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

• US 9,336,426 B2
• Filed: 09/11/2014
• Issued: 05/10/2016
• Est. Priority Date: 03/28/2012
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Aoki, Takahiro
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): Azima, Shaghayegh
• Application Number:
  US14/483,564
• Publication Number:
  US 20140376784A1
• Time in Patent Office: 607 Days
• Field of Search: 382/115
• US Class Current: 1/1
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G06V 40/1318 using electro-optical elements or layers, e.g. electroluminescent sensing
• CPC Class Codes: G06V 40/1341 Sensing with light passing through the finger
• CPC Class Codes: G06V 40/145 Sensors therefor
• CPC Class Codes: G06V 40/50 Maintenance of biometric data or enrolment thereof

Abstract

A biometric authentication device includes: a memory configured to store an enrollment feature data; a biometric sensor that obtains a biometric image of a user; and a circuitry configured to: obtain a surface reflection degree of the biometric image; extract a comparison-use feature data from the biometric image; perform a comparing based on a similarity between the comparison-use feature data and the enrollment feature data; and reflect a correction coefficient and the surface reflection degree related to a region of the biometric image to the similarity.

Claims

1. A biometric authentication device comprising:

a memory configured to store an enrollment feature data;

a biometric sensor that obtains a biometric image of a user; and

a circuitry configured to;

obtain a surface reflection degree of the biometric image;

extract a comparison-use feature data from the biometric image; and

perform a comparing based on a similarity between the comparison-use feature data and the enrollment feature data, the similarity being obtained by using a correction coefficient and the surface reflection degree related to a region of the biometric image, the correction coefficient being a weighting coefficient of the similarity.

2. The biometric authentication device as claimed in claim 1, wherein the circuitry is configured to obtain a similarity with respect to each of regions of the biometric image.

3. The biometric authentication device as claimed in claim 1, wherein the circuitry is configured to update the correction coefficient based on an authentication result.

4. The biometric authentication device as claimed in claim 3, wherein the circuitry is configured to use the surface reflection degree as a weight for updating the correction coefficient.

5. The biometric authentication device as claimed in claim 1 wherein:

the memory is configured to store a surface reflection degree of a basic biometric image for the enrollment feature data; and

the circuitry is configured to reflect the stored surface reflection degree to the similarity between the enrollment feature data and the comparison-use feature data.

6. The biometric authentication device as claimed in claim 1, wherein the circuitry is configured to obtain a surface reflection degree based on a luminance value and a high frequency component of the biometric image.

7. The biometric authentication device as claimed in claim 1, wherein the circuitry is configured to obtain a surface reflection degree by a fitting process with respect to a luminance value of the biometric image.

8. A biometric authentication method comprising:

obtaining a surface reflection degree of a biometric image obtained by a biometric sensor;

extracting a comparison-use feature data from the biometric image; and

obtaining a similarity between the comparison-use feature data and an enrollment feature data by using a correction coefficient and the surface reflection degree related to a region of the biometric image when performing a comparing based on the similarity, the correction coefficient being a weighting coefficient of the similarity.

9. A computer readable, non-transitory medium storing a program that causes a computer to execute a process, the process comprising:

obtaining a surface reflection degree of a biometric image obtained by a biometric sensor;

extracting a comparison-use feature data from the biometric image; and

obtaining a similarity between the comparison-use feature data and an enrollment feature data by using a correction coefficient and the surface reflection degree related to a region of the biometric image when performing a comparing based on the similarity, the correction coefficient being a weighting coefficient of the similarity.