# US 2021/0264135 A1 · Secure facial recognition

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

- Number: US 2021/0264135 A1
- Document ID: US20210264135A1
- Status: Published application
- Kind: A1
- Application number: 17/181,874
- Filed: 2021-02-22
- Published: 2021-08-26
- Earliest claimed: 2020-02-20
- Assignees: AlethealD Limited
- Applicants: AlethealD Limited
- Inventors: Lindsay WHITELAW; Craig DORAN
- Web page: https://patentgrep.com/patent/US20210264135A1

## CPC

- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 40/168: {Feature extraction; Face representation}
- G06V 40/172: {Classification, e.g. identification}
- G06V 40/173: {face re-identification, e.g. recognising unknown faces across different face tracks}
- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- G06F 2221/2103: Challenge-response
- G06T 2207/30201: Face
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method of facial recognition comprises detecting (606) a visual cue (702) within an image (700), the visual cue having a predetermined appearance indicative of a registered user of a facial recognition system (100). A region (706) of the image that includes both the visual cue (702) and a face (705) is identified (608), and facial recognition is performed (620) only within the identified region.

## Claims

### Claim 1

A computer-implemented method of facial recognition, the method comprising:
detecting a visual cue within an image, the visual cue having a predetermined appearance indicative of a registered user of a facial recognition system;
identifying a region of the image that includes both the visual cue and a face; and
performing facial recognition within the identified region only.

### Claim 2 (depends on 1)

A method in accordance with claim 1, further comprising:
obtaining an identifier of a specific registered user of the facial recognition system;
using the identifier to retrieve facial data for the specific registered user; and
wherein performing facial recognition comprises comparing facial data extracted from the image with the retrieved facial data.

### Claim 3 (depends on 2)

A method in accordance with claim 2, wherein obtaining the identifier includes extracting the identifier from the visual cue.

### Claim 4 (depends on 1)

A method in accordance with claim 1, further comprising:
obtaining a decryption key of a specific registered user of the facial recognition system;
decrypting encrypted facial data for the specific registered user using the decryption key; and
wherein performing facial recognition comprises comparing facial data extracted from the image with the decrypted facial data.

### Claim 5 (depends on 4)

A method in accordance with claim 4, wherein obtaining the decryption key includes extracting the decryption key from the visual cue.

### Claim 6 (depends on 1)

A method in accordance with claim 1, further comprising:
extracting a password from the visual cue;
using the password to retrieve facial data for the specific registered user; and
wherein performing facial recognition comprises comparing facial data extracted from the image with the retrieved facial data.

### Claim 7 (depends on 1)

A method in accordance with claim 1, wherein the visual cue comprises a barcode.

### Claim 8 (depends on 1)

A method in accordance with claim 1, wherein the visual cue comprises a predetermined sequence of colours.

### Claim 9 (depends on 8)

A method in accordance with claim 8, wherein detecting the visual cue comprises:
identifying a plurality of pixels at a common location in each image of a series of images, wherein the colour values of each of the plurality of pixels represent each colour of the predetermined sequence of colours.

### Claim 10 (depends on 1)

A method in accordance with claim 1, wherein identifying the region of the image comprises:
processing the image with an edge detection algorithm to identify a plurality of edges in the image; and
combining the plurality of edges to form one or more continuous lines that surround the visual cue, wherein each continuous line defines a respective candidate region of the image.

### Claim 11 (depends on 1)

A method in accordance with claim 1, wherein identifying the region of the image comprises:
processing the image with a foreground detection algorithm to identify one or more foreground regions of the image; and
selecting at least one foreground region that includes the visual cue as a candidate region of the image.

### Claim 12 (depends on 10)

A method in accordance with claim 10, wherein identifying the region of the image further comprises:
performing a face detection algorithm within each candidate region to identify a candidate region that includes a single face.

### Claim 13 (depends on 1)

A computer program product comprising instructions which, when executed by a computer, cause the computer to the method of claim 1.

### Claim 14 (depends on 1)

A computer-readable medium comprising instructions which, when executed by a computer, cause the computer to perform the method of claim 1.

### Claim 15 (depends on 1)

An apparatus configured to perform the method of claim 1.
