EP0090377B1
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Finger-print identification system
Assignee: Fingermatrix Inc
•
Filing: 1983-03-25
•
Granted: 1989-09-27
•
Expires: 2003-03-25
Abstract
Abstract An automatic fingerprint enrollment and identification technique is provided for automatically processing an input image represented by pixels having either a one or a zero value. The automatic processing involves a series of steps in which the initial processing is a rough screening technique for eliminating a reasonable portion of the noise while passing through almost all of the minutia. As the steps proceed, the processing becomes more complex to provide a tighter screening out of noise while passing through as much of the minutia as possibe. The later steps by operating on relatively fewer minutia or anomaly points that the earlier steps can be economical though more complex so as to be more discriminate than the earlier steps. The processing provides an optimum trade off between enrolling as large a proportion of the population as possible while minimizing the number of false identification errors.
Inventors
- 👤 Michael Schiller
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-04 12:16
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/20; G06V10/30; G06V10/40; G06V10/70; G06V10/74; G06V10/75; G06V40/00; G06V40/10; G06V40/12; G06V40/1347; G06V40/1365; G07; G07C; G07C9/00; G07C9/30; G07C9/32; G07C9/37
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
201 words
Method of identifying fingerprint minutiae from a binary field of pixels having first and second values representing the fingerprint including scanning each of a predetermined set of anomaly templates across the field of pixels, and identifying as an anomaly each match of any of said templates against a subfield of said field of pixels, including the steps of testing a field of pixels of contrasting value around each of said identified anomalies for thickness uniformity, identifying as a minutia candidate those anomalies where the surrounding field exhibits a uniformity of thickness in accordance with first predetermined criteria to provide a set of minutia candidates, characterized by screening the set of said minutia candidates for noise anomalies using geometric criteria related to the minutia structure to provide a reduced set of minutia candidates, erecting an analytical zone around each of said reduced set of minutia candidates, within said analytical zone, comparing all anomalies except said minutia candidate to identify paired anomalies, within said analytical zone, comparing said minutia candidate with each unpaired anomaly to identify any minutia candidate anomaly pair, and eliminating from said reduced set of minutia candidates any of said minutia candidate anomaly pairs, to provide a set of minutia.
Claim 2
Dependent Claim
201 words
Method of identifying fingerprint minutiae from a binary field of pixels having first and second values representing the fingerprint including scanning each of a predetermined set of anomaly templates across the field of pixels, and identifying as an anomaly each match of any of said templates against a subfield of said field of pixels, including the steps of testing a field of pixels of contrasting value around each of said identified anomalies for thickness uniformity, identifying as a minutia candidate those anomalies where the surrounding field exhibits a uniformity of thickness in accordance with first predetermined criteria to provide a set of minutia candidates, characterized by screening the set of said minutia candidates for noise anomalies using geometric criteria related to the minutia structure to provide a reduced set of minutia candidates, erecting an analytical zone around each of said reduced set of minutia candidates, within said analytical zone, comparing all anomalies except said minutia candidate to identify paired anomalies, within said analytical zone, comparing said minutia candidate with each unpaired anomaly to identify any minutia candidate anomaly pair, and eliminating from said reduced set of minutia candidates any of said minutia candidate anomaly pairs, to provide a set of minutia.
Claim 3
Dependent Claim
34 words
Method according to Claim 1 characterized by each of said anomaly templates positioned over successive pixels so that overlapping subfields of said pixels are compared against a predetermined template to provide identification of anomalies.
Claim 4
Dependent Claim
75 words
Method according to any of Claims 1 to 2, characterized in that said step of testing comprises: counting the distances from first and second predetermined points of each of said anomaly subfields in predetermined directions to predetermined transitions between the values of said field of pixels to provide first and second distance counts, and comparing said first and second counts and eliminating from further consideration those anomalies wherein said comparison is past a predetermined threshold.
Claim 5
Dependent Claim
95 words
Method according to any of Claims 1 to 3, characterized in that said step of screening comprises: erecting a predetermined window around each of said set of minutia candidates, identifying each of said anomalies in said window, comparing the relationship between the set of said anomalies in said window against a predetermined fingerprint noise characteristic based at least in part on the number of anomalies in said window, to provide a determination of the presence of fingerprint noise, and rejecting the minutia candidate of said window where there has been a determination of fingerprint noise.
Claim 6
Dependent Claim
17 words
Method according to Claim 4 characterized by said window having the same size as said analytical zone.
Claim 7
Dependent Claim
118 words
Method according to any one of Claims 1 to 5, characterized by repeatedly scanning and analyzing a predetermined plurality of subsequent binary fields of pixels created by repeated application of the fingerprint that is subject to the initial scan, to provide a separate set of minutiae on each of said subsequent scans of said binary fields, correlating the position of said initial scan minutia against each of said subsequent scan minutiae within the corresponding subfield zone, designating as a minutia for the subsequent scan involved only those minutiae whose positions correspond within predetermined limits with the position of the initial scan minutia, and finally retaining only those minutiae which are identified in a predetermined number of said scans.
Claim 8
Dependent Claim
23 words
Method according to Claim 6, characterized in that said correlation is limited to those minutiae which have an angular correspondence within predetermined limits.
Claim 9
Dependent Claim
28 words
Method according to Claim 7, characterized in that a normalized representation of each of said minutiae in skeletal form is employed to identify the angle of said correspondence.
Claim 10
Dependent Claim
79 words
Method according to Claim 6, characterized in that said step of repeatedly scanning includes a first set of subsequent scans and a second set of subsequent scans, the correlation criteria between each minutia in each of said second sets of scans and minutiae from said initial scan being substantially tighter than the correlation criteria in each of said first sets of scans, said second set of scans applying only to individuals having more than a predetermined number of minutiae.
Claim 11
Dependent Claim
118 words
Method according to any one of Claims 1 to 9, characterized by retaining in a final enrollment file only those minutiae which are identified in a predetermined number of said scans to provide a stable, limited enrollment file, verifying the correspondence between minutiae from a binary field of pixels representing a subsequent application of an input fingerprint and said minutiae from said final enrollment file, said step of verifying employing to those employed in said step of repeatedly scanning and analyzing the binary field representing subsequent applications of the input fingerprint during the enrollment process, whereby the biases in verification are matched by and at least partially compensated by the comparable biases in the repeated scans during enrollment.
References Cited (Backward Citations)
US4151512A
Cited
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.