Документ взят из кэша поисковой машины. Адрес оригинального документа : http://imaging.cmc.msu.ru/pub/2011.IIP.Pavelyeva_Krylov.Iris.ru.pdf Дата изменения: Mon Aug 11 15:26:59 2014 Дата индексирования: Sat Apr 9 22:33:46 2016 Кодировка: koi8-r

ИНФОРМАТИКА И Еї ПРИМЕНЕНИЯ, 2011. Т. 5. Вып. 1. С. 6872


. . 1 , . . 2
: . . , , , . CASIA-IrisV3. : ; ; ;



1



: ( ) ( ). [1] , , (. 1). . [2, 3] -

() . . [4] [5]. CASIA-IrisV3 [6], , ,

. 1


. 2
CASIA



10-07-00433 « - » 2009­2013 . «» 20- -2010, .-, 20­24 2010 . 1 . . . , , paveljeva@yandex.ru 2 . . . , , kryl@cs.msu.ru

68




0,23% . CASIA . 2. . , -- , . . .

, [4] 1,0 (. 5). , , , .

2



, [4] , . () (. 3). . [4]. (. . 3). , (). , . (. 4), -

. 1,0 (x, y ) = 5 -(x2 +y 2 )
= -( 2/ )xe

3
mask (i, j ) 1, , . 0. , [7] (Canny Edge detector). 245, . : TL = 0, TH = 30 = 5 -

. 3

. 6 (); . 4 ,
( ) ( ); (). -- , 69

5 1 2011


. . , . .

( ); = 1, TL = 0, TH = 50. , . . 6.

c - n

m, m

( ) =

n! cosn-m sinm , (n - m)!m! m = 0, . . . , n ;

4
(. 7), . ( ) , .

p - "n

k ,k

( ) =



2n (n - k )!k ! 2 cos(n - 2k ) , n! 0k< 2n (n - k )!k ! ; n! n ; 2

k = n-k;

2n (n - k )!k ! 2 sin(n - 2k ) , n! n
: : l l
p n-m,m p m,n-m

() ()

=
p n-m,m p m,n-m

=

l cos(n - 2m) sin(n - 2m) · - sin(n - 2m) cos(n - 2m) l

.

. 7


. li,j -- [8, 9] , . . ( ):


l

i,j

=
-

dy
-

I (x, y )i,j (x, y ) dx .

p ln-k,k ln-m,m : n

. 8 () ( ) ()

l

p n-k,k

=
m =0

Gcp (m, k )l n
2

n-m,m

;

Gcp n

1 (m, k ) = 2

c - n
0

m, m

( )p - "n

k ,k

( ) d ; . 9
5 1 2011

70




. 10 ( ) , ( ) . , -- N в N . (r = N/3). 64 , , N в N (. 8, ). (. 8, ). ln-i,i n = 0, 1, . . . , 63, i = 0, 1, . . . , n , = ±2 , ±4 , . . . , ±20. . , , . . 9. , (. 10). F (x0 , y0 ) = (I (x, y )1,0 (x, y ))(x0 , y0 ), -- . ( ) N (N = 300) , : N/2 F ( . 12), 2 , N/2 -- F ( ). .

. 11


. 12


5.1
[4] , 150 (. 13). . ( , -- ), . i Mi , Mi /ki .
71

5



(. 11), .

5 1 2011


. . , . .

, . , , , . CASIA-IrisV3.


. 13 1. Proenca H. Iris recognition: On the segmentation of degraded images acquired in the visible wavelength // IEEE Transaction on Pattern Analysis and Machine Intelligence, 2010. Vol. 32. No. 8. P. 1502­1516. 2. Daugman J. How iris recognition works // IEEE Transactions on Circuits and Systems for Video Technology, 2004. Vol. 14. No. 1. P. 21­30. 3. Hollingsworth K., Bowyer K., Flynn P. The best bits in an iris code // IEEE Transaction on Pattern Analysis and Machine Intelligence, 2009. Vol. 31. No. 6. P. 964­973. 4. . ., . . // , 2010. . 4. . 1. . 79­82. 5. Martens J.-B. The Hermite transform-theory // IEEE Transactions on Acoustics, Speech, and Signal Processing, 1990. Vol. 38. No. 9. P. 1595­1606. 6. CASIA-IrisV3. http://www.cbsr.ia.ac.cn/ IrisDatabase.htm. 7. Canny J. A computational approach to edge detection // IEEE Transaction on Pattern Analysis and Machine Intelligence, 1986. Vol. 8. P. 34­43. 8. Martens J.-B. Local orientation analysis in images by means of the Hermite transform // IEEE Transactions on Image Processing, 1997. Vol. 6. No. 8. P. 1103­1116. 9. Kutovoi A. V., Krylov A. S. A new method for texture-based image analysis // GraphiCon'2006: Conference Proceedings. -- Novosibirsk, 2006. P. 235­238.

ki , kmean = 2,08. , i Ni , [Mi /kmean , Mi ]. , Nmean = 300.

5.2
, , [4] ( -- ) . . , 100%- CASIA-IrisV3.

6
, -

72

5 1 2011