Fingerprint identification method
The present invention provides fingerprint-based verification system and fingerprint identification method. The fingerprint-based verification system verifies identify by analyzing biometric minutiae including the ridges and pores on a fingerprint. The fingerprint identification method comprises a step for obtaining a first fingerprint, a step for obtaining a second fingerprint, and a step for comparing the first fingerprint and the second fingerprint. The present invention provides effective systems and methods for mitigating identity fraud.
1. A method for identifying fingerprints, comprising:
obtaining a first fingerprint image from a first subject;
extracting a first ridge-based information and a first pore-based information from the first fingerprint image, wherein the first pore-based information comprises a first descriptor;
obtaining a second fingerprint image from a second subject;
extracting a second ridge-based information and a second pore-based information from the second fingerprint image, wherein the second pore-based information comprises a second descriptor;
generating a ridge similarity score by comparing the first ridge-based information and the second ridge-based information;
generating a pore similarity score by comparing the first pore-based information and the second pore-based information; and
determining the identity of the second subject based on the ridge similarity score and the pore similarity score;
wherein the first descriptor and the second descriptor each represents the pairing status of a pore.
2. The method according to claim 1 , wherein the step of obtaining the first fingerprint image and the step of obtaining the second fingerprint image are performed with one selected from the group consisting of an optical sensor, a capacity sensor, and a thermal sensor.
3. The method according to claim 2 , wherein the optical sensor has a resolution of 500 dpi or above.
4. The method according to claim 1 , wherein the first ridge-based information and the second ridge-based information are each selected from the group consisting of a singular point, a deflection point, a ridge class, a skeleton coordinate system, a feature point, and the combination thereof.
5. The method according to claim 4 , wherein the first pore-based information and the second pore-based information each comprises multiple descriptors.
6. The method according to claim 5 , wherein one of the multiple descriptors represents the completeness of a pore.
7. The method according to claim 5 , wherein one of the multiple descriptors represents the shape of a pore.
8. The method according to claim 5 , wherein one of the multiple descriptors represents the order of a pore.
9. The method according to claim 5 , wherein one of the multiple descriptors represents the angle between a pore and a reference.
10. A method for identifying fingerprints, comprising:
obtaining a first fingerprint image from a first subject;
converting half-closed pores and open pores in the first fingerprint image into closed pores;
extracting a first ridge-based information and a first pore-based information from the first fingerprint image, wherein the first pore-based information comprises a first descriptor;
obtaining a second fingerprint image from a second subject;
converting half-closed pores and open pores in the second fingerprint image;
extracting a second ridge-based information and a second pore-based information from the second fingerprint image, wherein the second pore-based information comprises a second descriptor;
generating a ridge similarity score by comparing the first ridge-based information and the second ridge-based information;
generating a pore similarity score by comparing the first pore-based information and the second pore-based information; and
determining the identity of the second subject based on the ridge similarity score and the pore similarity score.
11. The method according to claim 10 , wherein the step of obtaining the first fingerprint image and the step of obtaining the second fingerprint image each further comprises the sub-steps of:
forming a principal axis on the skeleton coordinate system.
12. The method according to claim 11 , wherein the first descriptor and the second descriptor each represents a semi-ridge, defined by the principal axis, which a pore is located at.
13. The method according to claim 12 , wherein the first descriptor and the second descriptor each represents the distance between a pore and the principal axis.
14. A method for mitigating identity fraud, comprising:
obtaining a first fingerprint image from a first subject;
converting half-closed pores and open pores in the first fingerprint image into closed pores;
extracting a first pore-based information from the first fingerprint image, wherein the first pore-based information comprises a first descriptor;
obtaining a second fingerprint image from a second subject;
converting half-closed pores and open pores in the second fingerprint image;
extracting a second pore-based information from the second fingerprint image, wherein the second pore-based information comprises a second descriptor;
generating a pore similarity score by comparing the first pore-based information and the second pore-based information; and
determining whether the pore similarity score satisfies a pre-determined value.