Method for comparison of a test fingerprint, which is in the form of an image strip sequence, with a stored reference fingerprint, and a suitable apparatus for carrying out the method

1. A method of comparing a test fingerprint with a stored reference fingerprint, comprising:

producing an image strip sequence of the test fingerprint, by a fingerprint sensor, wherein image strips of the image strip sequence represent different areas of the test fingerprint;

producing the reference fingerprint from memory, wherein the reference fingerprint is produced in an image strip sequence, and image strips of the image strip sequence represent different sections of the reference fingerprint;

determining individual distance values, using a distance function, between each image strip of the test fingerprint and at least one section of the reference fingerprint;

calculating a sum function using the individual distance values to determine an overall distance value, which is a measure of similarity between the test fingerprint and the reference fingerprint;

comparing the overall distance value, by a comparator, with a threshold value; and

if the overall distance value has a defined relationship with the threshold value, assuming the test fingerprint and the reference fingerprint are identical.

2. The method according to claim 1 , wherein the overall distance value is determined using a Viterbi algorithm.

3. The method according to claim 1 , further comprising:

comparing the test fingerprint with a plurality of reference fingerprints, each comparison resulting in an overall distance value; and

determining a minimum overall distance value.

4. The method according to claim 1 , wherein the image strips of the test fingerprint do not overlap.

5. The method according to claim 1 , further comprising calculating an association function between the image strips of the test fingerprint and sections of the reference fingerprint from the individual distance values.

6. The method according to claim 1 , wherein the step of determining the individual distance values is based on a normalized correlation between the image strips of the test fingerprint and sections of the reference fingerprint.

7. The method according to claim 1 , further comprising:

breaking down the image strips of the test fingerprint into image rows; and

determining individual distance values between the image rows and the at least one section of the reference fingerprint.

8. The method according to claim 1 , further comprising:

breaking down each image strip of the test fingerprint into image rows before determining the respective individual distance values;

determining a distance value for each image row; and

determining the individual distance value for each image strip using the distance values of the image rows of the respective image strip.

9. The method according to claim 8 , wherein the step of determining the individual distance value for each image strip using the distance values of the image rows of the respective image strip includes using a Viterbi algorithm.

10. The method according to claim 1 , wherein the image strips of the test fingerprint are recorded using the fingerprint sensor in a form of a strip.

11. The method according to claim 10 , further comprising image-conditioning preprocessing the image strips after the image strips are stored.

12. The method according to claim 1 , further comprising:

determining fingerprint-specific features from the image strips and from sections of the reference fingerprint; and

determining a similarity between image strips and the sections of the reference fingerprint, using the fingerprint-specific features.

13. The method according to claim 12 , further comprising storing the reference fingerprint in a form of fingerprint-specific features in a memory.

14. The method according to claim 1 , wherein the step of determining the individual distance values includes calculating a Euclidean distance between feature vectors of the image strips.

15. The method according to claim 1 , further comprising:

training a hidden Markov model using features from two or more reference fingerprints; and

comparing the test fingerprint using its features with respect to the hidden Markov model of the reference fingerprints.

16. The method according to claim 15 , wherein the comparison step includes using a Viterbi algorithm.

17. An apparatus for identifying fingerprints comprising:

a fingerprint sensor in a form of a strip configured to record image strips of a test finger;

a memory having stored reference fingerprints; and

a comparator designed to carry out the method according to claim 1 .