# US 2024/0203145 A1 · Systems and methods for document authentication

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

- Number: US 2024/0203145 A1
- Document ID: US20240203145A1
- Status: Published application
- Kind: A1
- Application number: 18/066,655
- Filed: 2022-12-15
- Published: 2024-06-20
- Earliest claimed: 2022-12-15
- Assignees: Idemia Identity & Security USA LLC
- Applicants: Idemia Identity & Security USA LLC
- Inventors: Rein-Lien Hsu; Brian Martin; Alexandru Bogdan
- Web page: https://patentgrep.com/patent/US20240203145A1

## CPC

- G06V 30/19013: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching (specially adapted for image segmentation G06T7/10; specially adapted for the analysis of motion G06T7/20; specially adapted for image alignment G06T7/30; specially adapted for the calculation of depth from stereo images G06T7/50; specially adapted for position determination G06T7/70)}
- G06V 10/56: relating to colour
- G06V 30/148: Segmentation of character regions
- G06V 30/18105: {related to colour}
- G06V 30/42: based on the type of document
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A system for authenticating a subject identification document includes instructions causing a processor to receive a first image of the document, depicting, in RGB color space, the document illuminated by UV light, and transform the first image to a second image in YCbCr color space. The instructions cause the processor to divide the second image into regions of interest (ROIs), and, for each ROI, generate a color profile descriptor including first data elements associated with pixel color in the YCbCr color space, and second data elements associated with pixel intensity of pixels within the ROI. The instructions also cause the processor to generate a score for the second image based on a comparison of the color profile descriptor for each ROI to a corresponding ROI of an enrolled document template, and compare the score to a threshold to determine whether the document is authenticated.

## Claims

### Claim 1

A system for authenticating a subject identification document, the system comprising:
a memory comprising a first memory section storing computer-executable instructions and a second memory section storing a plurality of enrolled document templates; and
a processor in communication with the memory and configured to execute the computer-executable instructions that, when executed, cause the processor to:
receive a first image of the subject identification document, the first image depicting, in a red-green-blue (RGB) color space, the subject identification document illuminated by ultraviolet (UV) light;
transform the first image of the subject document to a second image of the subject identification document in a YCbCr color space;
divide the second image into a plurality of regions of interest (ROIs);
for each ROI, generate a color profile descriptor including first data elements associated with a number of pixels in each of a plurality of angular sectors in a CbCr color map of the YCbCr color space, within the corresponding ROI, and second data elements associated with pixel intensity of the pixels within the corresponding ROI;
generate a matching score for the second image based on a comparison of the color profile descriptor for each ROI to a corresponding ROI of a first enrolled document template; and
compare the matching score to a threshold to determine whether the subject identification document is authenticated.

### Claim 2 (depends on 1)

The system of claim 1, wherein the computer-executable instructions, when executed, further cause the processor to generate the color profile descriptor for a first ROI of the plurality of ROIs by:
dividing the CbCr color map into a plurality of angular sectors;
mapping each pixel in the first ROI to a corresponding one of the angular sectors; and
incrementing a corresponding sector of a color histogram based on each mapped pixel.

### Claim 3 (depends on 2)

The system of claim 2, wherein the computer-executable instructions, when executed, further cause the processor to generate the matching score for the second image by:
for each ROI of the plurality of ROIs:
computing, using the first data elements of the corresponding color profile descriptor, a normalized initial score of overlap between the color histogram of the ROI and the respective color histogram of the corresponding ROI of the first enrolled document template; and
adjusting the initial score using the second data elements in the corresponding color profile descriptor; and
computing the matching score as a mean of the adjusted scores.

### Claim 4 (depends on 3)

The system of claim 3, wherein the computer-executable instructions, when executed, further cause the processor to generate the matching score for the second image by:
sorting the adjusted scores in increasing order; and
removing at least the highest adjusted score and at least the lowest adjusted score; and
computing the matching score as the mean of only the remaining adjusted scores.

### Claim 5 (depends on 1)

The system of claim 1, wherein the computer-executable instructions, when executed, further cause the processor to:
validate each ROI prior to generating the color profile descriptor for the corresponding ROI; and
only generate the color profile descriptor for valid ROIs of the plurality of ROIs.

### Claim 6 (depends on 5)

The system of claim 5, wherein the computer-executable instructions, when executed, further cause the processor to validate a first ROI by:
computing an average pixel intensity for the first ROI; and
determining that the average pixel intensity falls within a range bounded by a dark-current threshold and a saturation threshold.

### Claim 7 (depends on 6)

The system of claim 6, wherein the computer-executable instructions, when executed, further cause the processor to further validate the first ROI by:
determining a count of valid pixels within the first ROI; and
determining the count of valid pixels exceeds a present threshold.

### Claim 8 (depends on 1)

The system of claim 1, wherein the computer-executable instructions, when executed, further cause the processor to generate each enrolled document template by:
receiving a first image of a corresponding enrollment document, the first image depicting, in the RGB color space, the enrollment document illuminated by UV light;
transforming the first image of the enrollment document to a second image of the subject document, the second image depicting, in the YCbCr color space, the enrollment document illuminated by the UV light;
dividing the second image of the enrollment document into a plurality of ROIs; and
for each ROI of the enrollment document, generating the color profile descriptor.

### Claim 9 (depends on 1)

The system of claim 1, wherein a number of ROIs in the first enrolled document template is the same as a number of ROIs in the subject document template.

### Claim 10 (depends on 1)

The system of claim 1, wherein the second image depicts, in the YCbCr color space, the subject identification document illuminated by the UV light.

### Claim 11

A non-transitory, computer readable storage medium having a first memory section storing a plurality of enrolled document templates and a second memory section having instructions stored thereon that, in response to execution by a processor, cause the processor to:
receive a first image of a subject identification document, the first image depicting, in a red-green-blue (RGB) color space, the subject identification document illuminated by ultraviolet (UV) light;
transform the first image of the subject identification document to a second image of the subject identification document in a YCbCr color space;
divide the second image into a plurality of regions of interest (ROIs);
for each ROI, generate a color profile descriptor including first data elements associated with a number of pixels in each of a plurality of angular sectors in a CbCr color map of the YCbCr color space, within the corresponding ROI, and second data elements associated with pixel intensity of the pixels within the corresponding ROI;
generate a matching score for the second image based on a comparison of the color profile descriptor for each ROI to a corresponding ROI of a first enrolled document template; and
compare the matching score to a threshold to determine whether the subject identification document is authenticated.

### Claim 12 (depends on 11)

The non-transitory, computer readable storage medium of claim 11, wherein the instructions further cause the processor to generate the color profile descriptor for a first ROI of the plurality of ROIs by:
dividing the CbCr color map into a plurality of angular sectors;
mapping each pixel in the first ROI to a corresponding one of the angular sectors; and
incrementing a corresponding sector of a color histogram based on each mapped pixel.

### Claim 13 (depends on 12)

The non-transitory, computer readable storage medium of claim 12, wherein the instructions further cause the processor to generate the matching score for the second image by:
for each ROI of the plurality of ROIs:
computing, using the first data elements of the corresponding color profile descriptor, a normalized initial score of overlap between the color histogram of the ROI and the respective color histogram of the corresponding ROI of the first enrolled document template; and
adjusting the initial score using the second data elements in the corresponding color profile descriptor; and
computing the matching score as a mean of the adjusted scores.

### Claim 14 (depends on 13)

The non-transitory, computer readable storage medium of claim 13, wherein the instructions further cause the processor to generate the matching score for the second image by:
sorting the adjusted scores in increasing order; and
removing at least the highest adjusted score and at least the lowest adjusted score; and
computing the matching score as the mean of only the remaining adjusted scores.

### Claim 15 (depends on 11)

The non-transitory, computer readable storage medium of claim 11, wherein the instructions further cause the processor to:
validate each ROI prior to generating the color profile descriptor for the corresponding ROI; and
only generate the color profile descriptor for valid ROIs of the plurality of ROIs.

### Claim 16 (depends on 15)

The non-transitory, computer readable storage medium of claim 15, wherein the instructions further cause the processor to validate a first ROI by:
computing an average pixel intensity for the first ROI; and
determining that the average pixel intensity falls within a range bounded by a dark-current threshold and a saturation threshold.

### Claim 17 (depends on 16)

The non-transitory, computer readable storage medium of claim 16, wherein the instructions further cause the processor to further validate the first ROI by:
determining a count of valid pixels within the first ROI; and
determining the count of valid pixels exceeds a present threshold.

### Claim 18

A computer-implemented method for authenticating a subject identification document, the method implemented using an authentication system including (i) a memory storing a plurality of enrolled document templates, and (ii) a processor in communication with the memory, the method comprising:
receiving a first image of the subject identification document, the first image depicting, in a red-green-blue (RGB) color space, the subject identification document illuminated by ultraviolet (UV) light;
transforming the first image of the subject document to a second image of the subject identification document in a YCbCr color space;
dividing the second image into a plurality of regions of interest (ROIs);
for each ROI, generating a color profile descriptor including first data elements associated with a number of pixels in each of a plurality of angular sectors in a CbCr color map of the YCbCr color space, within the corresponding ROI, and second data elements associated with pixel intensity of the pixels within the corresponding ROI;
generating a matching score for the second image based on a comparison of the color profile descriptor for each ROI to a corresponding ROI of a first enrolled document template; and
comparing the matching score to a threshold to determine whether the subject identification document is authenticated.

### Claim 19 (depends on 18)

The computer-implemented method of claim 18, wherein generating the color profile descriptor for a first ROI of the plurality of ROIs comprises:
dividing the CbCr color map into a plurality of angular sectors;
mapping each pixel in the first ROI to a corresponding one of the angular sectors; and
incrementing a corresponding sector of a color histogram based on each mapped pixel.

### Claim 20 (depends on 19)

The computer-implemented method of claim 19, wherein generating the matching score for the second image comprises:
for each ROI of the plurality of ROIs:
computing, using the first data elements of the corresponding color profile descriptor, a normalized initial score of overlap between the color histogram of the ROI and the respective color histogram of the corresponding ROI of the enrolled document template; and
adjusting the initial score using the second data elements in the corresponding color profile descriptor; and
computing the matching score as a mean of the adjusted scores.
