CS589-04 Digital Image Processing

Lecture 6. Color Image Processing

Spring 2008
New Mexico Tech
 Color Fundamentals

12/26/20 2
 Color Fundamentals

12/26/20 3
 Color Fundamentals

► 6 to 7 million cones in the human eye can be divided into

three principal sensing categories, corresponding roughly
to red, green, and blue.
65%: red 33%: green 2%: blue (blue cones are the
most sensitive)

12/26/20 4
 Color Fundamentals

12/26/20 5
12/26/20 6
 Color Fundamentals

► The characteristics generally used to distinguish one color

from another are brightness, hue, and saturation

brightness: the achromatic notion of intensity.

hue: dominant wavelength in a mixture of light waves,

represents dominant color as perceived by an observer.

saturation: relative purity or the amount of white light

mixed with its hue.

12/26/20 7
 Color Fundamentals

► Tristimulus
Red, green, and blue are denoted X, Y, and Z,
respectively. A color is defined by its trichromatic
coefficients, defined as
X
x
X Y  Z
Y
y
X Y  Z
Z
z
X Y  Z
12/26/20 8
 CIE Chromaticity Diagram

It shows color
composition
as a function
of x (red) and
y (green)

12/26/20 9
 RGB Color Model

12/26/20 10
 RGB Color Model

Pixel depth

The total number of

colors in a 24-bit RGB
image is (28)3 =
16,777,216

12/26/20 11
12/26/20 12
 Safe RGB colors (or
safe Web colors) are
reproduced faithfully,
reasonably
independently of
viewer hardware
capabilities
12/26/20 13
12/26/20 14
 The CMY and CMYK Color Models

 C  1  R 
 M   1  G 
    
 Y  1  B 
Equal amounts of the pigment primaries, cyan, magenta, and
yellow should produce black. In practice, combining these
colors for printing produces a muddy-looking black.

To produce true black, the predominant color in printing, the

fourth color, black, is added, giving rise to the CMYK color
model.
12/26/20 15
 CMY vs. CMYK

12/26/20 16

http://en.wikipedia.org/wiki/CMYK
 HIS Color Model

brightness: the achromatic notion of intensity.

hue: dominant wavelength in a mixture of light waves, represents dominant color

as perceived by an observer.

saturation: relative purity or the amount of white light mixed with its hue.

12/26/20 17
 HIS Color Model

12/26/20 18
 HIS Color Model

12/26/20 19
 HIS Color Model

12/26/20 20
 Converting Colors from RGB to HSI

► Given an image in RGB color format, the H component of

each RGB pixel is obtained using the equation

 if B  G
H 
360   if B>G

 1 
1 
 ( R  G )  ( R  B )  
  cos  2
1/2 
  R  G   ( R  B )(G  B )  
2

  

12/26/20 21
 Converting Colors from RGB to HSI

► Given an image in RGB color format, the saturation

component is given by

3
S  1  min( R, G, B)
( R  G  B)

12/26/20 22
 Converting Colors from RGB to HSI

► Given an image in RGB color format, the intensity

component is given by

1
I   R  G  B
3

12/26/20 23
 Converting Colors from HSI to RGB

► RG sector (0  H  120 )

B  I (1  S )
 S cos H 
R  I 1  
 cos(60  H ) 


and
G  3I  ( R  B )

12/26/20 24
 Converting Colors from HSI to RGB

► RG sector (120  H  240 )

H  H  120
R  I (1  S )
 S cos H 
G  I 1  
 cos(60 
 H ) 
and
B  3I  ( R  G )
12/26/20 25
 Converting Colors from HSI to RGB

► RG sector (240  H  360 )

H  H  240
G  I (1  S )
 S cos H 
B  I 1  
 cos(60 
 H ) 
and
R  3I  (G  B)
12/26/20 26
12/26/20 27
12/26/20 28
12/26/20 29
 Pseudocolor Image Processing

► The process of assigning colors to gray values based on a

specified criterion.

► Intensity Slicing

f ( x, y )  ck if f ( x, y ) Vk

12/26/20 30
12/26/20 31
12/26/20 32
12/26/20 33
12/26/20 34
12/26/20 35
 Pseudocolor Image Processing

► Intensity to Color Transformation

12/26/20 36
The images are obtained
from an airport X-ray
scanning system.
The left contains ordinary
articles and the right
contains the same articles
as well as a block of
simulated plastic explosives.

12/26/20 37
12/26/20 38
12/26/20 39
12/26/20 40
Pseudocolor by combining
several of the sensor
images from the Galileo
spacecraft, some of which
are in spectral regions not
visible to the eye.

Bright red depicts materials

newly ejected from an
active volcano on Io, and
the surrounding yellow
materials are older sulfur
deposits.

12/26/20 41
 Basics of Full-Color Image Processing

Let c represent an arbitrary vector in RGB color space:

 cR   R 
c  cG   G 
 cB   B 
At coordinates (x, y ),
 c R ( x , y )   R ( x, y ) 
c( x, y )  cG ( x, y)   G ( x, y) 
 cB ( x, y )   B ( x, y ) 

12/26/20 42
 Basics of Full-Color Image Processing

12/26/20 43
 Color Transformations

g ( x, y )  T  f ( x, y ) 

si  Ti (r1 , r2 ,..., rn ), i  1, 2,..., n.

12/26/20 44
12/26/20 45
 g ( x, y )  kf ( x, y )

si  kri , si  kri  (1  k ), s3  kr3

12/26/20 i  1, 2,3. i  1, 2,3. 46
12/26/20 47
12/26/20 48
 Color slicing

► Highlighting a specific range of colors in an image

If the colors of interest are enclosed by a cube of width W

and centered at a protypical color with components
(a1 , a2 ,..., an ), the necessary set of transformations is
0.5 if | rj  a j | W / 2 
si   any 1 j  n

 ri otherwise

12/26/20 49
 Color slicing

If a sphere is used to specify the colors of interest,

R 0 is the radius of the enclosing of its center.
The transformations is
 n

 j j  0
2
 0.5 if r  a  R 2

si   j 1
r otherwise
i

12/26/20 50
 Color slicing

12/26/20 51
 Tone and
Color
Corrections

12/26/20 52
12/26/20 53
12/26/20 54
 Color Image Smoothing

Let S xy denote the set of coordinates defining a neighborhood

centered at (x, y ) in an RGB color image. The average of the
RGB component vectors in this neighborhood is
1 
  R ( s, t ) 
 K ( s ,t )S xy 
1 1 
c ( x, y )  
K ( s ,t )S xy
c ( s, t )   
 K ( s ,t )S xy
G ( s, t ) 

 
1 
 K ( s ,
B ( s , t )

 t )S xy 
12/26/20 55
12/26/20 56
12/26/20 57
12/26/20 58
 Color Image Sharpening

The Laplacian of vector c is

  2 R ( x, y ) 
 2 
  c ( x, y )     G ( x, y ) 
2

  2 B ( x, y ) 
 

12/26/20 59
12/26/20 60
 Image
Segmentation
Based on Color:

Segmentation
in HIS Color
Space

12/26/20 61
 Segmentation in RGB Vector Space

Let the average color of interest is denoted by the

RGB vector a. Let z denote an arbitrary point in
RGB space.
1/2
D( z , a)  z  a  ( z  a ) ( z  a ) 
T

2 1/2
 ( z R  aR )  ( zG  aG )  ( zB  aB ) 
2 2

12/26/20 62
12/26/20 63
 Color Edge Detection (1)

Let r, g, and b be unit vectors along the R, G, and B

axis of RGB color space, and define vectors
R G B
u r g b
x x x
and
R G B
v r g b
y y y

12/26/20 64
 Color Edge Detection (2)

2 2 2
R G B
g xx  u u=  
x x x
2 2 2
R G B
g yy  vv=  
y y y
and
R R G G B B
g xy  u v=  
x y x y x y

12/26/20 65
 Color Edge Detection (3)

The direction of maximum rate of change of c(x, y ) is given by

the angle
1  2 g xy 
 ( x, y )  tan 
1

2  g xx  g yy 
The value of the rate of change at (x, y ) in the direction of  ( x, y ),
is given by
1/2
1  
F (x, y )=   g xx  g yy    g xx  g yy  cos 2 ( x, y )  2 g xy sin 2 ( x, y )  
2 

12/26/20 66
12/26/20 67
12/26/20 68