Method for identifying and/or authenticating an individual by iris recognition
View Patent ↗A method for identifying and/or authenticating an individual by a system including a storage device storing at least one binary code of a reference iris and a binary code of an associated reference mask: acquisition of an image of an eye of the individual, segmentation of the acquired image to isolate a region containing the texture of the iris and determine an associated mask, division of the region and the mask into N2 concentric rings, normalization of the region, determination of a binary iris code IC and a binary code of mask IM matching at least one ring of the iris with a ring of the reference iris to minimize a matching distance between the acquired image and the reference image, computation of the minimized matching distance, identification and/or authentication of the individual if the minimized matching distance is less than a predetermined threshold.
1. A method for identifying and/or authenticating an individual comprising the following steps performed by a system for identifying and/or authenticating an individual,
said system for identifying and/or authenticating an individual comprising a storage device storing at least one binary code of a reference iris obtained from a reference iris image divided into a first predetermined number N1 of concentric rings, and a binary code of associated reference mask identifying regions of the reference iris in which eyelids, eyelashes, reflections or other sources of noise have been detected:
acquisition of an image of an eye of the individual to be identified and/or authenticated,
segmentation of the acquired image of the eye so as to isolate a region containing the texture of the iris and determine an associated mask,
division of said region containing the iris texture and of said mask into a second number N2 of concentric rings,
normalization of said region containing the texture of the iris and of said mask of Cartesian coordinates into polar coordinates,
determination of a binary iris code IC of size equal to N2*P*F coding said region containing the texture of the normalized iris and a binary code of mask IM of size equal to N2*P*F coding the associated mask, by application of a third predetermined number of Gabor filters F to each position from a fourth predetermined number P of positions of each ring,
matching at least one ring of the iris of the acquired image with a ring of one of said reference irises so as to minimize a matching distance between the acquired image and the reference image, said matching distance being obtained from the determined and stored reference iris codes and the associated mask codes by computing a sum of distances between each of said rings of the matched acquired image iris and the ring of the reference iris which corresponds to it,
wherein said match comprises computation of a comparison matrix M of size N1*N2, each coefficient M(i,j) of said comparison matrix coding the result of the comparison between the i th ring of the stored reference iris and the j th ring of the iris of the acquired image by means of said determined and reference iris codes and the associated mask codes,
computation of said minimized matching distance,
identification and/or authentication of the individual if said minimized matching distance is less than a predetermined threshold.
2. The identification and/or authentication method according to claim 1 wherein the matching step implements a Viterbi algorithm.
3. The identification and/or authentication method according to claim 2 wherein the matching step comprises:
construction of a Viterbi trellis wherein the cost for each matching of a ring i of the reference iris and of a ring j of the iris of the acquired image is:
for
i
=
1
,
Cost
(
i
,
j
)
=
Prob
(
i
,
j
)
*
M
(
i
,
j
)
for
any
i
>
1
:
Cost
(
i
,
j
)
=
Prob
(
i
,
j
)
*
M
(
i
,
j
)
+
min
L
=
li
:
ls
and
k
=
k
min
:
k
max
(
ProbT
(
(
i
,
j
)
,
(
i
-
L
,
j
+
K
)
)
*
Cost
(
i
-
L
,
j
+
k
)
)
with:
li, ls, kmin, kmax predetermined relative integers, with li≥1 and 0<j+k≤N2,
Prob(i,j) a predetermined match probability of the i th ring of the reference iris and of the j th ring of the iris of the acquired image,
ProbT((i,j),(p,q)) a predetermined match probability of the p th ring of the reference iris and of the q th ring of the iris of the acquired image considering matching of the i th ring of the reference iris and of the j th ring of the iris of the acquired image,
determination of a path in said Viterbi trellis comprising:
matching a M th ring of the reference iris with the Path(M) th ring of the iris of the acquired image where Path(M) is the index belonging to [1; N2] minimizing (Cost(M,j)) over j with M an integer less than or equal to the first predetermined number N1,
matching at least one other ring of the reference iris of index M′ with a ring of the iris of the acquired image of index Path(M′), where M′<M, as a function of a ring of the reference iris of index D already matched with a ring of the iris of the acquired image of index Path(D) with M′=D−Z(D, Path(D), 1) and Path(M′)=Path(D)+Z(D, Path(D), 2), the function Z being defined from R 3 in R such that Z(i,j,1) and Z(i,j,2) are respectively the integers Lϵ[li,ls] and kϵ[kmin,kmax] minimizing the function ProbT((i,j),(i−L,j+k))*Cost(i−L,j+k).
4. The identification and/or authentication method according to claim 3 wherein computation of the minimized matching distance is carried out by means of the formula
HD
Viterbi
=
MIN
t
=
-
T
:
T
∑
i
=
1
N
Dist
(
i
,
Path
(
i
)
,
t
)
1
+
∑
i
=
1
N
Mask
(
i
,
Path
(
i
)
,
t
)
with:
T a predetermined maximum tolerance to a rotation between the acquired image and the reference image,
IC1, IC2, IM1 and IM2, matrices of size N1×(P*F) or N2×(P*F) corresponding respectively to the code of the reference iris, the code of the iris of the acquired image, and the associated mask codes,
Dist( i,j,t )=Σ p=1 P Σ f=0 F−1 |IC 1( i,p+f )− IC 2( j,p+t+f )|,
Mask( i,j,t )=Σ p=1 P Σ f=0 F−1 IM 1( i,p+f )* IM 2( j,p+t+f ).
5. The identification and/or authentication method according to claim 4 wherein each coefficient M(i,j) of said comparison matrix M is the result of a transformation LT of the ratio between Dist(i,j,t) and Mask(i,j,t) for a fixed t.
6. The identification and/or authentication method according to claim 3 wherein the probabilities ProbT and Prob are determined by automatic learning or by using a distortion model of the texture of the iris.
7. The identification and/or authentication method according to claim 3 wherein the probabilities ProbT and Prob are a function of the level of dilation of the pupil.
8. The identification and/or authentication method according to claim 1 wherein said concentric rings vary in thickness.
9. The identification and/or authentication method according to claim 1 wherein at least two of said concentric rings overlap.
10. A non-transitory computer-readable medium containing code instructions for execution of a method for identifying and/or authenticating an individual according to claim 1 when the code instructions are executed by a processor.
11. A data-processing device which is connectable to a storage device storing at least one binary code of a reference iris obtained from a reference iris image divided into a first predetermined number N1 of concentric rings, and a binary code of associated reference mask identifying regions of the reference iris wherein eyelids, eyelashes, reflections or other sources of noise have been detected wherein the data-processing device comprises:
a communications interface configured to receive an acquired image of an eye of an individual to be identified and/or authenticated;
a computer configured to:
segment the image of the eye received so as to isolate a region containing the texture of the iris and determine an associated mask,
divide said region containing the iris texture and said mask into a second number N2 of concentric rings,
normalize said region containing the texture of the iris and said mask of Cartesian coordinates into polar coordinates,
determine a binary iris code IC of size equal to N2*P*F coding said region containing the texture of the normalized iris and a binary code of mask IM of size equal to N2*P*F coding the associated mask, by application of a third predetermined number of Gabor filters F to each position from a fourth predetermined number P of positions of each ring,
match at least one ring of the iris of the acquired image with a ring of one of said reference irises so as to minimize a matching distance between the acquired image and the reference image, said matching distance being obtained from the determined and stored reference iris codes and the associated mask codes by computing a sum of distances between each of said rings of the matched acquired image iris and the ring of the reference iris which corresponds to it,
wherein said match comprises computation of a comparison matrix M of size N1*N2, each coefficient M(i,j) of said comparison matrix coding the result of the comparison between the i th ring of the stored reference iris and the j th ring of the iris of the acquired image by means of said determined and reference iris codes and the associated mask codes,
compute said minimized matching distance,
compare said minimized matching distance to a predetermined threshold.
12. A system for identifying and/or authenticating an individual comprising:
a storage device storing at least one binary code of a reference iris obtained from a reference iris image divided into a first predetermined number N1 of concentric rings, and a binary code of associated reference mask identifying regions of the reference iris wherein eyelids, eyelashes, reflections or other sources of noise have been detected,
an image capture device configured to acquire an image of an eye of the individual to be identified and/or authenticated,
a data-processing device according to claim 11 configured to minimize a matching distance, between the acquired image and the reference image, and to identify and/or authenticate the individual if said matching distance is less than said predetermined threshold.