# US 2021/0279499 A1 · Detection of skin reflectance in biometric image capture

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

- Number: US 2021/0279499 A1
- Document ID: US20210279499A1
- Status: Published application
- Kind: A1
- Application number: 17/185,487
- Filed: 2021-02-25
- Published: 2021-09-09
- Earliest claimed: 2020-02-28
- Assignees: The Government of the United States of America, as represented by the Secretary of Homeland Security
- Applicants: The Government of the United States of America, as represented by the Secretary of Homeland Security
- Inventors: Yevgeniy B. Sirotin; Arun R. Vemury; Cynthia M. Cook; John J. Howard; Jerry L. Tipton
- Web page: https://patentgrep.com/patent/US20210279499A1

## CPC

- G07C 9/00563: {using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns}
- G06V 10/141: Control of illumination
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/162: {using pixel segmentation or colour matching}
- G06V 40/166: {using acquisition arrangements}
- G06V 40/168: {Feature extraction; Face representation}
- G06V 40/172: {Classification, e.g. identification}
- H04N 23/611: where the recognised objects include parts of the human body
- H04N 23/71: Circuitry for evaluating the brightness variation
- H04N 23/72: Combination of two or more compensation controls
- H04N 23/74: by influencing the scene brightness using illuminating means
- H04N 23/76: by influencing the image signals
- G07B 15/00: Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points (handling coins or valuable papers, e.g. banknotes, G07D; apparatus for vending or hiring articles or services activated by coins, credit cards, paper currency or the like G07F7/00, G07F17/00)
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G07B: TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS

## Abstract

In examples, a relative skin reflectance of a captured image of a subject is determined. The determination selects from the captured image pixels of the subject's face and pixels in the background and normalizes luminance values of the skin pixels using the background pixels. The relative skin reflectance value is determined for the captured image, based on the normalized luminance values of the skin pixels. Optionally the relative skin reflectance value is qualified, based on thresholds of skin reflectance values, as suitable for biometric use. Optionally, a non-qualifying captured image is flagged and, optionally, another image is acquired, or the non-conforming image is processed further to transform the image into a suitable image for biometric analysis.

## Claims

### Claim 1

A system for quantification of phenotypes in received captured images capture for biometric matching, comprising:
a processing system having a hardware processor configured to perform a predefined set of basic operations in response to receiving a corresponding basic instruction selected from a predefined native instruction set of codes;
a memory, accessible to the processing system; and
logic, comprising a set of machine codes stored in the memory and selected from the predefined native instruction set of codes of the hardware processor, the set of machine codes causing the hardware processor to:
receive an image, and store the image as a received image, the received image including facial pixels and including background pixels, the facial pixels being of a face of a subject, and the facial pixels including a plurality of facial skin pixels;
determine a relative reflectance value, indicative of a relative reflectance of at least a portion of the facial skin pixels; and
generate a reflectance qualification indicator, indicating whether the relative reflectance value meets a reflectance qualification.

### Claim 2 (depends on 1)

The system of claim 1, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to:
automatically select, as a selected next process, between a remediation process and a biometric identification process using the received image, the select being based at least in part on the reflectance qualification indicator; and
perform the selected next process.

### Claim 3 (depends on 2)

The system of claim 2, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to include in the biometric identification process a generation of an access control signal, having a value set between an access open value and an access closed value, based at least in part on a result of the biometric identification process.

### Claim 4 (depends on 2)

The system of claim 2, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to:
select, in association with the selected next process being the remediation process, the remediation process from among a plurality of different remediation processes, the plurality of different remediation processes including a post capture reflectance correction process; and
include in performing the post capture reflectance correction process a post process determining of whether the post capture reflectance correction process is successful, successful including a corrected reflectance image.

### Claim 5 (depends on 4)

The system of claim 4, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to:
update the selected next process, in response to a positive indication by the post process determining, to the biometric identification process using, as the received image, the corrected reflectance image; and
select and perform, in response to determining the post capture reflectance correction process is not successful, another among the plurality of different remediation processes.

### Claim 6 (depends on 1)

The system of claim 1, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to determine the relative reflectance value based at least in part on luminance values of at least the portion of the facial skin pixels and luminance values of at least a portion of the background pixels.

### Claim 7 (depends on 1)

The system of claim 1, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to:
compute a first mean, the first mean being a mean of at least a portion of the background pixels;
compute normalized luminance values of at least the portion of the facial skin pixels, based on dividing luminance values of at least the portion of the facial skin pixels by the first mean;
compute, as a second mean, the mean of the normalized luminance values of at least the portion of the facial skin pixels; and
generate the relative reflectance value based on the second mean.

### Claim 8 (depends on 1)

The system according of claim 1, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to:
detect a facial image, within the received image;
establish a border, aligned with and surrounding the facial image;
obtain the facial pixels by dividing the received image, using the border, into facial pixels within the border and remainder pixels outside the border, the facial pixels having associated color component values;
obtain a set of luminance values for at least some of the facial pixels; and
obtain the plurality of facial skin pixels by operations including selecting and discarding outlier facial pixels, among the facial pixels, the selecting and discarding based at least in part on the set of luminance values.

### Claim 9 (depends on 8)

The system according of claim 8, further comprising the logic including, in the set of machine codes, codes causing the hardware processor to select, as outlier facial pixels, ones of the facial pixels that are outside 1.5 standard deviations of a mean of the set of luminance values.

### Claim 10

A method for quantifying of phenotypes in received captured images capture for biometric matching, comprising:
receiving an image, and storing the image as a received image, the received image including facial pixels and including background pixels, the facial pixels being of a face of a subject, a plurality of the facial pixels being facial skin pixels;
determining a relative reflectance value, indicative of a relative reflectance of at least a portion of the facial skin pixels; and
generating a reflectance qualification indicator, indicating whether the relative reflectance value meets a reflectance qualification.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
automatically selecting, as a selected next process, between a remediation process and a biometric identification process using the received image, the select being based at least in part on the reflectance qualification indicator; and
performing the selected next process.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
selecting, in association with the selected next process being the remediation process, the remediation process from among a plurality of different remediation processes, the plurality of different remediation processes including a post capture reflectance correction process; and
including in performing the post capture reflectance correction process a post process determining of whether the post capture reflectance correction process is successful, successful including a corrected reflectance image.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
updating the selected next process, in response to a positive result of the post process determining, to the biometric identification process using, as the received image, the corrected reflectance image; and
selecting and performing, in response to determining the post capture reflectance correction process is not successful, another among the plurality of different remediation processes.

### Claim 14 (depends on 10)

The method of claim 10, wherein determining the relative reflectance value is based at least in part on:
determining luminance values of at least a portion of the background pixels;
determining luminance values of at least the portion of the facial skin pixels;
generating normalized luminance values of at least the portion of the facial skin pixels, based at least in part on the luminance values of at least the portion of the facial skin pixels and the luminance values of at least a portion of the background pixels; and
determining the relative reflectance value based at least in part on a mean of the normalized luminance values of at least the portion of the facial skin pixels.

### Claim 15 (depends on 10)

The method of claim 10, further comprising:
computing a first mean, the first mean being a mean of at least a portion of the background pixels;
computing normalized luminance values of at least the portion of the facial skin pixels, based on dividing luminance values of at least the portion of the facial skin pixels by the first mean;
computing, as a second mean, the mean of the normalized luminance values of at least the portion of the facial skin pixels; and
generating the relative reflectance value based on the second mean.

### Claim 16 (depends on 10)

The method of claim 10, further comprising:
detecting a facial image, within the received image; and
obtaining the facial pixels from the facial image, by operations including establishing a border, aligned with and surrounding the facial image, the facial pixels being within the border and remainder pixels being outside the border, the facial pixels having associated color component values.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
obtaining a set of luminance values for at least some of the facial pixels;
selecting outlier facial pixels, among the facial pixels, based at least in part on the set of luminance values; and
obtaining the facial skin pixels by a discarding of the outlier facial pixels.

### Claim 18 (depends on 17)

The method of claim 17, further comprising selecting, as the outlier facial pixels, ones of the facial pixels outside 1.5 standard deviations of a mean of the set of luminance values.