Color Image Processing

Preview
 Why use color in image processing?
 Color is a powerful descriptor


Object identification and extraction

eg. Face detection using skin colors
 Humans can discern thousands of color shades

and intensities

Human discern only two dozen shades of
grays
 Preview (cont.)
 Two category of color image
processing
 Full color processing

Images are acquired from full-color sensor or
equipments
 Pseudo-color processing

In the past decade, color sensors and
processing hardware are not available

Colors are assigned to a range of monochrome
intensities
 Outline
 Color fundamentals
 Color models
 Basics of full-color image
processing
 Noise in color images
 Color image compression
 Color fundamentals
 Physical phenomenon
 Physical nature of color is known

 Psysio-psychological phenomenon
 How human brain perceive and interpret
color?
 Color fundamentals (cont.)
 1666, Isaac Newton
 Visible light
 Chromatic light span the
electromagnetic spectrum (EM) from
400 to 700 nm
 Color fundamentals (cont.)
 The color that human perceive in an
object = the light reflected from the
object

scene
Illumination source

reflection
eye
 describe a chromatic light
source
 Radiance: total amount of energy that flow from the
light source, measured in watts (W)
 Luminance: amount of energy an observer perceives
from a light source, measured in lumens (lm)
 infrared light: high radiance, but 0 luminance
 Brightness: subjective descriptor that is hard to
measure, similar to the achromatic notion of intensity
 How human eyes sense
light?
 3 principal sensing categories in
eyes
 Red light 65%, green light 33%, and
blue light 2%
 Primary and secondary
colors
In 1931, International Commission on
Illumination defines
 specific wavelength values to the primary
colors
 B = 435.8 nm, G = 546.1 nm, R = 700 nm
 However, we know that no single color may
be called red, green, or blue
 Secondary colors:
G+B=Cyan, R+G=Yellow, R+B=Magenta
 Primary colors of light v.s.
primary colors of pigments
 Primary color of pigments
 Color that subtracts or absorbs a primary
color of light and reflects or transmits the
other two
Color of light: R G B

Color of pigments: absorb R absorb G absorb B

Cyan Magenta Yellow
 Application of additive
nature of light colors
 Color TV
 CIE XYZ model
 RGB -> CIE XYZ model
 X   0.431 0.342 0.178  R 
 Y   0.222 0.707 0.071  G 
    
 Z   0.020 0.130 0.939  B 
 Normalized tristimulus values
X Y Z
x y z
X Y  Z X Y  Z X Y  Z

=> x+y+z=1. Thus, x, y (chromaticity coordinate) is

enough to describe all colors
By additivity of colors:
Any color inside the
triangle can be produce
by combinations of the
three initial colors

RGB gamut of
monitors
Color gamut of
printers
 Outline
 Color fundamentals
 Color models
 Basics of full-color image
processing
 Color transformations
 Smoothing and sharpening
 Color models
 Color model / color space / color system
 Specify colors in a standard way
 A coordinate system that each color is
represented by a single point

 RGB model Suitable for hardware

 CYM model (printers/ monitors / cameras)
 CYMK model or
Applications (graphics / animations)
 HSI model

- match
CYMK - Cyan, Yellow, Magenta, the human
Black description
 HIS  Hue , Saturation, Intensity
RGB color model
 Pixel depth
 Pixel depth: the number of bits used
to represent each pixel in RGB space
 Full-color image: 24-bit RGB color
image
 (R, G, B) = (8 bits, 8 bits, 8 bits)
 Total no of colos = (2 pow 8 pow 3)
 Safe RGB colors
 Subset of colors is enough for some
applications
 Safe RGB colors (safe Web colors, safe
browser colors)

(6)3 = 216
 Safe RGB color (cont.)

Full color cube Safe color cube

000000  black
FFFFFF  White
 CMY model (+Black =
CMYK)
 CMY: secondary colors of light /
primary colors of pigments
 Used to generate hardcopy output

 C  1  R
 M  1   G
     
 Y  1  B 
 HSI color model
 Will you describe a color using its R, G,
B components?
 Human describe a color by its hue,
saturation, and brightness
 Hue : color attribute
 Saturation: purity of color (white->0,
primary color->1)
 Brightness: achromatic notion of intensity
 HSI color model (cont.)
 RGB -> HSI model Relation
Colors on this triangle
Have the same hue
Intensity
line
saturation
HSI model: hue and
saturation
HSI model
 Convert colors from RGB – HSI

I/P : Image RGB color Format

Hue (H) = Theta (an angle)  if B<=G
360 – Theta  if B>G

Theta = cos -1
{ ½ [(R-G) + (R-B)] /
[(R-G)2 + (R-B)(G-B)]2}

Saturation (S) = 1- [3/(R+G+B)*[min()R,G,B]]

Intensity (I) = 1/3 (R+G+B)

Convert HIS  RGB

RG Sector – (0 <=H <120 degrees)

B=I(1-S)
R=I[1+((S cos H) / cos (60deg – H))]
G = 3I – (R+B)

GB Sector – (120 <=H <240 degrees)

H = H-120 deg

R=I(1-S)
G=I[1+((S cos H) / cos (60deg – H))]
B = 3I – (R+B)

BR Sector – (240 <=H <360 degrees)

H = H-240 deg

G=I(1-S)
B=I[1+((S cos H) / cos (60deg – H))]
R= 3I – (R+B)
 Manipulating
HSI component images

R,G,B Hue

intensity
saturation
 Outline
 Color fundamentals
 Color models
 Pseudo-color image processing
 Basics of full-color image
processing
 Color transformations
 Smoothing and sharpening
 Pseudo-color image
processing

 Assign colors to gray values based on

a specified criterion
 For human visualization and
interpretation of gray-scale events
 Intensity slicing
 Gray level to color transformations
 Intensity slicing
 3-D view of intensity image

Color 1

Color 2

Image plane
 Intensity slicing (cont.)
 Alternative representation of intensity
slicing
 Intensity slicing (cont.)
 More slicing plane, more colors
 Application 1

Radiation test pattern 8 color regions

* See the gradual gray-level changes
 Application 2

X-ray image of a weld

焊接物
Application 3

Rainfall statistics
 Gray level to color
transformation
 Intensity slicing: piecewise linear
transformation

 General Gray level to color

transformation
Gray level to color
transformation
Application 1
 Combine several
monochrome images
Example: multi-spectral images
Washington D.C.

R G

Near
Infrared
B (sensitive
to biomass)

R+G+B near-infrared+G+B
 Outline
 Color fundamentals
 Color models
 Pseudo-color image processing
 Basics of full-color image
processing
 Color transformations
 Smoothing and sharpening
 Color pixel
 A pixel at (x,y) is a vector in the color
space
 RGB color space
 R ( x, y ) 
c( x, y )  G ( x, y )
 B ( x, y ) 

c.f. gray-scale image

f(x,y) = I(x,y)
Example: spatial mask
 How to deal with color
vector?
 Per-color-component processing
 Process each color component

 Vector-based processing
 Process the color vector of each pixel

 When can the above methods be equivalent?

 Process can be applied to both scalars and

vectors
 Operation on each component of a vector

must be independent of the other

component
 Two spatial processing
categories
 Similar to gray scale processing
studied before, we have to major
categories
 Pixel-wise processing
 Neighborhood processing
Outline
 Color fundamentals
 Color models
 Pseudo-color image processing
 Basics of full-color image
processing
 Color transformations
 Smoothing and sharpening
 Color transformation
 Similar to gray scale transformation
 g(x,y)=T[f(x,y)]
 Color transformation
si Ti (r1 , r2 ,..., rn ) , i 1,2,..., n
g(x,y) f(x,y)
s1 T1 f1
s2 T2 f2
… … …
sn Tn fn
 Use which color model in
color transformation?
 RGB CMY(K)  HSI
 Theoretically, any transformation can
be performed in any color model
 Practically, some operations are better
suited to specific color model
 Example: modify intensity
of a color image
 Example: g(x,y)=k f(x,y), 0<k<1
 HSI color space

Intensity: s3 = k r3
 Note: transform to HSI requires

complex operations
 RGB color space

For each R,G,B component: si = k ri
 CMY color space
 For each C,M,Y component:


si = k ri +(1-k)
I H,S
Problem of using Hue
component

dis-continuous

Un-defined
over gray
axis
 Implementation of color
slicing
 Recall the pseudo-color intensity slicing

1-D intensity
 Implementation of color
slicing
 How to take a region of colors of
interest?

prototype color prototype color

Sphere region Cube region

Application

cube sphere
 Outline
 Color fundamentals
 Color models
 Pseudo-color image processing
 Basics of full-color image
processing
 Color transformations
 Smoothing and sharpening
 Color image smoothing
 Neighborhood processing
Color image smoothing:
averaging mask

1
c( x, y ) 
K
 c( x, y )
( x , y )S xy
vector processing

Neighborhood
Centered at (x,y)
1 
  R ( x, y ) 
 K ( x , y )S xy 
1 
c ( x , y )   G ( x, y ) 
per-component processing
 K ( x , y )S xy 
1 
 K  B ( x, y ) 
 ( x , y )S xy 
original R

G G
 Example: 5x5 smoothing
mask
Smooth I
RGB model in HSI model difference