EP1126403A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Automated, non-invasive iris recognition system and method
Assignee: Sensar Inc
•
Filing: 1995-09-05
•
Granted: —
•
Expires: 2015-09-05
Abstract
Abstract Iris recognition is achieved by iris acquisition that permits a user to self-position his or her eye (216) into an imager's (200) field of view without the need for any physical contact, spatially locating the data defining that portion of a digitised video image of the user's eye that defines solely the iris thereof without any initial spatial condition of the iris being provided , and pattern matching the spatially located data defining the iris of the user's eye with stored data defining a model iris by employing normalised spatial correlation for first comparing, at each of a plurality of spatial scales, each of distinctive spatial characteristics of the respective irises that are spatially registered with one another to quantitatively determine, at each of the plurality of spatial scales, a goodness value of match at that spatial scale, and then judging whether or not the pattern which manifests solely the iris of the user's eye matches the digital data which manifests solely the model iris in accordance with a certain combination of the quantitatively-determined goodness values of match at each of said plurality of spatial scales.
Inventors
- 👤 Richard Patrick Wildes
- 👤 Jane Circle Asmuth
- 👤 Keith James Hanna
- 👤 Stephen Charles Hsu
- 👤 Raymond Joseph Kolczynski
- 👤 James Regis Matey
- 👤 Sterling Eduard Mcbride
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-06 17:39
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/10; G06V40/18; G07; G07C; G07C9/00; G07C9/30; G07C9/32; G07C9/37; G06V10/00; G06V10/20; G06V10/24; G06V10/245
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
190 words
In an image-processing method responsive to digital data defining a
digitized image of the eye of an individual for delimiting said digital data to
that portion thereof that defines solely the iris of said eye of said individual;
wherein said method includes a delimiting step of locating that data which is
within the image of said individual 's eye that defines at least one of the limbic
boundary of said iris, the pupilary boundary of said iris, and the boundaries of
said eye's upper and lower eyelids; the improvement wherein said delimiting
step comprises the steps of: a) image-filtering said one of the limbic boundary of said iris, the
pupilary boundary of said iris, and the boundaries of said eye's upper and
lower eyelids to derive an enhanced image thereof; and b) histogramming said enhanced image, in which said histogramming
step embodies a voting scheme for recovering said one of said iris boundaries
from said enhanced image; whereby said recovery of said one of said iris boundaries does not
require knowledge of any initial conditions other than the digital data defining
said digitized image of said eye of said individual.
Claim 2
Dependent Claim
127 words
The method of Claim 1, wherein said delimiting step includes the
sequential steps of: c) first, locating that portion of said digital data that defines said limbic
boundary of said iris; d) second, locating that portion of said digital data which is within said
limbic boundary that defines said pupilary boundary of said iris; e) third, locating that portion of said digital data which is within said
limbic boundary that defines said boundaries of said eye's upper and lower
eyelids; and f) fourth, employing only that portion of said digital data that is outside
of said pupilary boundary, inside said limbic boundary, and below the upper
eyelid and above the lower eyelid thereby to delimit said digital data to that
portion thereof which manifests said eye's iris.
Claim 3
Dependent Claim
104 words
The method of Claim 2, wherein step (c) includes the steps of: g) employing gradient-based edge detector filter means tuned in
orientation to favor near verticality for detecting edge data; and h) thinning and then histogramming said detected edge data into a
three-dimensional (xc, yc, r)-space, according to permissible (xc, yc, r) values
for a given (x, y) image location in accordance with a model of said limbic
boundary as a circle parameterized by its two center coordinates, xc and yc,
and its radius r; whereby the (xc, yc, r) point with the maximal number of votes is
taken to represent the limbic boundary.
Claim 4
Dependent Claim
103 words
The method of Claim 2, wherein step (d) includes the steps of: g) employing gradient-based edge detector filter means that is
directionally untuned in orientation for detecting edge data; and h) thinning and then histogramming said detected edge data into a
three-dimensional (xc, yc, r)-space, according to permissible (xc, yc, r) values
for a given (x, y) image location in accordance with a model of said pupilary
boundary as a circle parameterized by its two center coordinates, xc and yc,
and its radius r; whereby the (xc, yc, r) point with the maximal number of votes is
taken to represent the pupilarv boundary.
Claim 5
Dependent Claim
94 words
The method of Claim 2, wherein step (e) includes the steps of: g) employing gradient-based edge detector filter means tuned in
orientation to favor the horizontal for detecting edge data; and h) thinning and then histogramming said detected edge data into a
three-dimensional space, according to permissible values for a given image
location in accordance with a model of each of said eye's upper eyelid
boundary and lower eyelid boundary as a parabolic parameterized by second-order
arcs; whereby the spatial point with the maximal number of votes is taken
to represent that eyelid boundary.
Claim 6
Dependent Claim
35 words
The method of Claim 1, further including the further step of: low-pass filtering and then subsampling said digital data defining said
digitized image of said eye of said individual prior to performing said delimiting
step.
Claim 7
Dependent Claim
195 words
In an image-processing method for use in providing automated iris
recognition for security access control; said method being responsive to first
digital data defining a digitized image of solely the iris of the eye of a certain
individual attempting access and previously stored second digital data of a
digitized image that defines solely the iris of the eye of a specified individual;
wherein said method includes a pattern-matching step that comprises the
steps of: a) employing normalized spatial correlation for first comparing, at each
of a plurality of spatial scales, each of distinctive spatial characteristics of
the respective irises of said given individual and said specified individual that
are spatially registered with one another to quantitatively determine, at each
of said plurality of spatial scales, a goodness value of match at that spatial
scale; and b) judging whether or not the pattern of said digital data which
manifests solely said iris of said eye of said given individual matches said
digital data which manifests solely the iris of an eye of said specified individual
in accordance with a certain combination of the quantitatively-determined
goodness values of match at each of said plurality of spatial scales.
Claim 8
Dependent Claim
84 words
The method of Claim 7, wherein step (a) comprises the step of: c) providing area-based image registration utilizing a mapping function
(u(x,y),v(x,y)) constrained to be a similarity transformation of translational
shift, scale and rotation, such that, for all (x,y), the data value at (x,y)-(u(x,y),v(x,y))
in the first digital data which manifests solely said iris of said
eye of said given individual is close to that at (x,y) of said second digital data
which manifests solely the iris of an eye of said specified individual.
Claim 9
Independent Claim
61 words
The method of Claim. 7, wherein step (a) comprises the step of: c) performing normalized spatial correlation over given spatial blocks
made up of a first plurality of data points in a first spatial dimension of each
of said plurality of scales and a second plurality of data points in a second
spatial dimension of each of said plurality of scales.
Claim 10
Dependent Claim
47 words
The method of Claim 9, wherein step (c) comprises the step of: d) combining said normalized spatial correlation over said given spatial
blocks via a median statistic at each of said plurality of spatial scales for
quantitatively determining said goodness value of match at that spatial
scale.
Claim 11
Dependent Claim
52 words
The method of Claim 7, wherein step (b) comprises the step of: c) combining the quantitatively-determined goodness values of match
at each of said plurality of spatial scales so that the variance within various
instances of the same iris is minimized and the variance within various
instances of different irises is maximized.
Claim 12
Dependent Claim
42 words
The Method of Claim 11, wherein step (c) comprises the step of: d) employing Fisher's Linear Discriminant as a linear function that
minimizes the variance among various instances of the same iris and
maximizes the variance among various instances of different irises.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.