurality of models;

receiving an edit parameter for the image; and

generating an edited model based on the edit parameter.

6. The computer-implemented method of claim 1, wherein determining the plurality of regions of the image comprises utilizing signals for identifying the salient region, the invariant region, a strong line, or a subject included in the image.

7. A computer, comprising:

a processor; and

a computer-readable storage medium in communication with the processor, the computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by the processor, cause the computer to

obtain data defining an intended use of an image,

determine a plurality of regions of the image by applying a plurality of signals to the image,

determine a confidence score for individual regions of the plurality of regions, wherein the confidence score is based, at least in part on at least one of a size of an identifiable object in the image, a depth of a color or a luminance variation of the image, an existence of identifiable features of the identifiable object, and an image quality of the image, and

generate a plurality of models, wherein individual models of the plurality of models define at least one selected region of the image, and wherein the at least one selected region is based on, at least in part, the intended use and the confidence score for the at least one selected region display a transformation of individual models of the plurality of models on an interface;

receive, at the interface, a gesture input indicating an intent directed toward one or more regions associated with at least one model; and

in response to the gesture input, generate additional models based on the intent.

8. The computer of claim 7, wherein individual models of the plurality of models are generated by applying one or more signals to the image to define the at least one selected region of the image, and wherein the computer-readable storage medium has further computer-executable instructions stored thereupon, which when executed by the processor, cause the computer to:

determine a signal score for individual models of the plurality of models;

filter individual models based on the signal score to determine selected models; and

display a transformation of the selected models, wherein an order of display of the selected models is based on the signal score.

9. The computer of claim 8, wherein the signal score is based on a success rating for the one or more signals that are applied to the image.

10. The computer of claim 7, wherein the computer-readable storage medium has further computer-executable instructions stored thereupon, which when executed by the processor, cause the computer to:

display a transformation of individual models of the plurality of models; and

receive a selection of a single model of the plurality of models.

11. The computer of claim 7, wherein the computer-readable storage medium has further computer-executable instructions stored thereupon, which when executed by the processor, cause the computer to:

display a transformation of individual models of the plurality of models;

receive an edit parameter for the image; and

generate an edited model based on the edit parameter.

12. The computer of claim 7, wherein determining the plurality of regions of the image comprises utilizing signals for identifying a salient region, an invariant region, a strong line or a subject included in the image.

13. A computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to:

obtain data defining an intended use of an image;

determine a plurality of salient regions and a plurality of invariant regions of the image by applying a plurality of signals to the image;

determine a confidence score for at least one salient region or at least one invariant region of the plurality of salient regions or the plurality of invariant regions; and

generate a plurality of models, wherein individual models of the plurality of models focus on the at least one salient region or the at least one invariant region of the image, and wherein a selection of the at least one salient region or the at least one invariant region is based on, at least in part, the intended use and the confidence score for the at least one salient region or the at least one invariant region display a transformation of individual models of the plurality of models on an interface;

receive, at the interface, a gesture input indicating an intent directed toward one or more regions associated with at least one model; and

in response to the gesture input, generate additional models based on the intent.

14. The computer-readable storage medium of claim 13, wherein individual models of the plurality of models are generated by applying one or more signals to the image to define the at least one salient region or the at least one invariant region of the image, and wherein the computer-readable storage medium comprises further computer-executable instructions stored thereupon for causing the computer to:

determine a signal score for individual models of the plurality of models;

filter individual models based on the signal score to determine selected models; and

display a transformation of the selected models, wherein an order of the display of the selected models is based on the signal score.

15. The computer-readable storage medium of claim 13, wherein the computer-readable storage medium comprises further computer-executable instructions stored thereupon for causing the computer to:

display a transformation of individual models of the plurality of models; and

receive a selection of a signal model of the plurality of models.

16. The computer-readable storage medium of claim 13, wherein the computer-readable storage medium comprises further computer-executable instructions stored thereupon for causing the computer to:

display a transformation of individual models of the plurality of models;

receive an edit parameter for the image; and

generate an edited model based on the edit parameter.

17. The computer-readable storage medium of claim 13, wherein the computer-readable storage medium comprises further computer-executable instructions stored thereupon for causing the computer to:

store data defining the intent in a datastore;

obtain data defining a second intended use of a second image;

determine a second plurality of regions of the second image by applying a second plurality of signals to the second image, wherein selection of at least one region of the second plurality of regions based, at least in part on the intent; and

generate at least one model from the second image based on the second plurality of regions of the second image.