# US 9,519,835 B2 · Efficient biometric authentication using narrowed biometric data

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 9,519,835 B2
- Document ID: US9519835B2
- Status: Granted
- Kind: B2
- Application number: 14/467,195
- Filed: 2014-08-25
- Published: 2014-12-11
- Granted: 2016-12-13
- Earliest claimed: 2012-03-30
- Assignees: Fujitsu Limited
- Applicants: Fujitsu Limited
- Inventors: Shigefumi Yamada
- Web page: https://patentgrep.com/patent/US9519835B2

## CPC

- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 30/248: {involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" (G06V30/242 takes precedence)}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A biometric authentication device includes: a biometric sensor that obtains biometric information; a memory; and a circuitry configured to: select an objective user according to density of a predetermined range including a comparison-use part data that is a part of a comparison-use feature data extracted from the biometric information in a class of a registered part data that is a part of a registered feature data; and perform comparing between a registered feature data of a selected objective user and the comparison-use feature data.

## Claims

### Claim 1

A biometric authentication device comprising:
a biometric sensor that obtains biometric information;
a memory; and
a circuitry configured to:
select an objective user according to density of distribution of registered part data within a predetermined range in a set of the registered part data, the predetermined range including a comparison-use part data that is a part of a comparison-use feature data extracted from the biometric information, the registered part data being a part of a registered feature data; and
perform comparing between a registered feature data of a selected objective user and the comparison-use feature data.

### Claim 2 (depends on 1)

The biometric authentication device as claimed in claim 1, wherein the circuitry is configured to:
narrow objective users by the comparing between the comparison-use part data and the registered part data; and
expand narrowed objective users when the density is equal to or more than a threshold.

### Claim 3 (depends on 2)

The biometric authentication device as claimed in claim 2, wherein the circuitry is configured to expand the narrowed objective users when the comparing between the registered feature data and the comparison-use feature data of the narrowed objective users is failed and the density is equal to or more than a threshold.

### Claim 4 (depends on 2)

The biometric authentication device as claimed in claim 2, wherein the circuitry is configured to increase a number of the narrowed users as the density increases.

### Claim 5 (depends on 1)

The biometric authentication device as claimed in claim 1, wherein the circuitry is configured not to expand the objective users when a quality value of the biometric information obtained by the biometric sensor is less than a predetermined value.

### Claim 6 (depends on 2)

The biometric authentication device as claimed in claim 2, wherein the circuitry is configured to:
determine whether a user relating to the biometric information obtained by the biometric sensor coincides with a user relating to biometric information that is obtained by the biometric sensor again; and
not to expand the objective users when it is determined that the user relating to the biometric information obtained by the biometric sensor does not coincide with the user relating to the biometric information that is obtained by the biometric sensor again.

### Claim 7 (depends on 1)

The biometric authentication device as claimed in claim 1, wherein the density indicates a relationship between an order of similarities between the comparison-use part data and the registered part data and the similarities.

### Claim 8 (depends on 1)

The biometric authentication device as claimed in claim 1, wherein:
the memory is configured to store a number of the registered part data in each region of a space indicating distribution of part data in advance; and
the density indicates the number of the registered part data in the region of the space corresponding to the comparison-use part data.

### Claim 9 (depends on 1)

The biometric authentication device as claimed in claim 1, wherein:
the circuitry is configured to classify each registered part data according to each similarity between registered part data;
the memory is configured to store a number of the registered part data belonging to each class; and
the density indicates the number of the registered part data in the class corresponding to the comparison-use part data.

### Claim 10

A biometric authentication method comprising:
selecting an objective user according to density of distribution of registered part data within a predetermined range in a set of the registered part data, the predetermined range including a comparison-use part data that is a part of a comparison-use feature data extracted from the biometric information obtained by a biometric sensor, the registered part data being a part of a registered feature data; and
performing a comparing between a registered feature data of a selected objective user and the comparison-use feature data.

### Claim 11 (depends on 10)

The method as claimed in claim 10, wherein:
objective users are narrowed by the comparing between the comparison-use part data and the registered part data; and
narrowed objective users are expanded when the density is equal to or more than a threshold.

### Claim 12 (depends on 11)

The method as claimed in claim 11, wherein the narrowed objective users are expanded when the comparing between the registered feature data and the comparison-use feature data of the narrowed objective users is failed and the density is equal to or more than a threshold.

### Claim 13 (depends on 11)

The method as claimed in claim 11, wherein a number of the narrowed users is increased as the density increases.

### Claim 14

A computer readable, non-transitory medium storing a program that causes a computer to execute a process, the process comprising:
selecting an objective user according to density of distribution of registered part data within a predetermined range in a set of the registered part data, the predetermined range including a comparison-use part data that is a part of a comparison-use feature data extracted from biometric information obtained by a biometric sensor, the registered part data being is a part of a registered feature data; and
performing comparing between a registered feature data of a selected objective user and the comparison-use feature data.

### Claim 15 (depends on 14)

The medium as claimed in claim 14, wherein:
objective users are narrowed by the comparing between the comparison-use part data and the registered part data; and
narrowed objective users are expanded when the density is equal to or more than a threshold.

### Claim 16 (depends on 15)

The medium as claimed in claim 15, wherein the narrowed objective users are expanded when the comparing between the registered feature data and the comparison-use feature data of the narrowed objective users is failed and the density is equal to or more than a threshold.

### Claim 17 (depends on 15)

The medium as claimed in claim 15, wherein a number of the narrowed users is increased as the density increases.
