Counterfeit image detection

Patent metadata

Field	Value
Publication number	US-11769313-B2
Application number	US-202117326490-A
Country	US
Kind code	B2
Filing date	May 21, 2021
Priority date	May 21, 2021
Publication date	Sep 26, 2023
Grant date	Sep 26, 2023

Abstract

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to acquire a first image from a first camera by illuminating a first object with a first light and determine an object status as one of a real object or a counterfeit object by comparing a first measure of pixel values corresponding to the first object to a threshold.

First claim

The invention claimed is:

1. A computer, comprising:
a processor; and

a memory, the memory including instructions executable by the processor to:
acquire a first image from a first camera by illuminating a first object with a first light;
determine a first measure of pixel values based on the first object;
acquire a second image of a second object with the first camera by illuminating the second object with the first light, wherein the second object is a real object;
determine a second measure of pixel values based on the second object in the second image, wherein the second measure of pixel values is based on a second mean and second standard deviation of pixel values corresponding to the second object in the second image;
determine a threshold by determining a second number of second standard deviations below which the second mean of pixel values corresponding to the second object occurs; and
determine an object status as one of a real object or a counterfeit object by comparing the first measure of pixel values based on the first object to the threshold.

2. The method of claim 1 , wherein the first light includes two wavelengths of light and pixels included the first image correspond to differences between the two wavelengths.

3. The computer of claim 1 , the instructions including further instructions to:
acquire a plurality of third images with a second camera by illuminating a plurality of third objects with a second light, wherein the plurality of third objects are real objects;
determine a plurality of third means and third standard deviations of pixel values corresponding to the plurality of third objects in the plurality of third images with a second computer;
determine a second threshold by determining a third number of second standard deviations below which the third means of pixel values corresponding to the third objects occur; and
adjust the second threshold based on a difference between the first light and the second light.

4. The computer of claim 3 , the instructions including further instructions to:
acquire a plurality of fourth images with a third camera by illuminating a plurality of fourth objects with a third light, wherein the plurality of fourth objects are counterfeit objects;
determine a plurality of fourth means and fourth standard deviations of pixel values corresponding to the plurality of fourth objects in the plurality of fourth images with a third computer;
determine a third threshold by determining a fourth number of standard deviations above which the fourth means of pixel values corresponding to the fourth objects occur; and
adjust the third threshold based on a difference between the first light and the third light.

5. The computer of claim 1 , wherein the first light includes one or more wavelengths of short wave infrared light, near infrared light, visible light and ultraviolet light.

6. The computer of claim 4 , the instructions including further instructions to, when the first object is a human face and is determined to be the real object, perform facial identification on the human face by acquiring a fifth image using a fourth light that includes visible light.

7. The computer of claim 1 , the instructions including further instructions to permit access to a vehicle, an area, or a device based on determining the object status.

8. The computer of claim 1 , wherein the first measure of pixel values includes a first mean and first standard deviation of pixel values in a histogram.

9. The computer of claim 1 , wherein the first measure of pixel values is a measure of image texture based on a Gabor texture filter.

10. The computer of claim 1 , wherein the first light includes two wavelengths of light and pixels included the first image correspond to differences between the two wavelengths.

11. The computer of claim 1 , the instructions including further instructions to adjust the threshold based on determining an offset between the center of the first object and the center of the first image.

12. The computer of claim 1 , the instructions including further instructions to adjust the threshold based on determining an angle at which the first object is facing with respect to the first camera.

13. A method, comprising:
acquiring a first image from a first camera by illuminating a first object with a first light;
determining a first measure of pixel values based on the first object;
acquiring a second image of a second object with the first camera by illuminating the second object with the first light, wherein the second object is the real object;
determining a second measure of pixel values based on the second object in the second image, wherein the second measure of pixel values is based on a second mean and second standard deviation of pixel values corresponding to the second object in the second image;
determining a threshold by determining a second number of second standard deviations below which the second mean of pixel values corresponding to the second object occurs; and
determining an object status as one of a real object or a counterfeit object by comparing the first measure of pixel values based on the first object to the threshold.

14. The method of claim 13 , wherein the first measure of pixel values is a measure of image texture based on a Gabor texture filter.

15. The method of claim 13 , further comprising:
acquiring a plurality of third images with a second camera by illuminating a plurality of third objects with a second light, wherein the plurality of third objects are real objects;
determining a plurality of third means and third standard deviations of pixel values corresponding to the plurality of third objects in the plurality of third images with a second computer;
determining a second threshold by determining a third number of second standard deviations below which the third means of pixel values occur corresponding to the third objects; and
adjusting the second threshold based on a difference between the first light and the second light.

16. The method of claim 15 , further comprising:
acquiring a plurality of fourth images with a third camera by illuminating a plurality of fourth objects with a third light, wherein the plurality of fourth objects are counterfeit objects;
determining a plurality of fourth means and fourth standard deviations of pixel values corresponding to the plurality of fourth objects in the plurality of fourth images with a third computer;
determining a third threshold by determining a fourth number of standard deviations above which the fourth means of pixel values corresponding to the fourth objects occur; and
adjusting the third threshold based on a difference between the first light and the third light.

17. The method of claim 13 , wherein the first light includes two wavelengths of light and pixels included the first image correspond to differences between the two wavelengths.

18. The method of claim 16 , further comprising, when the first object is a human face and is determined to be the real object, perform facial identification on the human face by acquiring a fifth image using a fourth light that includes visible light.

19. The method of claim 13 , further comprising permitting access to a vehicle, an area, or a device based on determining the object status.

20. The method of claim 13 , wherein the first measure of pixel values includes a first mean and first standard deviation of pixel values in a histogram.

Assignees

• Ford Global Tech Llc

Inventors

• Hassani Ali
• Diedrich Jonathan
• Malik Hafiz
• Parenti Robert
• Hanson Ryan Edwin

Classifications

• G06V10/143 Primary

  Sensing or illuminating at different wavelengths · CPC title

• G06T7/44

  using image operators, e.g. filters, edge density metrics or local histograms · CPC title

• G06V10/60

  relating to illumination properties, e.g. using a reflectance or lighting model · CPC title

• G06V40/162

  using pixel segmentation or colour matching · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title