Method and system of accounting for positional variability of biometric features

• US 8,520,903 B2
• Filed: 02/01/2010
• Issued: 08/27/2013
• Est. Priority Date: 02/01/2010
• Status: Active Grant

• Current Assignee: Corporation DAON Technology
• Original Assignee: Daon Holdings Limited
• Inventors: Gupta, Gaurav, Peirce, Michael, White, Conor Robert
• Primary Examiner(s): Zarka, David
• Assistant Examiner(s): ROWLAND, JHERE M
• Application Number:
  US12/697,703
• Publication Number:
  US 20110188709A1
• Time in Patent Office: 1,303 Days
• Field of Search: None
• US Class Current: 382/115
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 10/44 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 Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors
• CPC Class Codes: G06V 40/1371 Matching features related to minutiae or pores

Abstract

A method of text-based authentication that accounts for positional variability of biometric features between captured biometric data samples includes capturing biometric data for a desired biometric type from an individual, and processing the captured biometric data to generate a biometric image and a biometric feature template. A selected conversion algorithm is executed by superimposing a positional relationship medium on the biometric image. The positional relationship medium includes a plurality of cells textually describable with words derivable from the positional relationship medium. The positions of biometric features are permitted to vary in overlapping border regions within the positional relationship medium. The method also includes identifying the position of at least one biometric feature within the overlapping border regions and generating a plurality of words for the at least one biometric feature.

Claims

1. A method of text-based biometric authentication comprising:

generating a biometric image from biometric data with a server system, the biometric image including biometric features, the server system storing data documents corresponding to different individuals, each data document including enrollment biometric words;

superimposing a positional relationship medium on the biometric image, the positional relationship medium including cells, each cell being described with a word derived from the positional relationship medium, adjacent cells include a common border;

establishing an overlapping border region between respective adjacent cells;

determining a biometric feature included in the biometric features is positioned in an overlapping border region;

deriving a word for each adjacent cell associated with the overlapping border region; and

comparing the derived words against the enrollment biometric words in each data document, and identifying a data document as a matching data document when a derived word matches an enrollment biometric word.

2. A method of text-based biometric authentication in accordance with claim 1, said generating operation further comprising extracting at least one minutia point from fingerprint biometric data, wherein the at least one minutia point represents the biometric feature.

3. A method of text-based biometric authentication in accordance with claim 2, further comprising establishing intersecting border regions at intersections of overlapping border regions.

4. A method of text-based biometric authentication in accordance with claim 1, said deriving operation comprising constructing a sentence from the derived words to describe the position of the biometric feature.

5. A method of text-based biometric authentication in accordance with claim 1, said deriving operation comprising one of:

generating words using sectors and bands of the positional relationship medium; and

generating words using radial line and circle designations of the positional relationship medium.

6. A method of text-based biometric authentication in accordance with claim 1, said generating operation further comprising:

capturing iris biometric data; and

extracting at least phase information and masking information from the captured iris biometric data.

7. A method of text-based biometric authentication in accordance with claim 1, further comprising:

assigning a cell number to each cell; and

translating each word into a single cell number.

17. A method of text-based biometric authentication in accordance with claim 1, further comprising:

adding biometric data to the data document for an individual; and

converting the biometric data into biometric words and adding the biometric words to the data document for the individual.

8. A system for text-based biometric authentication comprising:

a computer configured as a server, said server including at least a data base and being configured to store within said database at least a data document gallery comprising data documents, each data document corresponding to a different individual and including enrollment biometric words; and

at least one client system operationally coupled to said server, said client system configured to at least capture biometric data from an individual, said server being further configured to

generate a biometric image from biometric data, the biometric image including biometric features,

superimpose a positional relationship medium on the biometric image, the positional relationship medium including cells, each cell being described with a word derived from the positional relationship medium, adjacent cells include a common border,

establish an overlapping border region between respective adjacent cells, determine a biometric feature included in the biometric features is positioned in an overlapping border region,

derive a word for each adjacent cell associated with the overlapping border region in which the biometric feature is positioned, and

compare the derived words against the enrollment biometric words in each data document, and identify a data document as a matching data document when a derived word matches an enrollment biometric word.

9. A system for text-based biometric authentication in accordance with claim 8, said client system being further configured to capture fingerprint biometric data, and said server being further configured to derive at least one minutia point from the captured fingerprint biometric data, wherein the at least one minutia point represents the biometric feature.

10. A system for text-based biometric authentication in accordance with claim 8, said server being further configured to establish intersecting border regions at intersections of overlapping border regions.

11. A system for text-based biometric authentication in accordance with claim 8, said server being further configured to:

compile the matching data documents into a list of potential matches;

rank the potential matches according to a number of matching words contained therein; and

verify the identity of an individual by comparing the captured biometric data against corresponding biometric data in each ranked potential match.

18. A system for text-based biometric authentication in accordance with claim 8, said server being further configured to:

add biometric data to the data document for an individual; and

convert the biometric data into biometric words and add the biometric words to the data document for the individual.

12. A method of text-based biometric authentication comprising:

generating cells, each cell including at least one border, and positioning cells adjacent each other to define a border between each pair of adjacent cells;

when a biometric feature included in a biometric template is positioned proximate a common border between adjacent cells determining that the biometric feature is located in each cell adjacent the common border with a processor, the processor operable to communicate with a memory that stores data documents corresponding to different individuals, each data document including enrollment biometric words;

deriving a word for each cell adjacent the common border; and

comparing the derived words against the enrollment biometric words in each data document, and identifying a data document as a matching data document when a derived word matches an enrollment biometric word.

13. A method of text-based biometric authentication in accordance with claim 12, further comprising expanding the border between adjacent cells to establish an overlapping border region between adjacent cells.

14. A method of text-based biometric authentication in accordance with claim 13, wherein positions of biometric features included in the biometric template are permitted to vary in the overlapping border regions.

15. A method of text-based biometric authentication in accordance with claim 12, said generating operation further comprising defining the at least one border of each cell with concentric circles and radial lines.

16. A method of text-based biometric authentication in accordance with claim 15, said generating operation further comprising generating a positional relationship grid with the concentric circles and radial lines.

19. A method of text-based biometric authentication in accordance with claim 12, further comprising:

adding biometric data to the data document for an individual; and

converting the biometric data into biometric words and adding the biometric words to the data document for the individual.