# US 2019/0057489 A1 · Image editing and repair

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

- Number: US 2019/0057489 A1
- Document ID: US20190057489A1
- Status: Published application
- Kind: A1
- Application number: 16/165,962
- Filed: 2018-10-19
- Published: 2019-02-21
- Earliest claimed: 2015-04-08
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Florian Kriener; Nils Kokemohr
- Web page: https://patentgrep.com/patent/US20190057489A1

## CPC

- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 11/60: Creating or editing images; Combining images with text
- H04N 23/635: {Region indicators; Field of view indicators}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A method for healing a target region on an input image is described. A preview image is received; the preview image may reflect a down-sampled image of an original image. The method determines a target region for the preview image. The target region indicates a segment of the preview image designated for healing. The method may then heal the target region associated with the preview image using a transformation. The method may store one or more parameters associated with the healed preview image. The method may then provide for display the healed preview image to a user on a mobile device.

## Claims

### Claim 1

A computer-implemented method comprising:
providing, using one or more computing devices, for display, a down-sampled preview image generated from an input image;
identifying a target region of the preview image using the one or more computing devices, the target region indicating a segment of the preview image to be modified;
responsive to identifying the target region:
identifying a source region from a plurality of candidate source regions in the preview image based on one or more features of the preview image;
transforming the source region onto the target region using a transformation to create a healed preview image, wherein the transformation is based on the source region; and
storing one or more parameters associated with the transformation and the healed preview image; and
updating, using the one or more computing devices, the input image based on the one or more parameters such that one or more image edits associated with the transformation are not distorted.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more parameters include at least one of: the source region, the transformation associated with the source region and the target region, or dimensions of the preview image.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the source region includes identifying the plurality of candidate source regions as having similar pixel values as the target region and identifying the source region as one of the candidate source regions that has similar pixel values that meet a predetermined pixel threshold associated with the target region.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more features of the preview image include at least one of: colors or brightness.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the source region includes searching for the source region using a second transformation.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein transforming the source region onto the target region includes:
comparing pixel values of the target region and the source region; and
healing one or more pixels of the target region by altering the one or more pixels based on the source region.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the transformation is determined using the plurality of candidate source regions as data models of a healed region, wherein transforming the source region onto the target region is performed using the data models.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein transforming the source region onto the target region includes refining the target region based on boundaries of the source region and the target region.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein one or more restriction regions are defined in the preview image, wherein the plurality of the candidate source regions exclude the one or more restriction regions.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the target region includes identifying a discrepancy related to an artifact in the preview image and classifying a segment of the preview image that includes the discrepancy as the target region.

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, wherein identifying the target region includes receiving a definition of the target region via user input.

### Claim 12

A system comprising:
a processor; and
a memory coupled to the processor, the memory storing instructions that, when executed, cause the processor to perform operations comprising:
providing, using one or more computing devices, for display, a down-sampled preview image generated from an input image;
identifying a target region of the preview image using one or more computing devices, the target region indicating a segment of the down-sampled preview image to be modified;
responsive to identifying the target region:
identifying a source region from a plurality of candidate source regions in the preview image based on one or more features of the preview image;
transforming the source region onto a target region using a transformation to create a healed preview image, wherein the transformation is based on the source region; and
storing one or more parameters associated with the transformation and the healed preview image; and
updating, using the one or more computing devices, the input image based on the one or more parameters such that one or more image edits associated with the transformation are not distorted.

### Claim 13 (depends on 12)

The system of claim 12, wherein the one or more parameters include at least one of: the source region, the transformation associated with the source region and the target region, or dimensions of the preview image.

### Claim 14 (depends on 12)

The system of claim 12, wherein the operation of identifying the source region includes identifying the plurality of candidate source regions as having similar pixel values as the target region and identifying the source region as one of the candidate source regions that has similar pixel values that meet a predetermined pixel threshold associated with the target region.

### Claim 15 (depends on 12)

The system of claim 12, wherein the operation of transforming the source region onto the target region includes operations of:
comparing pixel values of the target region and the source region; and
healing one or more pixels of the target region by altering the one or more pixels based on the source region.

### Claim 16 (depends on 12)

The system of claim 12, wherein the operation of transforming the source region onto the target region includes an operation of refining the target region based on boundaries of the source region and the target region.

### Claim 17 (depends on 12)

The system of claim 12, wherein the operation of identifying the target region includes an operation of identifying a discrepancy related to an artifact in the preview image and classifying a segment of the preview image including the discrepancy as the target region.

### Claim 18 (depends on 12)

The system of claim 12, wherein the operation of identifying the target region includes an operation of receiving a definition of the target region via user input.

### Claim 19

A non-transitory computer readable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to perform operations comprising:
providing, using one or more computing devices, for display, a down-sampled preview image generated from an input image;
identifying a target region of the preview image using one or more computing devices, the target region indicating a segment of the down-sampled preview image to be modified;
responsive to identifying the target region:
identifying a source region from a plurality of candidate source regions in the preview image based on one or more features of the preview image;
transforming the source region onto a target region using a transformation to create a healed preview image, wherein the transformation is based on the source region; and
storing one or more parameters associated with the transformation and the healed preview image; and
updating, using the one or more computing devices, the input image based on the one or more parameters such that one or more image edits associated with the transformation are not distorted.

### Claim 20 (depends on 19)

The non-transitory computer readable medium of claim 19, wherein the operation of transforming the source region onto the target region includes:
comparing pixel values of the target region and the source region; and
healing one or more pixels of the target region by altering the one or more pixels based on the source region.
