Fingerprint identification system

• US 5,659,626 A
• Filed: 10/20/1994
• Issued: 08/19/1997
• Est. Priority Date: 10/20/1994
• Status: Expired due to Fees

• Current Assignee: Veridian Engineering Incorporated
• Original Assignee: Calpine Corporation
• Inventors: Kiefer, Frederick W., Dennison, Raymond J., Ort, James R., Lange, Douglas L.
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Tran, Phuoc
• Application Number:
  US08/326,757
• Time in Patent Office: 1,034 Days
• Field of Search: 382/124, 382/125, 382/203, 382/204, 382/260, 382/266, 382/286
• US Class Current: 382/125
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1359 Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition

Abstract

A method for locating minutia in a gray scale image of a fingerprint using a pair of filters, called "Gabor" and "Minutia" filters, includes determining direction and spacing of ridges at regularly spaced pixels, aligning filters by ridge direction, determining outputs of filters where Gabor Filter has high level output when in parallel ridge flow and, due to phase discontinuity at a minutia, low level output when in neighborhood of a minutia. The Minutia filter exhibits opposite phenomenon, having low level output in parallel ridge flow and high output in neighborhood of a minutia. A method for creating a state map of a fingerprint includes determining image quality, identifying minutia locations, determining areas of good quality where minutia are present, areas of good quality where no minutia are present and areas where quality is below a predetermined value to reliably determine presence or absence of minutia. A method for determining location of, associating, and determining number of ridges between cores and deltas in digitized gray scale of a fingerprint image by Direct Estimation of Orientated Patterns includes determining ridge angle and frequency at regularly spaced pixels, computing gradients of ridge angles, ordering gradient according to size, creating vector field of image, measuring curling of vector field, locating cores and deltas, tracing path of constant value ridge angle between deltas and cores, calculating line integral of vector frequency along straight line from delta to core.

Claims

1. A method of detecting minutia in a fingerprint image comprising the steps of

scanning a gray scale image of a fingerprint,

determining the direction of fingerprint ridges at multiple, spaced apart locations within the fingerprint,

determining the spacing of fingerprint ridges at said multiple, spaced apart locations,

orienting a pair of filters over each of said multiple locations by reference to said ridge direction at each of said locations,

adjusting the area of said filters by reference to the spacing of said ridges at each of said locations whereby said filter observes a predetermined number of ridges,

one of said filters having a high level output when observing parallel fingerprint ridge flow and a low output when the ridge flow in not parallel, the other of said filters having a low level output when observing parallel fingerprint ridge flow and a high output when the ridge flow is not parallel,

monitoring the outputs of said filters at each of said locations,

locating a minutia by reference to simultaneous changes in the outputs of both filters, and

recording those locations indicating non-parallel ridges as an indication of a minutia.

2. The method of claim 1 further comprising the step of

determining the ratio of magnitude of the output of one filter relative to the other filter as an indication of the presence of a minutia.

3. The method of claim 1 wherein one of said filters is a Gabor Filter and the other of said filters is a Minutia filter.

4. The method of claim 1 further including the steps of

determining the quality of the image at each location,

identifying areas of good quality containing minutiae,

separately identifying areas of good quality without minutiae, and

identifying areas that are either poor quality or indeterminant as to the presence of minutia.

5. A method of detecting and recording the location of minutia in a fingerprint image comprising the steps of

scanning a gray scale image of a fingerprint,

determining the direction of fingerprint ridges at multiple, spaced apart locations within the fingerprint,

determining the spacing of fingerprint ridges at said multiple, spaced apart locations,

orienting a filter over each of said multiple locations by reference to said ridge direction at each of said locations,

adjusting the area of said filter by reference to the spacing of said ridges at each of said locations whereby said filter observes a predetermined number of ridges,

said filter having an output level which is a function of relative angle of ridges adjacent the location being observed,

and recording those locations indicating non-parallel ridges as an indication of minutia.

6. Apparatus for locating minutiae contained in a fingerprint image comprising means for determining the direction of fingerprint ridges at multiple locations,

means for determining the spacing of said fingerprint ridges at each of said multiple locations,

means responsive to said direction determining means and said spacing determining means for detecting a phase discontinuity in the ridge flow of the fingerprint image at each of said multiple locations, wherein said means for determining the phase discontinuity in the ridge flow of fingerprint image, which indicates a ridge ending or bifurcation, comprises

a Gabor filter having a high level output when observing parallel fingerprint ridge flow and a low output when the ridge flow is not parallel,

a Minutiae Filter having a low level output when observing parallel fingerprint ridge flow and a high output when the ridge flow is not parallel,

means responsive to said direction determining means for aligning said Gabor Filter and said Minutiae Filter with the fingerprint at each of said multiple locations,

means responsive to said spacing determining means for adjusting the size of said Gabor Filter and said Minutiae Filter calculation kernel to view a predetermined number of fingerprint ridges, and

means for determining the ratio of the outputs of said filters as they are aligned at each of said multiple locations to identify minutiae, and

means for recording the location of said phase discontinuities.

7. A method for creating and recording for future use an image state map containing image quality and areas of minutiae locations of a fingerprint image comprising the steps of

converting a fingerprint image into a digitized gray scale image comprising a plurality of individual pixels,

determining the quality of the fingerprint image at regularly spaced individual pixels,

determining the quality of minutiae located on said fingerprint image,

determining the location of minutiae within said fingerprint image,

recording on said state map those areas where no minutiae are detected,

identifying on said state map those areas where minutiae are present,

and recording on said state map those areas where the quality of the image is too poor to reliably determine the presence or absence of minutiae or where minutiae were detected having a quality value below a predetermined value.

8. A method of determining the location of core and delta features in an image of a fingerprint comprising the steps of

scanning a gray scale image of a fingerprint,

measuring and mapping ridge angle and ridge frequency and associated image quality,

computing a gradient map,

finding and rank ordering gradient features and measuring and recording associated image quality, and

applying vector field mathematics of Direct Estimation of Orientated Patterns to said gradient map to determine core and delta type to each gradient feature.

9. The method of claim 8 further including the step of detecting an associated pair of deltas and cores, or cores and cores, by tracing a path of constant value ridge angle between said deltas and cores, or cores and cores.

10. The method of claim 9 further including the step of determining the ridge count between associated cores and deltas.

11. The method of claim 10 wherein the step of determining ridge count includes the step of

calculating the line integral of the vector ridge frequency along a straight line from one feature to another.

12. Apparatus for recording in machine readable form the existence and location of cores and deltas in an image of a fingerprint, said apparatus including

means for converting a fingerprint image into a digitized gray scale image comprising a plurality of individual pixels,

means for determining the ridge angle and quality of the fingerprint image at regularly spaced individual pixels to create a Ridge Angle Map and an image quality map,

means for computing the gradients of said Ridge Angle Map to derive the location of possible cores and deltas,

means for sorting the gradients according to size,

means for creating a vector field representation of said fingerprint image,

means for detecting and measuring the curling of said vector field, and

means responsive to said detecting means for identifying cores and deltas.

13. The apparatus of claim 12 further comprising

means for detecting an associated pair of deltas and cores, or cores and cores, by tracing a path of constant value ridge angle between said deltas and cores, or cores and cores.

14. The apparatus of claim 13 further including

means for calculating the number of fingerprint ridges between associated deltas and cores.

15. The apparatus of claim 14 wherein said means for calculating the number of fingerprint ridges includes means for calculating the line integral of the vector frequency along a straight line from a delta to an associated core.