Pre-processing biometric parameters before encoding and decoding
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.
1. A computer implemented method for securely storing biometric parameters in a database, in which the biometric parameters represent biometric features of a user, comprising the steps of:
applying a set of binary logical conditions to the biometric parameters to produce a binary representation of the biometric parameters, wherein each binary logical condition produces at least one bit of the binary representation based on statistical properties of at least a portion of the biometric features, wherein the statistical property is selected from a set of predetermined statistical properties;
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, wherein the hash function is cryptographic; and
storing the enrollment syndrome vector and the enrollment hash in a 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.