Biometric matching engine

• US 8,832,124 B2
• Filed: 10/03/2012
• Issued: 09/09/2014
• Est. Priority Date: 10/03/2011
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Partington, Alastair Ross, Astrom, Per Anders Matteus, Bataller, Cyrille
• Primary Examiner(s): Perveen, Rehana
• Assistant Examiner(s): Bui, Thuy
• Application Number:
  US13/644,056
• Publication Number:
  US 20130086090A1
• Time in Patent Office: 706 Days
• Field of Search: 707/754, 707/758, 382/115, 382/117
• US Class Current: 707/754
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/42 using separate channels for security data
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1365 Matching; Classification
• CPC Class Codes: G06V 40/1382 Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

The present disclosure concerns a method of identifying a biometric record of an individual in a database (108), the database comprising at least first and second sets of records, each set comprising at least one record, the method comprising: receiving by a processing device (102) at least first and second input biometric samples of said individual; performing on the records of said first set a first matching process comprising a first filtering operation followed by a second filtering operation, and performing on the records of said second set a second matching process comprising said second filtering operation followed by said first filtering operation, wherein said first filtering operation comprises comparing said first input biometric sample to a first reference biometric sample of each record, and said second filtering operation comprises comparing said second input biometric sample to a second reference biometric sample of each record; and identifying a biometric record of said individual based on results of the first and second matching processes.

Claims

1. A method comprising:

receiving, by a processing device, a first input biometric sample associated with an individual and a second input biometric sample associated with the individual;

determining, by the processing device, one or more first characteristics associated with the first input biometric sample and one or more second characteristics associated with the second input biometric sample;

grouping, by the processing device and after receiving the first input biometric sample and the second input biometric sample, a plurality of records to form a first set of records and a second set of records,

wherein the grouping is based on the one or more first characteristics and the one or more second characteristics;

performing, by the processing device and on the first set of records, a first matching process based on at least one first filtering threshold,

the at least one first filtering threshold being determined based on metadata extracted from at least one record included in the first set of records, and

the first matching process comprising;

a first filtering operation followed by a second filtering operation, the first filtering operation including;

comparing the first input biometric sample to a first reference biometric sample associated with each record included in the first set of records, and the second filtering operation including;

comparing the second input biometric sample to a second reference biometric sample associated with each record included in the first set of records;

performing, by the processing device and on the second set of records, a second matching process based on at least one second filtering threshold,

the at least one second filtering threshold being determined based on metadata extracted from at least one record included in the second set of records, and

the second matching process comprising;

a third filtering operation followed by a fourth filtering operation,

the third filtering operation including;

 

comparing the first input biometric sample to a third reference biometric sample associated with each record included in the second set of records, and

the fourth filtering operation including;

 

comparing the second input biometric sample to a fourth reference biometric sample associated with each record included in the second set of records; and

identifying, by the processing device, a biometric record associated with the individual based on a result of the first matching process and a result of the second matching process.

2. The method of claim 1, where the first input biometric sample and the first reference biometric sample associated with each record, of the plurality of records, comprise a first type of biometric sample, and

where the second input biometric sample and the second reference biometric sample associated with each record, of the plurality of records, comprise a second type of biometric sample,

where the second type of biometric sample is a different type of biometric sample than the first type of biometric sample.

3. The method of claim 2, where the first type of biometric sample includes one of:

an image of a face of the individual,

a fingerprint of the individual,

an iris scan of the individual,

an image of a signature of the individual,

a finger vein or palm vein image of the individual, or

a voice sample of the individual.

4. The method of claim 1, where performing the first matching process further comprises:

eliminating a first group of records, from the first set of records, based on a result of the first filtering operation,

the first set of records including a remaining group of records after eliminating the first group of records; and

where performing the second matching process includes;

eliminating, from the remaining group of records, one or more of;

each record included in the remaining group of records, or all but one record included in the remaining group of records.

5. The method of claim 1, where the plurality of records are stored in a database;

and

where grouping the plurality of records includes;

prior to performing the first matching process and the second matching process and subsequent to receiving the first biometric input sample and the second biometric input sample, partitioning the database into a first partition that includes the first set of records and a second partition that includes the second set of records by comparing a parameter relating to at least one reference biometric sample associated with each record, of the plurality of records, with at least one threshold.

6. The method of claim 5, where the parameter is a first parameter, and

where partitioning the database includes:

determining, based on the one or more first characteristics and the one or more second characteristics, a second parameter relating to at least one of the first input biometric sample and the second input biometric sample; and

partitioning the database into the first partition and the second partition further based on the second parameter.

7. The method of claim 5, where the parameter is a quality measurement associated with the at least one reference biometric sample associated with each record of the plurality of records.

8. The method of claim 7, further comprising:

determining the quality measurement based on one or more of;

an age of an individual associated with the at least one reference biometric sample associated with each record of the plurality of records,

a gender of the individual associated with the at least one reference biometric sample associated with each record of the plurality of records,

a size of an image of the at least one reference biometric sample associated with each record of the plurality of records,

a sharpness of the image of the at least one reference biometric sample associated with each record of the plurality of records,

a viewing angle of the image of the at least one reference biometric sample associated with each record of the plurality of records, or

a contrast in the image of the at least one reference biometric sample associated with each record of the plurality of records.

9. The method of claim 5, where partitioning the database includes:

partitioning the database into the first partition and the second partition based on a quality measurement of at least one of the first input biometric sample or the second input biometric sample and based on a quality measurement of the at least one reference biometric sample associated with each record of the plurality of records.

10. The method of claim 1, further comprising:

receiving a third input biometric sample and a fourth input biometric sample;

determining one or more third characteristics associated with the third input biometric sample and one or more fourth characteristics associated with the fourth input biometric sample;

grouping the plurality of records to form a third set of records and a fourth set of records based on the one or more third characteristics and the one or more fourth characteristics,

where the third set of records and the fourth set of records each include one or more of;

a record included in the first set of records, or

a record included in the second set of records.

11. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by a processor, cause the processor to;

receive a first input biometric sample and a second input biometric sample,

the first input biometric sample and the second input biometric sample being associated with an individual;

determine one or more first characteristics associated with the first input biometric sample and one or more second characteristics associated with the second input biometric sample;

group, after receiving the first input biometric sample, a plurality of records to form a first set of records and a second set of records,

wherein the plurality of records are grouped based on the one or more first characteristics and the one or more second characteristics;

perform, on the first set of records, a first matching process based on at least one first filtering threshold,

the at least one first filtering threshold being determined based on metadata extracted from at least one record included in the first set of records, and

the one or more instructions to perform the first matching process including;

one or more instructions that, when executed by the processor, cause the processor to perform a first filtering operation followed by a second filtering operation,

 

the one or more instructions to perform the first filtering operation including;

 

one or more instructions that, when executed by the processor, cause the processor to compare the first input biometric sample to a first reference biometric sample associated with each record included in the first set of records, and

 

the one or more instructions to perform the second filtering operation including;

 

one or more instructions that, when executed by the processor, cause the processor to compare the second input biometric sample to a second reference biometric sample of each record included in the first set of records;

perform, on the second set of records, a second matching process based on at least one second filtering threshold,

the at least one second filtering threshold being determined based on metadata extracted from at least one record included in the second set of records, and

the one or more instructions to perform the second matching process including;

one or more instructions that, when executed by the processor, cause the processor to perform a third filtering operation followed by a fourth filtering operation,

 

the one or more instructions to perform the third filtering operation including;

 

one or more instructions that, when executed by the processor, cause the processor to compare the first input biometric sample to a third reference biometric sample associated with each record included in the second set of records, and

 

the one or more instructions to perform the fourth filtering operation including;

 

one or more instructions that, when executed by the processor, cause the processor to compare the second input biometric sample to a fourth reference biometric sample of each record included in the second set of records; and

identify a biometric record associated with the individual based on a result of the first matching process and a result of the second matching process.

12. The non-transitory computer-readable medium of claim 11, where the instructions further comprise:

one or more instructions that, when executed by the processor, cause the processor to;

receive a third input biometric sample and a fourth input biometric sample;

determine one or more third characteristics associated with the third input biometric sample and one or more fourth characteristics associated with the fourth input biometric sample;

group the plurality of records to form a third set of records and a fourth set of records based on the one or more third characteristics and the one or more fourth characteristics,

where the third set of records and the fourth set of records each include one or more of;

a record included in the first set of records, or

a record included in the second set of records.

13. The non-transitory computer-readable medium of claim 12, where the instructions further comprise:

one or more instructions that, when executed by the processor, cause the processor to;

perform a third matching process on the third set of records and a fourth matching process on the fourth set of records,

the fourth matching process being different from the first matching process, the second matching process, and the third matching process; and

identify another biometric record, of the plurality of biometric records, associated with another individual based on a result of performing the third matching process and the fourth matching process.

14. A biometric matching device comprising:

a processor to;

receive a first input biometric sample and a second input biometric sample;

determine one or more first characteristics associated with the first input biometric sample and one or more second characteristics associated with the second input biometric sample;

group, after receiving the first input biometric sample and the second input biometric sample, a plurality of records to form a first set of records and a second set of records,

wherein the plurality of records are grouped based on the one or more first characteristics and the one or more second characteristics;

perform, on records included in the first set of records, a first matching process based on at least one first filtering threshold,

the at least one first filtering threshold being determined based on metadata extracted from at least one record included in the first set of records, and

when performing the first matching process, the processor being to;

perform a first filtering operation followed by a second filtering operation,

 

when performing the first filtering operation, the processor being to;

 

compare the first input biometric sample to a first reference biometric sample of each record included in the first set of records, and

 

when performing the second filtering operation, the processor being to;

 

compare the second input biometric sample to a second reference biometric sample included in each record of the first set of records; and

perform, on records included in the second set of records, a second matching process based on at least one second filtering threshold,

the at least one second filtering threshold being determined based on metadata extracted from at least one record included in the second set of records, and

when performing the second matching process, the processor being to;

perform a third filtering operation followed by a fourth filtering operation,

 

when performing the third filtering operation, the processor being to;

 

compare the first input biometric sample to a third reference biometric sample associated with each record included in the second set of records, and

 

when performing the fourth filtering operation the processor being to;

 

compare the second input biometric sample to a fourth reference biometric sample associated with each record included in the second set of records; and

identify a biometric record, of the plurality of biometric records, associated with an individual based on a result of the first matching processing and a result of the second matching process.

15. The biometric matching device of claim 14, where the plurality of records are stored in a database associated with the biometric matching device;

and

where, when grouping the plurality of records to form the first set of records and the second set of records, the processor is to;

partition the database into a first partition comprising the first set of records and a second partition comprising the second set of records by comparing a parameter, relating to at least one reference biometric sample associated with each record, of the plurality of records, with at least one threshold.

16. The biometric matching device of claim 14, where the processor is further to:

receive a third input biometric sample and a fourth input biometric sample;

determine one or more third characteristics associated with the third input biometric sample and one or more fourth characteristics associated with the fourth input biometric sample; and

group the plurality of records to form a third set of records and a fourth set of records based on the one or more third characteristics and the one or more fourth characteristics,

the third set of records and the fourth set of records each including one or more of;

a record included in the first set of records, or

a record included in the second set of records.

17. A biometric matching system comprising:

a biometric matching device including;

a processor to;

receive a first input biometric sample of an individual and a second input biometric sample of the individual;

determine one or more first characteristics associated with the first input biometric sample and one or more second characteristics associated with the second input biometric sample;

group, after receiving the first input biometric sample and the second input biometric sample, a plurality of records to form a first set of records and a second set of records,

wherein the plurality of records are grouped based on the one or more first characteristics and the one or more second characteristics;

perform, on the first set of records, a first matching process based on at least one first filtering threshold,

the at least one first filtering threshold being determined based on metadata extracted from at least one record included in the first set of records, and

when performing the first matching process the processor being to;

 

perform a first filtering operation followed by a second filtering operation,

 

when performing the first filtering operation, the processor being to;

 

compare the first input biometric sample to a first reference biometric sample associated with each record included in the first set of records, and

 

when performing the second filtering operation, the processor being to;

 

compare the first input biometric sample to a second reference biometric sample associated with each record included in the first set of records;

perform, on the second set of records, a second matching process based on at least one second filtering threshold,

the at least one second filtering threshold being determined based on metadata extracted from at least one record included in the second set of records, and

when performing the second matching process, the processor being to;

 

perform a third filtering operation followed by a fourth filtering operation,

 

when performing the third filtering operation, the processor being to;

 

compare the second input biometric sample to a third reference biometric sample associated with each record included in the second set of records, and

 

when performing the fourth filtering operation, the processor being to;

 

compare the second input biometric sample to a fourth reference biometric sample of each record included in the second set of records; and

identify a biometric record, of the plurality of biometric records, associated with the individual based on a result of the first matching process and a result of the second matching process.

18. The biometric matching system of claim 17, where the biometric matching device is further to:

receive a third input biometric sample and a fourth input biometric sample;

determine one or more third characteristics associated with the third input biometric sample and one or more fourth characteristics associated with the fourth input biometric sample; and

group the plurality of records to form a third set of records and a fourth set of records based on the one or more third characteristics and the one or more fourth characteristics,

where the third set of records and the fourth set of records each include one or more of;

a record included in the first set of records, or

a record included in the second set of records.

19. The biometric matching system of claim 18, where the biometric matching device is further to:

perform a third matching process on the third set of records and a fourth matching process on the fourth set of records,

the fourth matching process being different from the first matching process, the second matching process, and the third matching process; and

identify another biometric record, of the plurality of biometric records, associated with another individual based on a result of performing the third matching process and the fourth matching process.

20. A method comprising:

after receiving a first input biometric sample associated with an individual and a second input biometric sample associated with the individual, partitioning, by a processing device, a database into a first partition and a second partition,

wherein the partitioning is based on one or more first characteristics associated with the first input biometric sample and one or more second characteristics associated with the second input biometric sample,

the first partition being associated with a first set of biometric records, of a plurality of biometric records stored in the database, and

the second partition being associated with a second set of biometric records, of the plurality of biometric records,

the second set of biometric records being different from the first set of biometric records;

determining, by the processing device and based on a first matching process, whether the first input biometric sample matches a first reference biometric sample associated with a first biometric record included in the first set of biometric records;

determining, by the processing device and based on a second matching process, whether the second input biometric sample matches a second reference biometric sample associated with a second biometric record included in the second set of biometric records; and

determining, by the processing device, that one of the first biometric record or the second biometric record is associated with the individual based on a result of the first matching process and a result of the second matching process.