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

Patent metadata

Field	Value
Publication number	US-10102416-B2
Application number	US-201715401175-A
Country	US
Kind code	B2
Filing date	Jan 9, 2017
Priority date	Jan 13, 2016
Publication date	Oct 16, 2018
Grant date	Oct 16, 2018

Abstract

A biometric authentication device includes: a memory; and a processor coupled to the memory and the processor configured to execute a process, the process comprising: extracting a finger crotch from a palm image for comparison; extracting a finger root wrinkle from the palm image for comparison; adjusting at least one of a position of a biometric feature for comparison of the palm image for comparison and a position of an enrollment biometric feature of an enrolled palm image, based on position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle; and comparing the biometric feature for comparison and the enrollment biometric feature after the adjusting.

First claim

What is claimed is:

1. A biometric authentication device comprising:
a memory; and
a processor coupled to the memory and the processor configured to execute a process, the process comprising:
extracting a finger crotch from a palm image for comparison;
based on an asperity shape of a palm outline extracted from the palm image and a regularity of palm surface information extracted from the palm image,
extracting a finger root wrinkle from the palm image for comparison, the surface information being extracted by applying an edge extraction filter;
adjusting at least one of a position of a biometric feature for comparison of the palm image for comparison and a position of an enrollment biometric feature of an enrolled palm image, based on position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle; and
comparing the biometric feature for comparison and the enrollment biometric feature after the adjusting.

2. The biometric authentication device as claimed in claim 1 , wherein in the extracting of the finger crotch, the finger crotch is extracted based on an asperity shape of a palm outline extracted from the palm image.

3. The biometric authentication device as claimed in claim 1 , wherein in the adjusting, at least one of the position of the biometric feature for comparison and the position of the enrollment biometric feature is adjusted with use of an approximated line that is acquired from the finger crotch extracted in the extracting of the finger crotch and the wrinkle extracted in the extracting of the finger root wrinkle.

4. The biometric authentication device as claimed in claim 1 , wherein:
the process further comprises calculating a first variability of each dot structuring the finger crotch extracted in the extracting of the finger crotch and a second variability of each dot structuring the wrinkle extracted in the extracting of the finger root wrinkle; and
in the adjusting, a usage ratio between position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle is changed in accordance with the first variability and the second variability.

5. A biometric authentication method comprising:
extracting a finger crotch from a palm image for comparison;
based on an asperity shape of a palm outline extracted from the palm image and a regularity of palm surface information extracted from the palm image,
extracting a finger root wrinkle from the palm image for comparison, the surface information being extracted by applying an edge extraction filter;
adjusting at least one of a position of a biometric feature for comparison of the palm image for comparison and a position of an enrollment biometric feature of an enrolled palm image, based on position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle; and
comparing the biometric feature for comparison and the enrollment biometric feature after the adjusting.

6. The biometric authentication method as claimed in claim 5 , wherein in the extracting of the finger crotch, the finger crotch is extracted based on an asperity shape of a palm outline extracted from the palm image.

7. The biometric authentication method as claimed in claim 5 , wherein in the adjusting, at least one of the position of the biometric feature for comparison and the position of the enrollment biometric feature is adjusted with use of an approximated line that is acquired from the finger crotch extracted in the extracting of the finger crotch and the wrinkle extracted in the extracting of the finger root wrinkle.

8. The biometric authentication method as claimed in claim 5 , further comprising:
calculating a first variability of each dot structuring the finger crotch extracted in the extracting of the finger crotch and a second variability of each dot structuring the wrinkle extracted in the extracting of the finger root wrinkle,
wherein in the adjusting, a usage ratio between position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle is changed in accordance with the first variability and the second variability.

9. A computer readable, non-transitory medium storing a program that causes a computer to execute a process, the process comprising:
extracting a finger crotch from a palm image for comparison;
based on an asperity shape of a palm outline extracted from the palm image and a regularity of palm surface information extracted from the palm image,
extracting a finger root wrinkle from the palm image for comparison, the surface information being extracted by applying an edge extraction filter;
adjusting at least one of a position of a biometric feature for comparison of the palm image for comparison and a position of an enrollment biometric feature of an enrolled palm image, based on position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle; and
comparing the biometric feature for comparison and the enrollment biometric feature after the adjusting.

10. The medium as claimed in claim 9 , wherein in the extracting of the finger crotch, the finger crotch is extracted based on an asperity shape of a palm outline extracted from the palm image.

11. The medium as claimed in claim 9 , wherein in the adjusting, at least one of the position of the biometric feature for comparison and the position of the enrollment biometric feature is adjusted with use of an approximated line that is acquired from the finger crotch extracted in the extracting of the finger crotch and the wrinkle extracted in the extracting of the finger root wrinkle.

12. The medium as claimed in claim 9 , wherein:
the process further comprises calculating a first variability of each dot structuring the finger crotch extracted in the extracting of the finger crotch and a second variability of each dot structuring the wrinkle extracted in the extracting of the finger root wrinkle; and
in the adjusting, a usage ratio between position information of the finger crotch extracted in the extracting of the finger crotch and position information of the wrinkle extracted in the extracting of the finger root wrinkle is changed in accordance with the first variability and the second variability.

Assignees

• Fujitsu Ltd

Inventors

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

Classifications

• G06V40/1365

  Matching; Classification · CPC title

• G06V40/1347 Primary

  Preprocessing; Feature extraction · CPC title

• G06T3/60

  Rotation of whole images or parts thereof · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06K9/48

  Physics · mapped topic