# US 2022/0277458 A1 · Systems and methods for extracting headshots from images

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

- Number: US 2022/0277458 A1
- Document ID: US20220277458A1
- Status: Published application
- Kind: A1
- Application number: 17/648,292
- Filed: 2022-01-18
- Published: 2022-09-01
- Earliest claimed: 2021-01-15
- Assignees: Promptu Systems Corporation
- Applicants: Promptu Systems Corporation
- Inventors: James Henry NEALAND; Blair William Thomas FIDLER
- Web page: https://patentgrep.com/patent/US20220277458A1

## CPC

- G06T 7/11: Region-based segmentation
- G06T 7/73: using feature-based methods
- G06F 16/583: using metadata automatically derived from the content
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 20/30: in albums, collections or shared content, e.g. social network photos or video
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/166: {using acquisition arrangements}
- 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}
- G06T 2207/20132: Image cropping
- G06T 2207/30201: Face
- 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

Various embodiments contemplate systems, architectures and methods for extracting and selecting headshots of human or non-human entities from catalogs of images of such subjects. The methods described may find and extract faces from within groups of subjects, verify that the extracted faces correspond to the desired subject, determine cropping or masking regions, or both, of rectangular, circular, elliptical or some other geometry to provide an easily recognized image of the desired subject, expand the output image by synthesizing pixels as may be needed for a desired cropping or masking region, select preferred images among a collection of images of the desired subject, and perform other useful functions. The resulting output images may be in either direct form, reference form or both forms.

## Claims

### Claim 1

A method comprising:
obtaining, by a computing system, a first image to be processed;
extracting, by said computing system, a face from said first image by determining a region of said first image that comprises said face;
labeling, by said computing system, said face with an identifier that is associated with a subject to whom said face belongs;
verifying, by said computing system, that an identity established by said identifier matches a nominal identity that is associated with said first image;
determining, by said computing system, a cropping region and/or a masking region for said face;
applying, by said computing system, said cropping region and/or said masking region to said first image, so as to produce a second image that is representative of a subset of said first image; and
expanding, by said computing system, said second image by synthesizing values for at least some pixels outside of said cropping region and/or said masking region.

### Claim 2 (depends on 1)

The method of claim 1, wherein said image is included in an entry of an image catalog that is accessible to said computing system via a network.

### Claim 3 (depends on 1)

The method of claim 1, wherein said region is represented by a bounding box whose coordinates define pixels of interest in said first image.

### Claim 4 (depends on 1)

The method of claim 1, wherein said region is a subset of said first image.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
identifying, by said computing system, at least one facial feature of said individual based on an analysis of said region of said first image.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
identifying, by said computing system, an orientation of said face in three-dimensional space based on an analysis of said region of said image.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
identifying, by said computing system, a measure of quality based on an analysis of said region of said first image.
