Biometric image processing device, biometric image processing method and computer-readable non-transitory medium

Patent metadata

Field	Value
Publication number	US-10643317-B2
Application number	US-201715833673-A
Country	US
Kind code	B2
Filing date	Dec 6, 2017
Priority date	Dec 20, 2016
Publication date	May 5, 2020
Grant date	May 5, 2020

Abstract

A biometric image processing device includes: a memory; and a processor coupled to the memory and the processor configured to execute a process, the process comprising: capturing a biometric image of an object by a camera; obtaining a histogram of brightness values from the biometric image; correcting the biometric image by expanding a dynamic range of a partial histogram of the histogram of which an appearance frequency is equal to or more than a threshold; and calculating a distance between the camera and the object on a basis of a high frequency component of the biometric image corrected in the correcting.

First claim

What is claimed is:

1. A biometric image processing device comprising:
a memory; and
a processor coupled to the memory and the processor configured to execute a process, the process comprising:
capturing a biometric image of an object by a camera;
obtaining a histogram of brightness values from the biometric image;
correcting the biometric image by expanding a dynamic range of a partial histogram of the histogram of which an appearance frequency is equal to or more than a first threshold;
determining whether an amount of a high frequency component in the biometric image corrected in the correcting is in a predetermined range; and
outputting instruction information for correcting a distance between the camera and the object when it is not determined that the amount of the high frequency component in the biometric image corrected in the correcting is in the predetermined range, wherein
the instruction information instructs to move the object away from the camera when the high frequency component is below a second threshold, or instructs to move object toward the camera when the high frequency component is above the second threshold.

2. The biometric image processing device as claimed in claim 1 , wherein, in the correcting, the dynamic range is expanded so that a pixel of which an appearance frequency of a brightness value is less than the first threshold is saturated in the histogram.

3. The biometric image processing device as claimed in claim 1 , wherein:
the process further comprises extracting the object from the biometric image captured by the camera; and
in the obtaining, a histogram of brightness values of the object extracted by the extracting is obtained.

4. The biometric image processing device as claimed in claim 1 , wherein the first threshold is equal to or less than 1/10 of a maximum integrated amount of the histogram.

5. The biometric image processing device as claimed in claim 1 , wherein, in the calculating, the high frequency component is calculated by a Fourier transform.

6. A biometric image processing method comprising:
capturing a biometric image of an object by a camera;
obtaining a histogram of brightness values from the biometric image;
correcting the biometric image by expanding a dynamic range of a partial histogram of the histogram of which an appearance frequency is equal to or more than a first threshold;
determining whether an amount of a high frequency component in the biometric image corrected in the correcting is in a predetermined range; and
outputting instruction information for correcting a distance between the camera and the object when it is not determined that the amount of the high frequency component in the biometric image corrected in the correcting is in the predetermined range, wherein
the instruction information instructs to move the object away from the camera when the high frequency component is below a second threshold, or instructs to move object toward the camera when the high frequency component is above the second threshold.

7. The biometric image processing method as claimed in claim 6 , wherein, in the correcting, the dynamic range is expanded so that a pixel of which an appearance frequency of a brightness value is less than the first threshold is saturated in the histogram.

8. The biometric image processing method as claimed in claim 6 , further comprising extracting the object from the biometric image captured by the camera,
wherein, in the obtaining, a histogram of brightness values of the object extracted by the extracting is obtained.

9. The biometric image processing method as claimed in claim 6 , wherein the first threshold is equal to or less than 1/10 of a maximum integrated amount of the histogram.

10. The biometric image processing method as claimed in claim 6 , wherein, in the calculating, the high frequency component is calculated by a Fourier transform.

11. A computer-readable, non-transitory medium storing a program that causes a computer to execute a process, the process comprising:
capturing a biometric image of an object by a camera;
obtaining a histogram of brightness values from the biometric image;
correcting the biometric image by expanding a dynamic range of a partial histogram of the histogram of which an appearance frequency is equal to or more than a first threshold;
determining whether an amount of a high frequency component in the biometric image corrected in the correcting is in a predetermined range; and
outputting instruction information for correcting a distance between the camera and the object when it is not determined that the amount of the high frequency component in the biometric image corrected in the correcting is in the predetermined range, wherein
the instruction information instructs to move the object away from the camera when the high frequency component is below a second threshold, or instructs to move object toward the camera when the high frequency component is above the second threshold.

12. The medium as claimed in claim 11 , wherein, in the correcting, the dynamic range is expanded so that a pixel of which an appearance frequency of a brightness value is less than the first threshold is saturated in the histogram.

13. The medium as claimed in claim 11 , wherein:
the process further comprises extracting the object from the biometric image captured by the camera; and
in the obtaining, a histogram of brightness values of the object extracted by the extracting is obtained.

14. The medium as claimed in claim 11 , wherein the first threshold is equal to or less than 1/10 of a maximum integrated amount of the histogram.

15. The medium as claimed in claim 11 , wherein, in the calculating, the high frequency component is calculated by a Fourier transform.

Assignees

• Fujitsu Ltd

Inventors

• Semba Satoshi
• Hama Soichi
• Maeda Satoshi
• Nada Hajime
• Abiko Yukihiro

Classifications

• G06T2207/30196

  Human being; Person · CPC title

• G06T7/77

  using statistical methods · CPC title

• G06T2207/10004

  Still image; Photographic image · CPC title

• G06T2207/20048

  Transform domain processing · CPC title

• G06K9/00033

  Physics · mapped topic