FINGERPRINT REPRESENTATION USING GRADIENT HISTOGRAMS

• US 20090285459A1
• Filed: 05/15/2008
• Published: 11/19/2009
• Est. Priority Date: 05/15/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Aggarwal, Gaurav, Jea, Tsai-Yang, Ratha, Nalini Kanta, Bolle, Rudolf Maarten
• Granted Patent: US 8,625,861 B2
• Time in Patent Office: Days
• US Class Current: 382/125
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1353 Extracting features related to minutiae or pores

Abstract

Techniques for generating a gradient characterization for a first fingerprint image are provided. One or more fingerprint feature points are selected from the first fingerprint image. A region is obtained for each of the one or more selected fingerprint feature points. The region is a representation of an area proximate a given fingerprint feature point. Each of the obtained regions is divided into a plurality of sub-regions. A histogram is generated for each of the plurality of sub-regions. For each of the one or more selected fingerprint feature points, the one or more generated histograms are combined into a concatenated histogram. The concatenated histogram is used for identification purposes.

Claims

1. A method for generating a gradient characterization for a first fingerprint image, the method comprising:

selecting one or more fingerprint feature points from the first fingerprint image;

obtaining a region for each of the one or more selected fingerprint feature points, wherein the region is a representation of an area proximate a given fingerprint feature point;

dividing each of the obtained regions into a plurality of sub-regions;

generating a histogram for each of the plurality of sub-regions; and

combining the one or more generated histograms into a concatenated histogram for each of the one or more selected fingerprint feature points, wherein the concatenated histogram is used for identification purposes.

2. The method of claim 1, wherein the histogram is a histogram of oriented gradient.

3. The method of claim 1, further comprising the step of enhancing the first fingerprint image before selecting the one or more fingerprint feature points.

4. The method of claim 1, further comprising the step of rotating each obtained region into a comparable direction.

5. The method of claim 1, further comprising the step of generating a first histogram set comprising the concatenated histograms of the first fingerprint image.

6. The method of claim 5, further comprising the step of generating one or more second histogram sets using one or more second fingerprint images.

7. The method of claim 6, further comprising the step of comparing the first histogram set to the one or more second histogram sets.

8. The method of claim 7, wherein the step of comparing further comprises the step of computing a degree of correlation between the first histogram set and the one or more second histogram sets.

9. The method of claim 8, wherein the degree of correlation is based on a number of correspondences between the first histogram set and the one or more second histogram sets.

10. An article of manufacture for generating a gradient characterization for a first fingerprint image, the article comprising a computer readable storage medium including one or more programs, which when executed by a computer implement the steps of claim 1.

11. An apparatus for generating a gradient characterization for a first fingerprint image, the apparatus comprising:

a memory; and

at least one processor coupled to the memory and operative to;

(i) select one or more fingerprint feature points from the first fingerprint image;

(ii) obtain a region for each of the one or more selected fingerprint feature points, wherein the region is a representation of an area proximate a given fingerprint feature point;

(iii) divide each of the obtained regions into a plurality of sub-regions;

(iv) generate a histogram for each of the plurality of sub-regions; and

(v) combine the one or more generated histograms into a concatenated histogram for each of the one or more selected fingerprint feature points, wherein the concatenated histogram is used for identification purposes.

12. The apparatus of claim 11, wherein the histogram is a histogram of oriented gradient.

13. The apparatus of claim 11, wherein the at least one processor is further operative to enhance the first fingerprint image before selecting the one or more fingerprint feature points.

14. The apparatus of claim 11, wherein the at least one processor is further operative to rotate each obtained region into a comparable direction.

15. The apparatus of claim 11, wherein the at least one processor is further operative to generate a first histogram set comprising the concatenated histograms of the first fingerprint image.

16. The apparatus of claim 15, wherein the at least one processor is further operative to generate one or more second histogram sets using one or more second fingerprint images.

17. The apparatus of claim 16, wherein the at least one processor is further operative to compare the first histogram set to the one or more second histogram sets.

18. The apparatus of claim 17, wherein the at least one processor is further operative to compute a degree of correlation between the first histogram set and the one or more second histogram sets.

19. The apparatus of claim 18, wherein the degree of correlation is based on a number of correspondences between the first histogram set and the one or more second histogram sets.

20. A system for generating a gradient characterization for a first fingerprint image, the system comprising:

a feature locator for selecting one or more fingerprint feature points from the first fingerprint image;

a feature summarizer for obtaining a region for each of the one or more selected fingerprint feature points, wherein the region is a representation of an area proximate a given fingerprint feature point;

a feature divider for dividing each of the obtained regions into a plurality of sub-regions;

a histogram generator for generating a histogram for each of the plurality of sub-regions; and

a histogram concatenator for combining the one or more generated histograms into a concatenated histogram for each of the one or more selected fingerprint feature points, wherein the concatenated histogram is used for identification purposes.