Detecting identification tampering using ultra-violet imaging

Patent metadata

Field	Value
Publication number	US-2021264583-A1
Application number	US-202117179676-A
Country	US
Kind code	A1
Filing date	Feb 19, 2021
Priority date	Feb 21, 2020
Publication date	Aug 26, 2021
Grant date	—

Abstract

Implementations of the present disclosure include applying UV light to a first target identification, generating a first UV image of the first target identification, and determining that a model brightness fingerprint is unavailable for the first target identification, and in response: calculating a region brightness value for a particular region of the first target identification based on the first UV image, calculating an identification brightness value for the first target identification based on the first UV image, and comparing the region brightness value to the identification brightness value to determine whether the first target identification has been tampered with.

First claim

What is claimed is:

1 . A computer-implemented method for determining whether an identification has been tampered with, the method comprising:
applying ultra-violet (UV) light to a first target identification; generating a first UV image of the first target identification; and determining that a model brightness fingerprint is unavailable for the first target identification, and in response:
calculating a region brightness value for a particular region of the first target identification based on the first UV image,
calculating an identification brightness value for the first target identification based on the first UV image, and
comparing the region brightness value to the identification brightness value to determine whether the first target identification has been tampered with.

2 . The method of claim 1 , further comprising:
generating a brightness fingerprint for the first target identification based on the first UV image; and providing the model brightness fingerprint at least partially based on the brightness fingerprint.

3 . The method of claim 1 , wherein the particular region comprises a photo region comprising an image provided in the first target identification.

4 . The method of claim 1 , wherein determining that a model brightness fingerprint is unavailable for the first target identification comprises:
determining an identification type of the first target identification; indexing a table of model brightness fingerprints using the identification type; and determining that the table is absent the identification type.

5 . The method of claim 1 , further comprising determining that the first target identification has been tampered with in response to the region brightness value being greater than or equal to the identification brightness value.

6 . The method of claim 1 , further comprising determining that the first target identification has not been tampered with in response to the region brightness value being less than the identification brightness value.

7 . The method of claim 1 , wherein the region brightness value is calculated as a mean brightness value across all pixels in the particular region depicted within the first UV image.

8 . The method of claim 1 , further comprising:
applying UV light to a second target identification; generating a second UV image of the second target identification; and determining that the model brightness fingerprint is available for the second target identification, and in response:
generating a brightness fingerprint for the second target identification,
determining a value for the second target identification based on the brightness fingerprint and the model brightness fingerprint, and
comparing the value to a threshold value to determine whether the second target identification has been tampered with.

9 . The method of claim 8 , wherein the brightness fingerprint comprises a brightness histogram of the second target identification based on the second UV image of the second target identification.

10 . The method of claim 1 , wherein the model brightness fingerprint is provided as a histogram of brightness values of a set of UV images of a set of known valid identifications.

11 . A system, comprising:
a scanner; and a computer-readable storage device coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for determining whether an identification has been tampered with, the operations comprising:
applying ultra-violet (UV) light to a first target identification;
generating a first UV image of the first target identification; and
determining that a model brightness fingerprint is unavailable for the first target identification, and in response:
calculating a region brightness value for a particular region of the first target identification based on the first UV image,
calculating an identification brightness value for the first target identification based on the first UV image, and
comparing the region brightness value to the identification brightness value to determine whether the first target identification has been tampered with.

12 . The system of claim 11 , wherein operations further comprise:
generating a brightness fingerprint for the first target identification based on the first UV image; and providing the model brightness fingerprint at least partially based on the brightness fingerprint.

13 . The system of claim 11 , wherein the particular region comprises a photo region comprising an image provided in the first target identification.

14 . The system of claim 11 , wherein determining that a model brightness fingerprint is unavailable for the first target identification comprises:
determining an identification type of the first target identification; indexing a table of model brightness fingerprints using the identification type; and determining that the table is absent the identification type.

15 . The system of claim 11 , wherein operations further comprise determining that the first target identification has been tampered with in response to the region brightness value being greater than or equal to the identification brightness value.

16 . The system of claim 11 , wherein operations further comprise determining that the first target identification has not been tampered with in response to the region brightness value being less than the identification brightness value.

17 . The system of claim 11 , wherein region brightness value is calculated as a mean brightness value across all pixels in the particular region depicted within the first UV image.

18 . The system of claim 11 , wherein operations further comprise:
applying UV light to a second target identification; generating a second UV image of the second target identification; and determining that the model brightness fingerprint is available for the second target identification, and in response:
generating a brightness fingerprint for the second target identification,
determining a value for the second target identification based on the brightness fingerprint and the model brightness fingerprint, and
comparing the value to a threshold value to determine whether the second target identification has been tampered with.

19 . The system of claim 18 , wherein the brightness fingerprint comprises a brightness histogram of the second target identification based on the second UV image of the second target identification.

20 . The system of claim 11 , wherein the model brightness fingerprint is provided as a histogram of brightness values of a set of UV images of a set of known valid identifications.

21 . Computer-readable storage media coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for determining whether an identification has been tampered with, the operations comprising:
applying ultra-violet (UV) light to a first target identification; generating a first UV image of the first target identification; and determining that a model brightness fingerprint is unavailable for the first target identification, and in response:
calculating a region brightness value for a particular region of the first target identification based on the first UV image,
calculating an identification brightness value for the first target identificatio

Assignees

• Accenture Global Solutions Ltd

Inventors

• Keller Matthew Francis
• Macgregor Johnathan David
• Mcclellan Christopher J

Classifications

• G06V30/153

  using recognition of characters or words · CPC title

• G06V30/40

  Document-oriented image-based pattern recognition · CPC title

• G07D7/1205 Primary

  Testing spectral properties · CPC title

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title