Документ взят из кэша поисковой машины. Адрес оригинального документа : http://imaging.cs.msu.su/pub/2009.Graphicon.Krylov.Iris.ru.pdf
Дата изменения: Fri Aug 21 23:00:00 2009
Дата индексирования: Sat Apr 9 23:11:54 2016
Кодировка:

.. , .. , .. , , E-mail: paveljeva@yandex.ru, kryl@cs.msu.ru

, . . , . . : , , , .

, , , .

2. 2.1
:

n ( x) =

(-1) n e

- x2 / 2

2 n n!

H n ( x) ,

H n ( x)

- :

1.
[1] [2,3,4]. ( ) , .. . - [2], [4] . - . , , , . . [5] . . , . [6,7], , 100% .

H 0 ( x) = 1, H 1 ( x ) = 2 x, H n ( x) = 2 x H
n -1

( x) - 2 (n - 1) H

n-2

( x).

,

L2 (-, ) .
2.2
(. 1) :

n ( x ) = 0 ( x ) n ( x ) =

(-1) n e

-x

2

2 n n!

H n ( x) .

. n -

, ..

, . :

n ( x) n > 0 .

-

n ( x ) dx = 0 ( x ) n ( x ) dx = 0 n > 0
-

,

n,m

( x, y) = n ( x) m ( y) .

0

3

.2: . (), . , , , , [5] (.3).

1, 0

2, 0

.1: .

2.3
( x0 , y 0 )

I ( x, y )
m ,n

.3: . , , ( x0 , y0 ) (m,n):

( x, y )
m.n

(m,n) [4]:

M =

m,n

( x 0 , y 0 ) = ( I ( x, y )
m,n

( x, y ) )( x 0 , y 0 ) =

G

I ( x, y )

( x 0 - x, y 0 - y )dx dy,

G

m,n

L

m ,n

( x 0 , y 0 ) = sgn M

m ,n

( x0 , y 0 ) .

3.
[8,5] . , . , . 2,

Lm

,n

[5] HD ( L ) . [5] . ,

HD ( L1, 0 ) + HD ( L2, 0 ) HD ( L1, 0 ) + HD ( L2,1 ) .
, . , . , . .

I

i

.

, i- ,

i =

90 0 I i , i {1,2,3,4} .

j =1

4

I

j

, i-
, .

3.1

I ( x, y ) =

I ( x, y ) y

max
y

x

I ( x, y )

F = M 1, 0 + M 2 , 0 + M 1,1 F . ( ) 500 F ( . 5). . 5 ( 2 - ).

x - r , x + r в y + r , y + ( R + r ) , p p 2 p 2 p 2 .4. ( x p , y p ) - , r R . , , .

. 5: . . 4: I ( x, y ) , I ( x, y ) . , .. (. 6). .

3.2
1 CASIA-IrisV3 [9] FAR FRR (False Acceptance/Rejection Rate /). . Tan [2] Tan [10] Romero-Ramirez [4] Daugman [11] FAR (%) 0 0 0.001 0.001 0 0 FRR (%) 0.82 0.33 1.13 0.4 9.71 0.008 CASIA-IrisV3 CASIA-IrisV3 CASIA V1.0 CASIA V1.0 CASIA V1.0 NIST (ICE-1)

. 6: .

4.1
. ( ), . . 7 . -10є 10є.

.7: .

1: .

4.2
CASIA-IrisV3, 2655 . 2.
( 2655) - ( FAR+FRR )

4.
[5] , m ,n ( x, y ) (1,0), (1,1), (2,0). .

67 = 54+13

54

13 (0.49%)

2: .

0.33% CASIA-IrisV3 1, , . , , , . , . 500 , 100. , ( 2 ). , 100 , (.8), , 500 (.5).

.8: 100 . : 100 ( Nx в Ny ) Nx / 3 в Ny / 3 ( 3 в 3 , , 1, 0). , 61 . [9] 40 (1.5 %).

[2] L. Ma, T. Tan, D. Zhang, Y. Wang. "Local Intensity Variation Analysis for Iris Recognition", Pattern Recognition, vol. 37, no. 6, pp. 1287-1298, 2004. [3] L. Wang, M. Dai. "Extraction of Singular Points in Fingerprints by the Distribution of Gaussian-Hermite Moment", IEEE Proc. 1 Int. Conf. DFMA, pp. 206-209, 2005. [4] A. Estudillo-Romero, B. Escalante-Ramirez, "The Hermite Transform: An Alternative Image Representation Model for Iris Recognition", LNCS, no. 5197, pp. 86-93, 2008. [5] .. , .. , .. . " ", . , 1, 2009, . 36-42. [6] F. Wang, J. Han. "Robust multimodal biometric authentication integrating iris, face and palmprint", Inform. techn. and control, vol.37, no.4, pp. 326-332, 2008. [7] A.K. Jain, A. Ross. "Multibiometric Systems", Comm. of the ACM, vol. 47, no. 1, pp. 34-40, 2004. [8] A. S. Krylov, E. A. Pavelyeva. "Iris Data Parametrization by Hermite Projection Method", GraphiCon'2007 Conf. proc., p. 147-149, 2007. [9] CASIA-IrisV3: http://www.cbsr.ia.ac.cn/IrisDatabase.htm. [10] L. Ma, T. Tan, Y. Wang, and D. Zhang, "Efficient iris recognition by characterizing key local variations" IEEE Trans. on Image Processing, vol. 13, no. 6, p. 739750, 2004. [11] J. Daugman, "New Methods in Iris Recognition", IEEE Transaction on Systems, Man, Cybernetics-part B, vol. 37, no. 5, pp. 1167-1175, 2007.

Iris identification algorithm using the most informative iris points Abstract
The algorithm of human iris identification using local Hermite transform is proposed. The most informative Hermite transform functions are used to form the iris code. The compact algorithm of Hermite transform method which uses only key iris points is also proposed. This method allows to decrease considerably the number of used iris points preserving identification reliability. Keywords: iris recognition, Hermite transform, iris key points, biometrics.

5.
, , . . . . « » 2009 2013 .

- . E-mail: Paveljeva@yandex.ru. ..-.., , . . - . E-mail: kryl@cs.msu.ru.

About the authors:
Elena A. Pavelyeva is a PhD student of Faculty of Computational Mathematics and Cybernetics, Lomonosov Moscow State University (CMC MSU). E-mail: Paveljeva@yandex.ru. Dr. Andrey S. Krylov is an associated professor, Head of the Laboratory of Mathematical methods of Image Processing, CMC MSU. E-mail: kryl@cs.msu.ru.

6.
[1] J.B. Martens. "The Hermite transform-theory", IEEE Transactions on Acoustics, Speech, and Signal Processing vol. 38, no. 9, pp. 15951606, 1990.