Fingerprint recognition for low computing power applications

Abstract

A method and apparatus are provided for improved fingerprint recognition. A fingerprint image associated with an authorized user can be captured with a sensor. Direction vectors for a plurality of pixels of the first fingerprint image are then calculated. Next, characteristic points of the fingerprint image are located in first coordinate system. The fingerprint central nucleus is determined based on the calculated direction vectors, and is expressed in the first coordinate system. Subsequently, a second coordinate system having an origin located relative to the fingerprint central nucleus is determined. Thereafter, the characteristic points of the fingerprint image are mapped to the second coordinate system. Finally, the fingerprint central nucleus and fingerprint characteristic points expressed in the second coordinate system are saved as a fingerprint template.

1 .- 18 . (canceled) 
     
     
         19 . A system for fingerprint recognition, the system comprising:
 a fingerprint sensor configured to capture a first fingerprint image;   a database remote from and in operative communication with the fingerprint sensor configured to store a fingerprint template associated with a reference fingerprint image, the fingerprint template including fingerprint template information corresponding to a fingerprint central nucleus and fingerprint characteristic points of the reference fingerprint image, the fingerprint template information further including direction vectors calculated for a plurality of pixels of the reference fingerprint image; and   a processor remote from and in operative communication with the fingerprint sensor configured to:
 (a) access the fingerprint template information stored at the database; 
 (b) receive the first fingerprint image from the fingerprint sensor; 
 (c) calculate direction vectors for a plurality of pixels of the first fingerprint image; 
 (d) locate characteristic points of the first fingerprint image in a first coordinate system; 
 (e) determine a fingerprint central nucleus based on the direction vectors of the first fingerprint image, wherein the fingerprint central nucleus is expressed in the first coordinate system; 
 (f) map the characteristic points and the fingerprint central nucleus of the first fingerprint image to a second coordinate system, the second coordinate system having an origin located relative to the fingerprint central nucleus of the reference fingerprint image; and 
 (g) compare the characteristic points and the fingerprint central nucleus of the first fingerprint image to the accessed fingerprint template information, the accessed fingerprint template information including the fingerprint central nucleus and the fingerprint characteristic points of the reference fingerprint image expressed in the second coordinate system, 
   wherein the fingerprint central nucleus of the reference fingerprint image is a center point of adjacent pixels determined by calculating a minimum radius from a plurality of radii of curvature based on the direction vectors of the reference fingerprint image, the adjacent pixels being adjacent to the minimum radius.   
     
     
         20 . The system of  claim 19 , wherein the reference fingerprint image is associated with an authorized user. 
     
     
         21 . The system of  claim 19 , wherein the fingerprint sensor is implemented on a stand alone IC card. 
     
     
         22 . The system of  claim 19 , wherein the fingerprint sensor is configured to read a fingerprint of a user and is at least one of: a biometric sensor, an optical sensor, a semiconductor sensor, or an ultrasound sensor. 
     
     
         23 . The system of  claim 19 , wherein the second coordinate system is a polar coordinate system representing an angle and a distance from its origin relative to the fingerprint central nucleus of the reference fingerprint image. 
     
     
         24 . The system of  claim 19 , wherein the second coordinate system is a multi-dimensional coordinate system having at least three dimensions. 
     
     
         25 . The system of  claim 24 , wherein one of the at least three dimensions indicates a pixel gradient intensity. 
     
     
         26 . A method for fingerprint recognition, the method comprising:
 accessing a fingerprint template associated with a reference fingerprint image, the fingerprint template including fingerprint template information corresponding to a fingerprint central nucleus and fingerprint characteristic points of the reference fingerprint image, the fingerprint template information further including direction vectors calculated for a plurality of pixels of the reference fingerprint image;   capturing a first fingerprint image with a sensor;   calculating direction vectors for a plurality of pixels of the first fingerprint image;   locating characteristic points of the first fingerprint image in a first coordinate system;   determining a fingerprint central nucleus of the first fingerprint image based on the direction vectors of the first fingerprint image, wherein the fingerprint central nucleus of the first fingerprint image is expressed in the first coordinate system;   mapping the characteristic points and the fingerprint central nucleus of the first fingerprint image to a second coordinate system, the second coordinate system having an origin located relative to the fingerprint central nucleus of the reference fingerprint image; and   comparing the characteristic points and the fingerprint central nucleus of the first fingerprint image to the accessed fingerprint template information, the accessed fingerprint template information including the fingerprint central nucleus and the fingerprint characteristic points of the reference fingerprint image expressed in the second coordinate system,   wherein the fingerprint central nucleus of the reference fingerprint image is a center point of adjacent pixels determined by calculating a minimum radius from a plurality of radii of curvature based on the direction vectors of the reference fingerprint image, the adjacent pixels being adjacent to the minimum radius.   
     
     
         27 . The method of  claim 26 , wherein the fingerprint characteristic points of the reference fingerprint image are represented in the first coordinate system as (X i , Y i ), wherein i=1, 2, 3, 4, and wherein the reference fingerprint central nucleus of the reference fingerprint image is represented in the first coordinate system as (X, Y). 
     
     
         28 . The method of  claim 27 , wherein the fingerprint central nucleus of the reference fingerprint image is represented in the second coordinate system as (ξ, η), wherein the fingerprint central nucleus of the reference fingerprint image is determined by solving the following equations for ξ, η:
     X =Σ( X   i ×Ø i ),
 
     Y =Σ( Y   i ×Ø i ),
 
   Ø 1 =0.25×(1−ξ)×(1·η),
 
   Ø 2 =0.25×(1+ξ)×(1−η),
 
   Ø 3 =0.25×(1−ξ)×(1·η),
 
   and 
   Ø 4 =0.25×(1·ξ)×(1+η).
 
 
     
     
         29 . The method of  claim 26 , further comprising after the capturing:
 verifying the quality of the first fingerprint image; and   based on the verifying, removing image noise from the first fingerprint image.   
     
     
         30 . The method of  claim 26 , further comprising:
 determining that each of the characteristic points and the fingerprint central nucleus of the first fingerprint image match with a corresponding one of the characteristic points and central nucleus of the reference fingerprint image of the accessed fingerprint information.   
     
     
         31 . The method of  claim 30 , further comprising:
 generating a fingerprint match based on determining that each of the characteristic points and the fingerprint central nucleus of the first fingerprint image match with a corresponding one of the characteristic points and central nucleus of the reference fingerprint image of the accessed fingerprint information.   
     
     
         32 . The method of  claim 26 , wherein the reference fingerprint image is associated with an authorized user. 
     
     
         33 . The method of  claim 26 , wherein the second coordinate system is a multidimensional coordinate system having at least three dimensions, and wherein one of the at least three dimension indicates a pixel gradient density. 
     
     
         34 . A system for fingerprint recognition, the system comprising:
 a fingerprint sensor configured to capture a first fingerprint image;   a database configured to store a fingerprint template associated with a reference fingerprint image, the fingerprint template including fingerprint template information corresponding to a fingerprint central nucleus and fingerprint characteristic points of the reference fingerprint image, the fingerprint template information further including direction vectors calculated for a plurality of pixels of the reference fingerprint image; and   a processor configured to:
 (a) access the fingerprint template information stored at the database; 
 (b) receive the first fingerprint image from the fingerprint sensor; 
 (c) calculate direction vectors for a plurality of pixels of the first fingerprint image; 
 (d) locate characteristic points of the first fingerprint image in a first coordinate system; 
 (e) determine a fingerprint central nucleus based on the direction vectors of the first fingerprint image, wherein the fingerprint central nucleus is expressed in the first coordinate system; 
 (f) map the characteristic points and the fingerprint central nucleus of the first fingerprint image to a second coordinate system, the second coordinate system having an origin located relative to the fingerprint central nucleus of the reference fingerprint image; and 
 (g) compare the characteristic points and the fingerprint central nucleus of the first fingerprint image to the accessed fingerprint template information, the accessed fingerprint template information including the fingerprint central nucleus and the fingerprint characteristic points of the reference fingerprint image expressed in the second coordinate system, 
   wherein the fingerprint central nucleus of the reference fingerprint image is a center point of adjacent pixels determined by calculating a minimum radius from a plurality of radii of curvature based on the direction vectors of the reference fingerprint image, the adjacent pixels being adjacent to the minimum radius.   
     
     
         35 . The system of  claim 34 , wherein the fingerprint sensor, the database, and the processor are implemented on an IC card. 
     
     
         36 . The system of  claim 34 , wherein the fingerprint sensor, the database, and the processor are implemented as stand alone components. 
     
     
         37 . The system of  claim 36 , wherein the sensor, the database, and the processor are in operative communication. 
     
     
         38 . The system of  claim 34 , wherein the fingerprint sensor is implemented on a stand alone IC card remote from and in operative communication with the database and the processor.