Biometric matching engine

• US 9,720,936 B2
• Filed: 04/29/2016
• Issued: 08/01/2017
• 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: Bataller, Cyrille, Partington, Alastair Ross, Astrom, Per Anders Matteus
• Primary Examiner(s): Herndon, Heather
• Assistant Examiner(s): Bui, Tiffany
• Application Number:
  US15/143,093
• Publication Number:
  US 20160239520A1
• Time in Patent Office: 459 Days
• Field of Search: 707754
• 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, an input biometric sample to be matched with a record of a plurality of records stored in a data structure;

determining, by the processing device, a characteristic associated with the input biometric sample;

partitioning, by the processing device and triggered by receiving the input biometric sample, the plurality of records by grouping the plurality of records stored in the data structure to form a first set of records and a second set of records based on a threshold associated with the characteristic;

performing, by the processing device and on the first set of records, a first matching process that compares the input biometric sample and the first set of records;

performing, by the processing device and on the second set of records, a second matching process that compares the input biometric sample and the second set of records,

the first matching process using a filter with a different threshold than the second matching process;

identifying, by the processing device, the record that matches the input biometric sample based on a result of the first matching process and a result of the second matching process;

providing, by the processing device, an identification result that indicates the record that matches the biometric sample was found;

receiving, by the processing device, another input biometric sample; and

dynamically re-partitioning, by the processing device, the plurality of records based on receiving the other input biometric sample.

2. The method of claim 1, where the input biometric sample comprises at least one of:

an image of a face,

a fingerprint,

an iris scan,

an image of a signature,

an image of a finger vein,

an image of a palm vein, or

a voice sample.

3. The method of claim 1, where the characteristic includes at least one of:

an age of an individual associated with the input biometric sample,

a gender of the individual,

a size of an image corresponding to a reference biometric sample,

a sharpness of the image,

a viewing angle of the image, or

a contrast in the image.

4. The method of claim 1, where the first matching process uses at least one filter that the second matching process does not use.

5. The method of claim 1, further comprising:

assigning the first matching process to the first set of records based on metadata extracted from the first set of records; and

assigning the second matching process to the second set of records based on metadata extracted from the second set of records.

6. A device comprising:

a memory; and

one or more processors, operatively connected to the memory, to;

receive a biometric sample to be matched with a record of a plurality of records stored in a data structure;

determine a characteristic associated with the biometric sample;

partition, triggered by receiving the biometric sample, the plurality of records by grouping the plurality of records stored in the data structure to form a first group of records and a second group of records based on a threshold associated with the characteristic;

perform a first matching process on the first group of records that compares the biometric sample and the first group of records;

perform a second matching process on the second group of records that compares the biometric sample and the second group of records,

the first matching process using at least one filter that the second matching process does not use;

identify the record that matches the biometric sample based on a result of the first matching process and a result of the second matching process;

provide an identification result that indicates the record that matches the biometric sample was found;

receive another biometric sample; and

dynamically re-partition the plurality of records based on receiving the other biometric sample.

7. The device of claim 6, where the biometric sample comprises at least one of:

an image of a face,

a fingerprint,

an iris scan,

an image of a signature,

an image of a finger vein,

an image of a palm vein, or

a voice sample.

8. The device of claim 6, where the characteristic includes at least one of:

an age of an individual associated with the biometric sample,

a gender of the individual,

a size of an image corresponding to a reference biometric sample,

a sharpness of the image,

a viewing angle of the image, or

a contrast in the image.

9. The device of claim 6, where the first matching process uses a filter with a different threshold than the second matching process.

10. The device of claim 6, where the one or more processors are further to:

assign the first matching process to the first group of records based on metadata extracted from the first group of records; and

assign the second matching process to the second group of records based on metadata extracted from the second group of records.

11. A non-transitory computer-readable medium storing instructions for managing a border via a management application architecture, the instructions comprising:

one or more instructions that, when executed by one or more processors of a computer, cause the one or more processors to;

receive an input biometric sample to be matched with a record of a plurality of records stored in a data structure;

determine a characteristic associated with the input biometric sample;

partition, triggered by receiving the input biometric sample, the plurality of records by grouping the plurality of records stored in the data structure to form a first partition of records and a second partition of records based on a threshold associated with the characteristic;

perform a first matching process on the first partition of records that compares the input biometric sample and the first partition of records;

perform a second matching process on the second partition of records that compares the input biometric sample and the second partition of records,

the first matching process using a filter with a different threshold than the second matching process;

identify the record that matches the input biometric sample based on a result of the first matching process and a result of the second matching process;

provide an identification result that indicates the record that matches the biometric sample was found;

receive another input biometric sample; and

dynamically re-partition the plurality of records based on receiving the other input biometric sample.

12. The non-transitory computer-readable medium of claim 11, where the input biometric sample comprises at least one of:

an image of a face,

a fingerprint,

an iris scan,

an image of a signature,

an image of a finger vein,

an image of a palm vein, or

a voice sample.

13. The non-transitory computer-readable medium of claim 11, where the characteristic includes at least one of:

an age of an individual associated with the input biometric sample,

a gender of the individual,

a size of an image corresponding to a reference biometric sample,

a sharpness of the image,

a viewing angle of the image, or

a contrast in the image.

14. The non-transitory computer-readable medium of claim 11, where the first matching process uses at least one filter that the second matching process does not use.