Pre-processing Biometric Parameters before Encoding and Decoding

• US 20080235515A1
• Filed: 10/30/2007
• Published: 09/25/2008
• Est. Priority Date: 12/07/2004
• Status: Active Grant

• Current Assignee: Anthony Vetro, Jonathan S. Yedidia, Stark C. Draper, Yagiz Sutcu
• Original Assignee: Anthony Vetro, Jonathan S. Yedidia, Stark C. Draper, Yagiz Sutcu
• Inventors: Vetro, Anthony, Draper, Stark C., Yedidia, Jonathan S., Sutcu, Yagiz
• Granted Patent: US 8,375,218 B2
• Time in Patent Office: Days
• US Class Current: 713/186
• CPC Class Codes: G06V 40/1353 Extracting features related to minutiae or pores
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: H04L 2209/30 Compression, e.g. Merkle-Damgard construction
• CPC Class Codes: H04L 2209/805 Lightweight hardware, e.g. radio-frequency identification [RFID] or sensor
• CPC Class Codes: H04L 9/3231 Biological data, e.g. fingerprint, voice or retina network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861
• CPC Class Codes: H04L 9/3236 using cryptographic hash functions

Abstract

Biometric parameters acquired from human faces, voices, fingerprints, and irises are used for user authentication and access control. Because the biometric parameters are continuous and vary from one reading to the next, syndrome codes are applied to determine biometric syndrome vectors. The biometric syndrome vectors can be stored securely, while tolerating an inherent variability of biometric data. The stored biometric syndrome vector is decoded during user authentication using biometric parameters acquired at that time. The syndrome codes can also be used to encrypt and decrypt data. The biometric parameters can be pre-processed to form a binary representation, in which the binary representation has a set of predetermined statistical properties enforced imposed by a set of binary logical conditions.

Claims

1. A computer implemented method for securely storing biometric parameters in a database, in which the biometric parameters are acquired of a user during an enrollment phase, comprising the steps of:

applying a set of binary logical conditions to enrollment biometric parameters of a user to produce a binary representation, in which the binary representation has a set of predetermined statistical properties imposed by the set of binary logical conditions;

encoding the binary representation using a syndrome encoder to produce an enrollment syndrome vector, in which the encoding is compatible with the binary representation and the set of predetermined statistical properties;

applying a hash function to the enrollment biometric vector to produce an enrollment hash; and

storing the enrollment syndrome vector and the enrollment hash in a database; and

authenticating the user using the database.

2. The method of claim 1, in which the authenticating further comprises:

acquiring authentication biometric parameters of the user;

applying the set of binary logical conditions to the authentication biometric parameters to produce the binary representation of the authentication biometric parameters, in which the binary representation has the set of predetermined statistical properties imposed by the set of binary logical conditions;

decoding the binary representation of the biometric parameters using a syndrome decoder to produce an authentication syndrome vector, in which the encoding is compatible with the binary representation of the biometric parameters and the set of predetermined statistical properties;

applying a hash function to the authentication biometric vector to produce an authentication hash; and

accessing the database with the authentication syndrome vector and the authentication hash to verify the user.

3. The method of claim 1, in which the set of statistical properties compels each bit in the binary representation to have an equal probability of being either a zero or a one.

4. The method of claim 1, in which the set of statistical properties compels different bits in the binary representation to be independent of each other.

5. The method of claim 1, in which the set of statistical properties compels binary representations from different users to be independent of each other.

6. The method of claim 1, in which the set of statistical properties compels binary representations of same user be statistically dependent on each other.

7. The method of claim 1, in which the biometric parameters are locations of minutiae points for a fingerprint.

8. The method of claim 7, in which the set of binary logical conditions includes a condition that determines whether a number of the minutiae points in a given two-dimensional region is greater than a threshold M.

9. The method of claim 7, in which the set of binary logical conditions includes a condition that is based on a difference between a number of minutiae points above a line and below the line.

10. The method of claim 7, in which the set of binary logical conditions is based on a difference between a number of minutiae points within a first rectangle and the number of minutiae in a second rectangle.

11. The method of claim 1, in which the biometric parameters are locations and orientations of minutiae points for a fingerprint.

12. The method of claim 11, in which the set of binary logical conditions includes a condition that determines whether a number of the minutiae points in a given three-dimensional region is greater than a threshold M.

13. The method of claim 1, in which the predetermined statistical properties are compatible with pattern-based data.

14. The method of claim 1, in which the predetermined statistical properties are compatible with frequency-domain data.

15. The method of claim 1, in which the application of the logical binary condition produces an intermediate value, and further comprising:

binarizing the intermediate value.

16. The method of claim 15, in which the binarizing further comprises:

thresholding the intermediate value.

17. The method of claim 16, in which the binarizing further comprises:

applying a transformation to the intermediate value before the thresholding.

18. The method of claim 17, in which the binarizing further comprises:

normalizing the intermediate value.

19. The method of claim 17, in which the transformation is a random projection.

20. The method of claim 17, in which the transformation is a principal component analysis.

21. The method of claim 1, further comprising:

analyzing the binary representation to ensure and confirm that the set of statistical properties are imposed.