# US 2021/0065338 A1 · Intelligence-based editing and curating of images

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

- Number: US 2021/0065338 A1
- Document ID: US20210065338A1
- Status: Published application
- Kind: A1
- Application number: 16/933,860
- Filed: 2020-07-20
- Published: 2021-03-04
- Earliest claimed: 2019-08-27
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Company, Ltd.
- Inventors: Christopher A. Peri; Euisuk Chung; Yingen Xiong; Lu Luo
- Web page: https://patentgrep.com/patent/US20210065338A1

## CPC

- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06F 18/24: Classification techniques
- G06T 5/20: using local operators
- G06T 11/60: Creating or editing images; Combining images with text
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06T 2207/20032: Median filtering
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20101: Interactive definition of point of interest, landmark or seed
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method implemented by a client device includes accessing a plurality of image frames captured by one or more cameras of the client device and generating a working image frame based at least in part on one or more of the plurality of image frames. The method further includes classifying one or more first objects detected in the working image frame based at least in part on a determined desirability of the one or more first objects. The one or more first objects are determined to be undesirable. The method further includes applying a pixel filtering process to the working image frame to replace one or more first pixel sets associated with the first objects with pixels from one or more image frames of the plurality of image frames to generate a final image frame, and displaying the final image frame on a display of the client device.

## Claims

### Claim 1

A method comprising, by a client device:
accessing a plurality of image frames captured by one or more cameras of the client device;
generating a working image frame based at least in part on one or more of the plurality of image frames;
classifying one or more first objects detected in the working image frame based at least in part on a determined desirability of the one or more first objects, wherein the one or more first objects are determined to be undesirable;
applying a pixel filtering to the working image frame to replace one or more first pixel sets associated with the one or more first objects with pixels from one or more image frames of the plurality of image frames to generate a final image frame; and
displaying the final image frame on a display of the client device.

### Claim 2 (depends on 1)

The method of claim 1, wherein classifying the one or more first objects comprises classifying the one or more first objects as dynamic objects.

### Claim 3 (depends on 2)

The method of claim 2, wherein the pixel filtering comprises:
performing a pixel-locking of the pixels from the one or more image frames of the plurality of image frames; and
applying one or more pixel filtering algorithms on the working image frame to remove the dynamic objects.

### Claim 4 (depends on 3)

The method of claim 3, wherein the pixel filtering further comprises:
performing a pixel-locking of at least a subset of the one or more first pixel sets to preserve one or more of the dynamic objects.

### Claim 5 (depends on 1)

The method of claim 1, wherein applying the pixel filtering to the working image frame comprises applying one or more of a pixel mean averaging algorithm, a pixel median filtering algorithm, a pixel appearance filtering algorithm, or a pixel general filtering algorithm.

### Claim 6 (depends on 1)

The method of claim 1, wherein applying the pixel filtering to replace the one or more first pixel sets with the pixels from the one or more image frames comprises applying one or more pixel filtering algorithms to replace the one or more first pixel sets with pixels of one or more second objects determined to be at least partially occluded by the one or more first objects in the working image frame.

### Claim 7 (depends on 1)

The method of claim 1, wherein the one or more first objects are determined to be undesirable based at least in part on one or more user inputs.

### Claim 8 (depends on 1)

The method of claim 1, wherein the pixels from the one or more image frames of the plurality of image frames are determined to be desirable based at least in part on a predetermined rule.

### Claim 9

A client device comprising:
one or more cameras;
a display;
one or more non-transitory computer-readable storage media including instructions; and
one or more processors coupled to the storage media, the one or more processors configured to execute the instructions to:
access a plurality of image frames captured by the one or more cameras;
generate a working image frame based at least in part on one or more of the plurality of image frames;
classify one or more first objects detected in the working image frame based at least in part on a determined desirability of the one or more first objects, wherein the one or more first objects are determined to be undesirable;
apply a pixel filtering to the working image frame to replace one or more first pixel sets associated with the one or more first objects with pixels from one or more image frames of the plurality of image frames to generate a final image frame; and
display the final image frame on the display.

### Claim 10 (depends on 9)

The client device of claim 9, wherein the instructions to classify the one or more first objects comprise instructions to classify the one or more first objects as dynamic objects.

### Claim 11 (depends on 10)

The client device of claim 10, wherein the instructions to apply the pixel filtering to the working image frame comprise instructions to:
perform a pixel-locking of the pixels from the one or more image frames of the plurality of image frames; and
apply one or more pixel filtering algorithms on the working image frame to remove the dynamic objects.

### Claim 12 (depends on 11)

The client device of claim 11, wherein the instructions to apply the pixel filtering to the working image frame comprise instructions to perform a pixel-locking of at least a subset of the one or more first pixel sets to preserve one or more of the dynamic objects.

### Claim 13 (depends on 9)

The client device of claim 9, wherein the instructions to apply the pixel filtering to the working image frame comprise instructions to apply one or more of a pixel mean averaging algorithm, a pixel median filtering algorithm, a pixel appearance filtering algorithm, or a pixel general filtering algorithm.

### Claim 14 (depends on 9)

The client device of claim 9, wherein the instructions to apply the pixel filtering to replace the one or more first pixel sets with the pixels from the one or more image frames comprise instructions to replace the one or more first pixel sets with pixels of one or more second objects determined to be at least partially occluded by the one or more first objects in the working image frame.

### Claim 15 (depends on 9)

The client device of claim 9, wherein the one or more first objects are determined to be undesirable based at least in part on one or more user inputs.

### Claim 16

A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors of a client device, cause the one or more processors to:
access a plurality of image frames captured by one or more cameras of the client device;
generate a working image frame based at least in part on one or more of the plurality of image frames;
classify one or more first objects detected in the working image frame based at least in part on a determined desirability of the one or more first objects, wherein the one or more first objects are determined to be undesirable;
apply a pixel filtering to the working image frame to replace one or more first pixel sets associated with the one or more first objects with pixels from one or more image frames of the plurality of image frames to generate a final image frame; and
display the final image frame on a display of the client device.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the instructions to classify the one or more first objects comprise instructions to classify the one or more first objects as dynamic objects.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the instructions to apply the pixel filtering to the working image frame comprise instructions to:
perform a pixel-locking of the pixels from the one or more image frames of the plurality of image frames; and
apply one or more pixel filtering algorithms on the working image frame to remove the dynamic objects.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the instructions to apply the pixel filtering to the working image frame comprise instructions to perform a pixel-locking of at least a subset of the one or more first pixel sets to preserve one or more of the dynamic objects.

### Claim 20 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the instructions to apply the pixel filtering to the working image frame comprise instructions to apply one or more of a pixel mean averaging algorithm, a pixel median filtering algorithm, a pixel appearance filtering algorithm, or a pixel general filtering algorithm.
