AUTOMATED IMAGE CROPPING AND SHARING

• US 20160188635A1
• Filed: 09/18/2013
• Published: 06/30/2016
• Est. Priority Date: 09/18/2013
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: SHAH, Shibani, MEINGAST, Marci
• Granted Patent: US 9,633,046 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 3/40 Scaling of whole images or parts thereof, e.g. expanding or contracting
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: H04L 65/75 Media network packet handling
• CPC Class Codes: H04N 23/00 Cameras or camera modules comprising electronic image sensors; Control thereof
• CPC Class Codes: H04N 5/2628 Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation

Abstract

Technologies for automated cropping and sharing of images include an imaging device configured to capture a digital image, recognize one or more subjects represented in the image, determine the social network groups associated with the subjects of the digital image, and crop the digital image to generate one or more sub-images. Each of the sub-images includes subjects associated with a particular social network group. Each of the sub-images may be shared with the relevant social network group. Subjects may include persons, objects, or events, and may be recognized through computer vision techniques as well as using contextual data. The imaging device may receive social network data from one or more social network servers, which may be used to determine the relevant social network groups. The imaging device may also exclude subjects from the cropped sub-images based on one or more content policies. Other embodiments are described and claimed.

Claims

1-25. -25. (canceled)

26. An imaging device for automated image cropping, the imaging device comprising:

an image capture module to capture a digital image;

a subject recognition module to recognize a first subject represented in the digital image;

a social network module to determine a first social network group to which the first subject is associated; and

an image crop module to crop, based on a content rule policy, the digital image to generate a sub-image including the first subject, the composition rule policy comprising a set of rules that define the composition of the sub-image based on the recognized first subject.

27. The imaging device of claim 26, further comprising an image sharing module to share the sub-image with the first social network group.

28. The imaging device of claim 26, wherein to recognize the first subject comprises to:

detect a position and characteristics of a human face represented in the digital image;

detect a position and an identity of an object represented in the digital image;

or

detect an event represented in the digital image.

29. The imaging device of claim 26, wherein to recognize the first subject comprises to recognize an event represented in the digital image based on contextual data received from a contextual sensor of the imaging device.

30. The imaging device of claim 26, wherein to recognize the first subject comprises to recognize an event represented in the digital image based on contextual data generated by an application of the imaging device.

31. The imaging device of claim 26, wherein the social network module is further to receive social network data from a social network server, the social network data to associate the first subject and the first social network group;

wherein to determine the first social network group comprises to determine the first social network group based on the social network data.

32. The imaging device of claim 26, wherein the subject recognition module is further to:

recognize a second subject represented in the digital image; and

determine that the second subject is not associated with the first social network group;

wherein to crop the digital image further comprises to exclude the second subject from the sub-image.

33. The imaging device of claim 32, wherein:

the social network module is further to determine a second social network group to which the second subject is associated, wherein the first subject is not associated with the second social network group;

the image crop module is further to crop, based on a composition rule policy, the digital image to generate a second sub-image including the second subject and excluding the first subject, the composition rule policy comprising a set of rules that define the composition of the second sub-image based on the recognized second subject; and

the imaging device further comprises an image sharing module to (i) share the sub-image with the first social network group and (ii) share the second sub-image with the second social network group.

34. The imaging device of claim 26, wherein the subject recognition module is further to recognize a second subject represented in the digital image;

wherein to crop the digital image further comprises to exclude the second subject from the sub-image as a function of a content policy stored on the imaging device, the content policy comprising a set of rules to define whether to include or to exclude the second subject based on the first social network group.

35. The imaging device of claim 26, wherein:

the subject recognition module is further to recognize a second subject represented in the digital image; and

the social network module is further to determine that the second subject is not associated with the first social network group;

wherein to crop the digital image based on the composition rule policy comprises to;

determine whether a rule of thirds composition rule policy generates an acceptable sub-image including the first subject and excluding the second subject;

determine whether a portrait composition rule policy generates an acceptable sub-image including the first subject and excluding the second subject; and

apply a fallback composition rule policy in response to a determination that the rule of thirds composition rule policy does not generate an acceptable sub-image and a determination that the portrait composition rule policy does not generate an acceptable sub-image, wherein to apply the fallback composition rule policy comprises to;

crop the digital image to generate the sub-image based on a smallest bounding box containing the first subject; and

obscure the second subject in the sub-image.

36. A method for automated image cropping, the method comprising:

capturing, by an imaging device, a digital image;

recognizing, by the imaging device, a first subject represented in the digital image;

determining, by the imaging device, a first social network group to which the first subject is associated; and

cropping, by the imaging device and based on a content rule policy, the digital image to generate a sub-image including the first subject, the composition rule policy comprising a set of rules that define the composition of the sub-image based on the recognized first subject.

37. The method of claim 36, further comprising:

recognizing, by the imaging device, a second subject represented in the digital image; and

determining, by the imaging device, that the second subject is not associated with the first social network group;

wherein cropping the digital image further comprises excluding the second subject from the sub-image.

38. The method of claim 36, further comprising:

recognizing, by the imaging device, a second subject represented in the digital image;

wherein cropping the digital image further comprises excluding the second subject from the sub-image as a function of a content policy stored on the imaging device, the content policy comprising a set of rules to define whether to include or to exclude the second subject based on the first social network group.

39. The method of claim 36, further comprising:

recognizing, by the imaging device, a second subject represented in the digital image; and

determining, by the imaging device, that the second subject is not associated with the first social network group;

wherein cropping the digital image based on the composition rule policy comprises;

determining whether a rule of thirds composition rule policy generates an acceptable sub-image including the first subject and excluding the second subject;

determining whether a portrait composition rule policy generates an acceptable sub-image including the first subject and excluding the second subject; and

applying a fallback composition rule policy in response to determining that the rule of thirds composition rule policy does not generate an acceptable sub-image and determining that the portrait composition rule policy does not generate an acceptable sub-image, wherein applying the fallback composition rule policy comprises;

cropping the digital image to generate the sub-image based on a smallest bounding box containing the first subject; and

obscuring the second subject in the sub-image.

40. One or more computer-readable storage media comprising a plurality of instructions that in response to being executed cause an imaging device to:

capture a digital image;

recognize a first subject represented in the digital image;

determine a first social network group to which the first subject is associated; and

crop, based on a content rule policy, the digital image to generate a sub-image including the first subject, the composition rule policy comprising a set of rules that define the composition of the sub-image based on the recognized first subject.

41. The one or more computer-readable storage media of claim 40, wherein to recognize the first subject comprises to recognize an event represented in the digital image based on contextual data received from a contextual sensor of the imaging device.

42. The one or more computer-readable storage media of claim 40, wherein to recognize the first subject comprises to recognize an event represented in the digital image based on contextual data generated by an application of the imaging device.

43. The one or more computer-readable storage media of claim 40, further comprising a plurality of instructions that in response to being executed cause the imaging device to:

recognize a second subject represented in the digital image; and

determine that the second subject is not associated with the first social network group;

wherein to crop the digital image further comprises to exclude the second subject from the sub-image.

44. The one or more computer-readable storage media of claim 40, further comprising a plurality of instructions that in response to being executed cause the imaging device to:

recognize a second subject represented in the digital image;

wherein to crop the digital image further comprises to exclude the second subject from the sub-image as a function of a content policy stored on the imaging device, the content policy comprising a set of rules to define whether to include or to exclude the second subject based on the first social network group.

45. The one or more computer-readable storage media of claim 40, further comprising a plurality of instructions that in response to being executed cause the imaging device to:

recognize a second subject represented in the digital image; and

determine that the second subject is not associated with the first social network group;

wherein to crop the digital image based on the composition rule policy comprises to;

determine whether a rule of thirds composition rule policy generates an acceptable sub-image including the first subject and excluding the second subject;

determine whether a portrait composition rule policy generates an acceptable sub-image including the first subject and excluding the second subject; and

apply a fallback composition rule policy in response to determining that the rule of thirds composition rule policy does not generate an acceptable sub-image and determining that the portrait composition rule policy does not generate an acceptable sub-image, wherein to apply the fallback composition rule policy comprises to;

crop the digital image to generate the sub-image based on a smallest bounding box containing the first subject; and

obscure the second subject in the sub-image.