# US 2025/0061923 A1 · Automatic video formatting with brand awareness

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

- Number: US 2025/0061923 A1
- Document ID: US20250061923A1
- Status: Published application
- Kind: A1
- Application number: 18/938,971
- Filed: 2024-11-06
- Published: 2025-02-20
- Earliest claimed: 2022-10-17
- Assignees: SalesTing, Inc.
- Applicants: SalesTing, Inc.
- Inventors: Piyush Saggi; Nitesh Chhajwani; Thomas Ploetz
- Web page: https://patentgrep.com/patent/US20250061923A1

## CPC

- G11B 27/036: Insert-editing
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/172: {Classification, e.g. identification}
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present invention includes a system for improving the visual quality of recorded videos, especially screen recordings such as webinars. The system automatically detects the boundaries of individual tile elements on a screen recording, and then performs facial recognition in order to identify which tiles include a human face and for tracking that face even when the tiles are repositioned over the course of the video. The system uses liveness detection to determine which tiles are video tiles and which tiles are screenshare tiles and then automatically shifts the relative position of the video tiles and the screenshare tiles to create an improved aesthetic quality of the recorded videos. The system is further capable of automatically integrating a company's color branding or logos into the recorded videos.

## Claims

### Claim 1

A system for improving the visual quality of screen recordings, comprising:
a server platform, including a processor and a memory;
wherein the server platform receives at least one screen recording;
wherein the server platform performs edge detection to automatically identify at least one tile constituting the at least one screen recording;
wherein the server platform performs liveness detection to determine if each of the at least one tile is a video tile or a screenshare tile; and
wherein the server platform automatically reconfigures relative locations of each tile for one or more time points in the at least one screen recording based on whether each tile is a video tile or a screenshare tile.

### Claim 2 (depends on 1)

The system of claim 1, wherein the at least one screen recording is a MP4, MOV, WMV, FLV, AVI, AVCHD, WebM, MKV, and/or OGV format prerecorded video.

### Claim 3 (depends on 1)

The system of claim 1, wherein the server platform uses a Hough transform to perform the edge detection.

### Claim 4 (depends on 1)

The system of claim 1, wherein the server platform receives information regarding at least one company and/or at least one individual associated with each screen recording, and wherein the server platform utilizes a web crawler to automatically retrieve brand information for the at least one associated company and/or the at least one associated individual.

### Claim 5 (depends on 4)

The system of claim 4, wherein the server platform automatically recolors at least one section of the at least one screen recording based on the brand information of the at least one associated company and/or the at least one associated individual.

### Claim 6 (depends on 4)

The system of claim 4, wherein the server platform automatically digitally overlays at least one logo to the at least one screen recording based on the brand information of the at least one associated company and/or the at least one associated individual.

### Claim 7 (depends on 1)

The system of claim 1, wherein the reconfiguration of the relative locations of each tile is based on user preferences received from at least one user device.

### Claim 8 (depends on 1)

The system of claim 1, wherein liveness detection includes determining if a number of changed pixels in a particular tile over a preset time period exceeds a preset threshold.

### Claim 9

A method for improving the visual quality of screen recordings, comprising:
a server platform receiving at least one screen recording;
the server platform performing edge detection and automatically identifying at least one tile constituting the at least one screen recording;
the server platform performing liveness detection to determine if each of the at least one tile is a video tile or a screenshare tile; and
the server platform automatically reconfiguring relative locations of each tile for one or more time points in the at least one screen recording based on whether each tile is a video tile or a screenshare tile.

### Claim 10 (depends on 9)

The method of claim 9, wherein the at least one screen recording is a MP4, MOV, WMV, FLV, AVI, AVCHD, WebM, MKV, and/or OGV format prerecorded video.

### Claim 11 (depends on 9)

The method of claim 9, further comprising the server platform utilizing a Hough transform to perform the edge detection.

### Claim 12 (depends on 9)

The method of claim 9, further comprising the server platform receiving information regarding at least one company and/or at least one individual associated with each screen recording, and utilizing a web crawler to automatically retrieve brand information for the at least one associated company and/or the at least one associated individual.

### Claim 13 (depends on 12)

The method of claim 12, further comprising the server platform automatically recoloring at least one section of the at least one screen recording based on the brand information of the at least one associated company and/or the at least one associated individual.

### Claim 14 (depends on 13)

The method of claim 13, further comprising the server platform automatically digitally overlaying at least one logo to the at least one screen recording based on the brand information of the at least one associated company and/or the at least one associated individual.

### Claim 15 (depends on 9)

The method of claim 9, wherein the reconfiguration of the relative locations of each tile is based on user preferences received from at least one user device.

### Claim 16 (depends on 9)

The method of claim 9, wherein liveness detection includes determining if a number of changed pixels in a particular tile over a preset time period exceeds a preset threshold.

### Claim 17

A system for improving the visual quality of screen recordings, comprising:
a server platform, including a processor and a memory;
wherein the server platform receives at least one screen recording;
wherein the server platform performs edge detection to automatically identify at least one tile constituting the at least one screen recording;
wherein the server platform performs liveness detection to determine if each of the at least one tile is a video tile or a screenshare tile;
wherein the server platform automatically reconfigures relative locations of each tile for one or more time points in the at least one screen recording based on whether each tile is a video tile or a screenshare tile;
wherein the server platform receives information regarding at least one company and/or at least one individual associated with each screen recording, and wherein the server platform utilizes a web crawler to automatically retrieve brand information for the at least one associated company and/or the at least one associated individual; and
herein the server platform automatically recolors at least one section of the at least one screen recording based on the brand information of the at least one associated company and/or the at least one associated individual.

### Claim 18 (depends on 17)

The system of claim 17, wherein the server platform automatically digitally overlays at least one logo to the at least one screen recording based on the brand information of the at least one associated company and/or the at least one associated individual.

### Claim 19 (depends on 17)

The system of claim 17, wherein the reconfiguration of the relative locations of each tile is based on user preferences received from at least one user device.

### Claim 20 (depends on 17)

The system of claim 17, wherein the at least one screen recording is a MP4, MOV, WMV, FLV, AVI, AVCHD, WebM, MKV, and/or OGV format prerecorded video.
