You are on page 1of 18

  




)(15

)2010 (1


) (Histogram

C++ Builder

)
(.

: .

.1

.


.

.
.
.

.2

. : ] [12 K-mean

] [14][13

.

+ e-mail:abduohassan@yahoo.com

   


)(15

)2010 (1

.Wavelet Wavelet

.
.
: ] [15 ) (Wavelet

. ) (Daubechies' wavelet
RGB ) (

. 10000
100 3.3.

.3


.

.4

) (Search by model

.

.5
.

.6
) (two dimensional function) (
) ( " " ) ( gray level
) (intensity . " " ) (
) (discrete quantities ) (picture elements).(pixels
" " " " " "].[2][1

   


)(15

)2010 (1

 : .
 :
.
.
 :
) (
:
.1 .

.2
.
.3 ) (making sense

].[2] [1

.7 )(Histogram
) (
) (normalised histogram function .

].[3

) :(1 .

.8
1.8 RGB
C ]:[4
)(1

0 I (C ) < I max 0 I (C ) < 256

:
)(2

) I (C ) = 0.3 R (C ) + 0.59 G (C ) + 0.11 B (C

   


)(15

)2010 (1


:
p

)(3

1 N 1 1
hi 2 hi
N i =0

= ) d p ( h, h
2

:
: 1 hi , 2 hi .
:P .
:N ) (R,G,B 0 .255

)d p ( 1h, 2 h
.
.2.8
) (1
. RGB
].[6

)(4

R r 1 ( i ) = H 1 r [ i ] H 2 r [ i 1] ,
R r 2 (i) = H 1r [i] H 2 r [i] ,
]R r 3 ( i ) = H 1 r [ i ] H 2 r [ i + 1


)(5

R g 2 (i ) = H 1 g [i ] H 2 g [i ] ,
]R g 3 ( i ) = H 1 g [ i ] H 2 g [ i + 1


)(6

R g 1 ( i ) = H 1 g [ i ] H 2 g [ i 1] ,

R b 1 ( i ) = H 1 b [ i ] H 2 b [ i 1] ,
R b 2 (i ) = H 1b [i ] H 2 b [i ] ,
]R b 3 ( i ) = H 1 b [ i ] H 2 b [ i + 1

) (6 5 4 H1,H2
) (][9

   


)(15

)2010 (1

:
)(7

1 k 3

................

N 1

)) ( i

rk

min( R

= Sr

i =0

:
)(8

................

1 k 3

N 1

)) ( i

gk

min( R

= Sg

i =0

:
)(9

................

1 k 3

N 1

)) R bk ( i

( min

= Sb

i =0

RGB :

)(10

................

S r2 + S g2 + S b2

= ) d ( H 1, H 2

RGB :

2
+
2

)(11

N 1
] min( H1r [i] H2 r [i 1] , H1r [i] H2 r [i] , H1r [i] H2 r [i + 1
i =0

N 1
]d(H1, H2) = min( H1 g [i] H2 g [i 1] , H1 g [i] H2 g [i] , H1 g [i] H2 g [i + 1
i =0

N 1
] min( H1b [i] H2 b [i 1] , H1b [i] H2 b [i] , H1b [i] H2 b [i + 1
i =0

.3.8

)
20 30 ( ].[7

   


)(15

)2010 (1

] K=NumP[i NumAll
:
NumAll = width height

width, height :
] NumP [ i
= ] Pr oc [ i
100%, i K
NumAll
RGB :

)(12

..

i K

NumP[i RB(G 1) ]
] ) NumP[i GB(R 1

+
+
NumAll
NumAll

] ) NumP[i RG(B 1
] NumP[i RGB
+
+

NumAll
NumAll
100%,

=
] ) NumP[i GB(R + 1
NumP[i RB(G + 1) ]
+
+

NumAll
NumAll

] )NumP[i RG(B + 1

NumAll

]Proc[i

:
)(13

1 K 1
2
) ] (Pr ocA [ i ] Pr ocB [ i
i
=
0
K

= ) d ( A, B

A,B .

.9
) (13)-(1
.
.1.9
Pixels
) (2 :

   


)(15

)2010 (1

i
N 255
&
i +1
) I( c
N 255

) I( c

) :(2 .


).(3

   


)(15

)2010 (1

TU

1 N 1 1 2
hi hi
N i =0

10

= ) d p ( h, h
2

) :(3 .

.2.9
) (11) (4
:

   


)(15

11

)2010 (1

Sr = 0

Sb = 0

Rr 1( i ) = H 1r [ i ] H 2r [ i 1 ] ,
Rr 2 ( i ) = H 1r [ i ] H 2r [ i ] ,
] Rr 3 ( i ) = H 1r [ i ] H 2r [ i + 1

Rb1( i ) = H 1b [ i ] H 2b [ i 1 ] ,
Rb 2 ( i ) = H 1b [ i ] H 2b [ i ] ,

) Sr = Sr + min( Rr 1 , Rr 2 , Rr 3

] Rb3 ( i ) = H 1b [ i ] H 2b [ i + 1
Sg = 0

) Sb = Sb + min( Rb1 , Rb 2 , Rb3

d ( H 1, H 2 ) = Sr2 + S g2 + Sb2

Rg 1( i ) = H 1g [ i ] H 2g [ i 1 ] ,
Rg 2 ( i ) = H 1g [ i ] H 2g [ i ] ,
] Rg 3 ( i ) = H 1g [ i ] H 2g [ i + 1
) S g = S g + min( Rg 1 , Rg 2 , Rg 3

) :(4 .

.3.9

) (13) (12 :

   


)(15

)2010 (1

di = di + ( NumColor[ l ]
NCol1[ l ])2

1
di
k

= di

) :(5 .

12

   


)(15

)2010 (1

13

.10 ) (
C++ Builder
.

) :(6 %& '()*+ "! .

) :(7 .

   


)(15

)2010 (1

14

:
.1 .
.2 .
.3 .
.4 .
.5 .
.6 .

) :(8 .

:
.1 .
.2 .
.3 .
.4 ) (.
.5 ) (.
.6 .
) (9
) (10
:
10x10, 50x50, 100x100, 200x200, 500x500, 1024x1024, 2048x2048

   


)(15

15

)2010 (1


.

.

) :(9 .

)(

)(

)(

)(

)(
) :(10

:
Athlon 1600GH : 256 MB : 128 MB : .XP

   


)(15

16

)2010 (1

.1.10
) (1 ) (
).(3) (2) (1
) :(1 .

2048 * 2048

1024 * 1024

500 * 500

200 * 200

100 * 100

50 * 50

10 * 10


1
2

6.9996
12.9996

3.1998
4.9998

0.9996
1.9998

0.4596
0.9996

0.2396
0.4396

0.1799
0.358

0.0733
0.1632

18.9996

7.9998

3.1998

1.3996

0.8996

0.527

0.2332

25.9998

9.9996

3.996

1.7996

1.2096

0.708

0.3232

34.9998

12.9996

4.99

2.2496

1.5196

0.8798

0.4042

) (1

.
.2.10
) (2 ) (
).(11) (4
) :(2 .

2048 * 2048

1024 * 1024

500 * 500

200 * 200

100 * 100

50 * 50

10 * 10


1
2

12.996
24.996

3.1998
6.9996

1.9998
3.3998

1.6998
3.1996

1.3998
1.9998

0.9996
1.0533

0.3998
0.5998

36.996

9.9996

5.1798

3.9996

3.6996

2.6998

0.9996

49.998

12.9996

7.9998

4.9998

4.6998

3.6998

1.9998

61.998

15.9996

7.9998

6.9996

6.6996

5.9998

2.6666

.3.10
) (3
.

   


)(15

17

)2010 (1

) :(3 .

2048 * 2048

1024 * 1024

200 * 200

500 * 500

100 * 100

10 * 10

50 * 50

26.0196

9.996

6.9996

5.0196

4.098

1.7

0.998

45.9996

15.3996

7.9998

6.9998

4.9998

2.98

1.54

66.9996

21.3996

9.1998

7.598

6.09

3.99

2.23

87.9798

26.0196

9.9798

8.7998

7.088

4.9998

3.128

109.9998

30.9996

10.9998

9.498

7.98

5.98

4.09

) (12) (11 :
: X .
:Y .
:


:
.

:
.
) :(4 .

"; 678

10 * 10

50 * 50

100 *100

200 *200

500 *500

1024 *1024

2048 *2048

%& '()*+ <7!=+ "!

0.0733

0.1799

0.2396

0.4596

0.9996

3.1998

6.9996

<7!=+" C!D>?)@AB

0.3998

0.9996

1.3998

1.6998

1.9998

3.1998

12.996

6*DE <7!=+"!

0.998

1.7

4.098

5.0196

6.9996

9.996

26.0196








) (


















 
 
   
   
) :(11 ) : (.

   


)(15

18

)2010 (1

) :(5 .

"; 678

10x10

50x50

100x100

200x200

500x500

1024x1024

2048x2048

%& '()*+ <7!=+ "!

0.4042

0.8798

1.5196

2.2496

4,99

12.9996

34.9998

<7!=+" C!D>?)@AB

2.6666

5.9998

6.6996

6.9996

7.9998

15.9996

61.998

6*DE <7!=+"!

4.09

5.98

7.98

9.498

10.9998

30.9996

109.9998








) (




 





 

 

 



 
 
   
   
) :(12 ) : (







.
)
( 75 75 )
( :
) :(6 .

) 75 (

) 75 (

64

4,6

80

45,3

16

   


)(15

)2010 (1

19


%100
(
)

.

.11


:
.1

.
.2
.
.3
.

.12
Gonzales, R. Woods, R. "Digital Image Processing". (Addison-Wesley -2002).
Azriel, R. Avinash, "Digital Picture Processing". (Academic Press, 1982).
Rajeev, Ramanath. "Interpolation methods for the bayer color array", (Masters thesis,
NorthCarolina State University, 2000).
Said A., Pearlman W.A. "New Fast and Efficient Image Codec Based on Set
Partitioning in Hierarchical Trees", (IEEE Trans. on Circuits and Systems for Video
Technology June 1996).
Carson, C., Belongie, S., Greenspan, H., Malik, J., "Color- and Texture-Based Image
Segmentation Using EM and Its application to Image Querying and Classification",
(http://elib.cs.berkeley.edu/papers/ -1997).
Smith, J.R. and Shih-Fu Chang. "Automated Image Retrieval Using Color and
Texture"( http://www.ctr.columbia.edu/~jrsmith/html/pubs/- 1995).
Smith, J.R. and Shih-Fu Chang. "Automated Binary Texture Feature Sets for Image
Retrieval" (http://www.ctr.columbia.edu/~jrsmith/html/pubs/- 1996).
Unser, M. Splines: A perfect fit for signal and image processing. IEEE Signal
Processing Magazine and IEEE Signal Processing Societys 2000 Magazine Award //
16(6):2238, November -1999.

][1
][2
][3
][4

][5

][6
][7
][8

20

[9]

[10]
[11]
[12]
[13]
[14]
[15]

2010 (1)

(15)


  

Ardizzone, E., La Cascia, M., Vito di Gesu,Valenti, C., "Content Based Indexing of
Image
and
Video
Databases
by
Global
and
Shape
Features
//http://www.cs.edu./associates/marco/publications.html -1996.
Sobel, I. "An isotropic image gradient operator. Machine Vision for Three-Dimensional
Scenes" // pp.376-379. Academic Press, 1990
Carson, C. and Ogle, V.E., "Storage and Retrieval of Feature Data for a Very Large
Online Image Collection" // http://elib.cs.berkeley.edu/papers/ - 1996.
Mohammed Abdulshakoor Ameen "Content-Based Image Search Engine", The 17the
national conference on Computer Science, King Abdul Aziz University,2004
Tou, J. T. and Gonzalez, R. C., Pattern Recognition Principles. Reading, MA: AddisonWesley, 1974.
Bezdek, J. C., Pattern Recognition with Fuzzy Objective Function Algorithms. New
York: Plenum, 1982.
James Ze Wang, Gio Wiederhold, Oscar Firschein and Sha Xin Wei, "Content-based
image indexing and searching using Daubechies' wavelets", Department of Computer
Science, Stanford University, Stanford, CA 94305, USA, US

You might also like