Information Technology Reference
In-Depth Information
in the range [0; 100], u component in the range [
−
134; 220], and v component in the
range [
128; 127].
The YC
r
C
b
color model is the basic color model used in digital video applications
[26]. The luminance component Y can be computed as a weighted average of Red,
Green and Blue components. The color difference, or chrominance, components
(C
r
,C
b
) are formed by subtracting luminance from Blue and Red. The equations for
converting an RGB image to YC
r
C
b
color space are given by:
−
140; 122]. The a and b component values are in the range [
−
Y
= 0
.
299
R
+ 0
.
587
G
+ 0
.
114
B
,
C
r
= 0
.
564 (
B
−
Y
)
,
(15)
C
b
= 0
.
713(
R
−
Y
)
.
The details information in a digital image are mainly present in the image luminance
component. Therefore, one can take advantage of the high sensibility of the human
visual system to the luminance variation than to the chrominance variation, to rep-
resent the C
r
and C
b
components with a lower resolution than Y. This reduces the
amount of data required to represent the chrominance information without having
an obvious effect on visual quality.
3.1.3
The Perceptual HSV System
The HSV (hue, saturation, value) color system, introduced by Smith [27], models
the human perceptual properties of hue, saturation, and value. It was developed to
be more intuitive in manipulating color and was designed to approximate the way
humans perceive and interpret color. Hue defines the basic color and is specified
by an angle in degrees between 0 and 360. Saturation is the intensity of the color.
Its values run from 0, which means no color saturation, to 1, which is the fullest
saturation of a given hue at a given illumination. Value is the brightness of the color.
It varies with color saturation and ranges from 0 to 1. The transformation from RGB
to HSV is accomplished through the following equations [5]:
⎧
⎨
⎩
π
,
if
R
=
G
=
B
1
2
((
R
B
))
√
(
R
−
G
)
2
+(
R
−
B
)(
G
−
B
)
,
−
G
)+(
R
−
arccos
if
B
≤
G
H
=
(16)
1
2
((
R
B
))
√
(
R
−
G
)
2
+(
R
−
B
)(
G
−
B
)
,
−
G
)+(
R
−
2
π
−
arccos
otherwise,
S
=
0
,
if
R
=
G
=
B
(17)
3min(
R
,
G
,
B
)
R
+
G
+
B
1
−
,
otherwise,
V
=
R
+
G
+
B
3
.
(18)
3.1.4
The Statistical Independent Component Systems
In primary systems, the three components are highly correlated because they have
in common the luminance information. To overcome this limitation, statistical
