# US 2017/0287183 A1 · Scaling and masking of image content during digital image editing

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0287183 A1
- Document ID: US20170287183A1
- Status: Published application
- Kind: A1
- Application number: 15/090,359
- Filed: 2016-04-04
- Published: 2017-10-05
- Earliest claimed: 2016-04-04
- Assignees: Adobe Systems Incorporated
- Applicants: Adobe Systems Incorporated
- Inventors: Nishant Kumar; Phaneendra Angara
- Web page: https://patentgrep.com/patent/US20170287183A1

## CPC

- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 11/60: Creating or editing images; Combining images with text
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present disclosure is directed towards systems and methods for modifying and scaling content within a digital image. For example, systems and methods described herein involve identifying source content to add to a destination image. The source content includes one or more detected objects. The systems and methods further involve scaling the source content based on a size of one or more detected objects within the destination image. Additionally, the systems and methods involve displaying the source content within the destination image while preventing portions of the source content from interfering with one or more protected regions corresponding to the one or more detected objects within the destination image. In this way, the systems and methods enable adding source content to a destination image while minimizing manual modifications to blend the source content into the display of the destination image.

## Claims

### Claim 1

In a digital medium environment for editing digital images, a method for intelligently adding content to a digital image, the method comprising:
identifying source content to be added to a destination image, the source content comprising an identified object;
identifying, by at least one processor and within the destination image, one or more protected regions of the destination image, the one or more protected regions of the destination image comprising a plurality of detected objects; and
displaying, by the at least one processor and within a graphical user interface of an image editing application, the source content at a first position within the destination image, wherein displaying the source content at the first position comprises:
preventing the source content from interfering with the one or more protected regions of the destination image;
determining that a first object of the plurality of detected objects is the closest of the plurality of detected objects to the first position; and
scaling the source content to correspond to a size of the first object of the plurality of detected objects by sizing the source content based on the size of the first object and a relative position between the first object and the first position.

### Claim 2 (depends on 1)

The method as recited in claim 1, further comprising displaying, by the at least one processor and within the graphical user interface of the image editing application, the source content at a second position within the destination image, wherein displaying the source content at the second position comprises rescaling the source content to correspond to a size of a second object of the plurality of detected objects based on a determination that the second object is associated with the second position.

### Claim 3 (depends on 2)

The method as recited in claim 2, further comprising detecting a user input causing a relocation of the source content from the first position within the destination image to the second position within the destination image, wherein displaying the source content at the second position comprises displaying the source content at the second position in response to detecting the user input causing the relocation of the source content from the first position within the destination image to the second position within the destination image.

### Claim 4 (depends on 1)

The method as recited in claim 1, wherein identifying the one or more protected regions of the destination image comprises generating a binary mask image representing the plurality of detected objects.

### Claim 5 (depends on 1)

The method as recited in claim 1, wherein identifying the one or more protected regions of the destination image comprises:
identifying a plurality of faces and associated upper bodies of people within the destination image; and
classifying the plurality of faces and associated upper bodies of people within the destination image as protected content of the destination image.

### Claim 6 (depends on 1)

The method as recited in claim 1, further comprising:
determining that a portion of the source content at the first position overlaps a portion of the one or more protected regions of the destination image; and
masking the portion of the source content that overlaps the portion of the one or more protected regions.

### Claim 7 (depends on 6)

The method as recited in claim 6, further comprising providing a selectable option to override the masking of the portion of the source content.

### Claim 8 (depends on 7)

The method as recited in claim 7, further comprising:
receiving a selection of the selectable option to override the masking of the portion of the source content; and
in response to receiving the selection of the selectable option, displaying the portion of the source content.

### Claim 9 (depends on 6)

The method as recited in claim 6, further comprising:
identifying, within the portion of the one or more protected regions that overlaps the portion of the source content, multiple sections corresponding to multiple respective objects of the plurality of detected objects; and
providing, for each of the multiple sections, a selectable option to override the masking of the source content.

### Claim 10 (depends on 9)

The method as recited in claim 9, further comprising:
receiving a selection of a first selectable option corresponding to a first section of the multiple sections of a protected region; and
in response to receiving the selection of the first selectable option, displaying a corresponding portion of the source content that overlaps the first section.

### Claim 11 (depends on 1)

The method as recited in claim 1, wherein scaling the source content comprises scaling the source content such that the identified object of the source content has a size corresponding to the size of the first object of the plurality of detected objects.

### Claim 12 (depends on 1)

The method as recited in claim 1, wherein scaling the source content comprises scaling the source content based on a Euclidean distance between the identified object of the source content and the first object of the plurality of detected objects.

### Claim 13 (depends on 1)

The method as recited in claim 1, wherein scaling the source content comprises scaling the source content based on a difference in horizontal position between the identified object of the source content and the first object of the plurality of detected objects.

### Claim 14

In a digital medium environment for editing digital images, a method for modifying and scaling content within a digital image, comprising:
identifying a cutout of a source image to be added to a destination image, the cutout of the source image comprising a face;
detecting, by at least one processor, a plurality of faces within the destination image;
displaying, by the at least one processor and within a graphical user interface of an image editing application, the cutout at a first position within the destination image, wherein displaying the cutout at the first position comprises scaling the cutout to correspond to a size of a first detected face of the plurality of detected faces based on a determination that the first detected face is the closest of the plurality of detected faces to the first position;
detecting a user input comprising a selection and movement of the cutout within the destination image, the movement causing the face of the cutout to move away from the first position and toward a second position within the destination image;
in response to detecting the movement of the cutout away from the first position and toward the second position, rescaling, by the at least one processor, the size of the cutout to correspond to a size of a second detected face of the plurality of detected faces based on a determination that the second detected face is the closest of the plurality of detected faces to the second position.

### Claim 15 (depends on 14)

The method as recited in claim 14, wherein detecting the user input comprising the selection and the movement of the cutout comprises a user selection of the cutout and a movement along a path between the first position and the second position.

### Claim 16 (depends on 14)

The method as recited in claim 14, wherein resealing the size of the cutout is performed while the cutout moves away from the first position and toward the second position.

### Claim 17 (depends on 14)

The method as recited in claim 14, wherein resealing the size of the cutout comprises resealing the size of the cutout to correspond to a size between the size of the first detected face and the size of the second detected face.

### Claim 18 (depends on 17)

The method as recited in claim 17, wherein resealing the size of the cutout to the size between the size of the first detected face and the size of the second detected face comprises resealing the size of the cutout based on a relative position of the cutout between a first detected object and a second detected object.

### Claim 19 (depends on 14)

The method as recited in claim 14, further comprising:
detecting one or more additional faces of the plurality of faces positioned between the first detected face and the second detected face;
wherein resealing the size of the cutout further comprises resealing the size of the cutout to correspond to a size of at least one of the one or more additional faces positioned between the first detected face and the second detected face.

### Claim 20

A computing device comprising:
at least one processor; and
a non-transitory computer-readable medium storing instructions thereon that, when executed by the at least one processor, cause the computing device to:
identify source content to be added to a destination image, the source content comprising an identified object;
identify, within the destination image, one or more protected regions of the destination image, the one or more protected regions of the destination image comprising a plurality of detected objects;
display, within a graphical user interface of an image editing application, the source content at a first position within the destination image, wherein displaying the source content at the first position comprises:
preventing the source content from interfering with the one or more protected regions of the destination image;
determining that a first object of the plurality of detected objects is the closest of the plurality of detected objects to the first position; and
scaling the source content to correspond to a size of the first object of the plurality of detected objects by sizing the source content based on a size of the first object and a relative position between the first object and the first position; and
display, within the graphical user interface of the image editing application, the source content at a second position within the destination image, wherein displaying the source content at the second position comprises resealing the source content to correspond to a size of a second object of the plurality of detected objects based on a determination that the second object is associated with the second position.
