lecture # 09 color processing &...
TRANSCRIPT
![Page 1: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/1.jpg)
1
Digital Image Processing
Lecture # 09Color Processing & Clustering
![Page 2: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/2.jpg)
COLOR IMAGE PROCESSING
![Page 3: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/3.jpg)
3
COLOR IMAGE PROCESSING
• Color Importance
– Color is an excellent descriptor
• Suitable for object Identification and Extraction
– Discrimination
• Humans can distinguish thousands of color shades and intensities but few shades of gray levels
• Color Image Processing
– Full-Color Processing
• Color is acquired with a full-color sensor
– Pseudo-Color Processing
• Assigning colors to monochrome images
![Page 4: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/4.jpg)
4
COLOR FUNDAMENTALS
• Colors that humans perceive in an object are determined by the nature of the light reflected from the object
• Visible light is composed of a relatively narrow band of frequencies in the electromagnetic spectrum
• A body that reflects light that is balanced in all visible wavelengths appears white to the observer
• A body that favours reflectance in a limited range of the visible spectrum exhibits some shades of color
• Green objects reflect light with wavelengths primarily in the 500 to 570 nm range while absorbing most of the energy at other wavelengths
![Page 5: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/5.jpg)
5
HUMAN PERSCEPTION OF COLOR
• Retina contains receptors– Cones
• Day vision, can perceive color tone
• Red, green, and blue cones
– Rods• Night vision, perceive brightness only
• Color sensation– Luminance (brightness)
– Chrominance• Hue (color tone)
• Saturation (color purity)
![Page 6: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/6.jpg)
Monochromatic images• Image processing - static images -
• Monochromatic static image - continuous image function f(x,y) – arguments - two co-ordinates (x,y)
• Digital image functions - represented by matrices– co-ordinates = integer numbers
– Cartesian (horizontal x axis, vertical y axis)
– OR (row, column) matrices
• Monochromatic image function range– lowest value - black
– highest value - white
• Limited brightness values = gray levels
![Page 7: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/7.jpg)
Chromatic images• Colour
– Represented by vector not scalar
• Red, Green, Blue (RGB)
• Hue, Saturation, Value (HSV)
• luminance, chrominance (Yuv , Luv)
![Page 8: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/8.jpg)
8
PRIMARY AND SECONDARY COLORS OF LIGHT AND PIGMENTS
• The primary colors can be added to produce the secondary colors of light
• The primary colors of light and primary colors of pigments are different
• For pigments, a primary color is defined as one that absorbs a primary color of light and reflects the other two
• Therefore, the primary colors of pigments are magenta, cyan, and yellow
![Page 9: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/9.jpg)
9
COLOR MODELS
• Color Model – Specify colors in a standard way
– A coordinate system that each color is represented by a single point.
• Most used models:– RGB model (Monitor/TV)
– CMY model (3-color Printers)
– HSI model (Color Image Processing and Description)
![Page 10: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/10.jpg)
RGB Color model
10
Active displays, such as computer monitors and television sets, emit
combinations of red, green and blue light. This is an additive color model
Source: www.mitsubishi.com
![Page 11: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/11.jpg)
CMY Color model
11
Passive displays, such as color inkjet printers, absorb light instead of
emitting it. Combinations of cyan, magenta and yellow inks are used. This
is a subtractive color model.
Source: www.hp.com
![Page 12: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/12.jpg)
RGB vs CMY
![Page 13: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/13.jpg)
13
RGB COLOR MODEL
• 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)
– Number of colors:
216,777,16238
![Page 14: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/14.jpg)
![Page 15: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/15.jpg)
15
COLOR IMAGE - RGB
Color Image
G-Channel
![Page 16: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/16.jpg)
CMY Model
– Color Printer, Color Copier
– RGB data to CMY
B
G
R
Y
M
C
1
1
1
![Page 17: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/17.jpg)
17
HSI COLOR MODEL• Human description of color is Hue, Saturation and Brightness:
• Hue– represents dominant color as perceived by an observer. It is an attribute
associated with the dominant wavelength.
• Saturation– refers to the relative purity or the amount of white light mixed with a
hue. The pure spectrum colors are fully saturated. • Pure colors are fully saturated.
• Pink is less saturated.
• Intensity– reflects the brightness.
![Page 18: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/18.jpg)
HSI Color Model
• The intensity component of any color
can be determined by passing a plane
perpendicular to the intensity axis and
containing the color point
• The intersection of the plane
with the intensity axis gives us the
intensity component of the color
![Page 19: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/19.jpg)
HSI Color Model
Intensity
Saturation
Hue
![Page 20: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/20.jpg)
20
HSI COLOR MODEL- SINGLE HUE
![Page 21: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/21.jpg)
HSI Color Model
• Hue is defined as an angle
– 0 degrees is RED
– 120 degrees is GREEN
– 240 degrees is BLUE
• Saturation is defined as the percentage of distance from the center of the HSI triangle to the pyramid surface.
– Values range from 0 to 1.
• Intensity is denoted as the distance “up” the axis from black.
– Values range from 0 to 1
21
![Page 22: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/22.jpg)
HSI Color Model
Because the only important things are the angle and the length of the saturation
vector this plane is also often represented as a circle or a triangle
![Page 23: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/23.jpg)
HSI Color Model
![Page 24: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/24.jpg)
HSI Color Model
![Page 25: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/25.jpg)
Converting from RGB to HSI
H if B G
360 if B G
cos1
12R G R B
R G 2 R B G B
12
S 13
RG B min R,G,B
I 13R G B
![Page 26: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/26.jpg)
Conversion Between RGB and HSI
![Page 27: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/27.jpg)
![Page 28: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/28.jpg)
28
COLOR IMAGE - HSI
![Page 29: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/29.jpg)
Manipulating Images In The HSI Model
• In order to manipulate an image under the HSI
model we:
– First convert it from RGB to HSI
– Perform our manipulations under HSI
– Finally convert the image back from HSI to RGB
RGB
ImageHSI Image
RGB
Image
Manipulations
![Page 30: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/30.jpg)
Pseudocolor Image Processing
• Pseudocolor (also called false color) image processing consists of assigning colors to grey values based on a specific criterion
• The principle use of pseudocolor image processing is for human visualization
![Page 31: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/31.jpg)
Pseudo Color Image Processing –Intensity Slicing
• Intensity slicing and color coding is one of the simplest kinds of
pseudocolor image processing
• First we consider an image as a 3D function mapping spatial
coordinates to intensities (that we can consider heights)
• Now consider placing planes at certain levels parallel to the
coordinate plane
• If a value is one side of such a plane it is rendered in one color, and
a different color if on the other side
![Page 32: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/32.jpg)
Pseudo Color Image Processing –Intensity Slicing
![Page 33: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/33.jpg)
Pseudo Color Image Processing –Intensity Slicing
• In general intensity slicing can be summarized as:
– Let [0, L-1] represent the grey scale
– Let l0 represent black [f(x, y) = 0] and let lL-1 represent white [f(x, y) = L-1]
– Suppose P planes perpendicular to the intensity axis are defined at levels l1, l2, …, lp
– Assuming that 0 < P < L-1 then the P planes partition the grey scale into P + 1 intervals V1, V2,…,VP+1
![Page 34: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/34.jpg)
Pseudo Color Image Processing –Intensity Slicing
– Grey level color assignments can then be made according to the relation:
– where ck is the color associated with the kth intensity level Vk defined by the partitioning planes at l = k – 1
and l = k
f (x,y) ck if f (x,y)Vk
![Page 35: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/35.jpg)
Intensity slicing (cont.)
• More slicing plane, more colors
![Page 36: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/36.jpg)
Pseudo Color Image Processing –Intensity Slicing
8 color regionsRadiation test pattern
![Page 37: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/37.jpg)
Pseudo Color Image Processing –Intensity Slicing
![Page 38: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/38.jpg)
Gray level to color transformation
![Page 39: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/39.jpg)
Color pixel
• A pixel at (x,y) is a vector in the color space
– RGB color space
),(
),(
),(
),(
yxB
yxG
yxR
yxc
c.f. gray-scale image
f(x,y) = I(x,y)
![Page 40: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/40.jpg)
Example: spatial mask
![Page 41: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/41.jpg)
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
![Page 42: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/42.jpg)
Two spatial processing categories
• Similar to gray scale processing studied before, we have to major categories
• Pixel-wise processing
• Neighborhood processing
![Page 43: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/43.jpg)
43
COLOR IMAGE - SMOOTHING• Smoothing can be viewed as a
spatial filtering operation in which the coefficients of the filtering mask are all 1’s
• This concept can be easily extended to the processing of full-color images
• Simply smooth each of the RGB color planes and then combine the processed planes to form a smoothed full-color result
![Page 44: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/44.jpg)
original R
G G
H S I
![Page 45: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/45.jpg)
Example: 5x5 smoothing mask
RGB model
Smooth I
in HSI model difference
![Page 46: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/46.jpg)
Color Image Sharpening
2
2 2
2
The Laplacian of vector c is
( , )
( , ) ( , )
( , )
R x y
c x y G x y
B x y
![Page 47: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/47.jpg)
![Page 48: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/48.jpg)
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
u r g b
and
v r g b
R G B
x x x
R G B
y y y
![Page 49: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/49.jpg)
Color Edge Detection (2)
2 2 2
2 2 2
u u=
v v=
and
u v=
xx
yy
xy
R G Bg
x x x
R G Bg
y y y
R R G G B Bg
x y x y x y
![Page 50: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/50.jpg)
![Page 51: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/51.jpg)
Cluster Analysis
![Page 52: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/52.jpg)
The goals of segmentation• Separate image into coherent “objects”
Berkeley segmentation database:http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/segbench/
image human segmentation
![Page 53: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/53.jpg)
The goals of segmentation• Separate image into coherent “objects”
– Top-down or bottom-up process?
– Supervised or unsupervised?
• Group together similar-looking pixels for efficiency of further processing
X. Ren and J. Malik. Learning a classification model for segmentation. ICCV 2003.
“superpixels”
![Page 54: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/54.jpg)
Segmentation as clustering
Source: K. Grauman
![Page 55: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/55.jpg)
Segmentation as clustering
Source: K. Grauman
![Page 56: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/56.jpg)
12/12/2019 Image Segmentation 56
K-Means Clustering1. Chose the number (K) of clusters and randomly select the
centroids of each cluster.
2. For each data point:
Calculate the distance from the data point to each cluster.
Assign the data point to the closest cluster.
3. Recompute the centroid of each cluster.
4. Repeat steps 2 and 3 until there is no further change in
the assignment of data points (or in the centroids).
![Page 57: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/57.jpg)
12/12/2019 Image Segmentation 57
K-Means Clustering
![Page 58: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/58.jpg)
12/12/2019 Image Segmentation 58
K-Means Clustering
![Page 59: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/59.jpg)
12/12/2019 Image Segmentation 59
K-Means Clustering
![Page 60: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/60.jpg)
12/12/2019 Image Segmentation 60
K-Means Clustering
![Page 61: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/61.jpg)
12/12/2019 Image Segmentation 61
K-Means Clustering
![Page 62: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/62.jpg)
12/12/2019 Image Segmentation 62
K-Means Clustering
![Page 63: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/63.jpg)
12/12/2019 Image Segmentation 63
K-Means Clustering
![Page 64: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/64.jpg)
12/12/2019 Image Segmentation 64
K-Means Clustering
![Page 65: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/65.jpg)
12/12/2019 Image Segmentation 65
K-Means Clustering
![Page 66: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/66.jpg)
12/12/2019 Image Segmentation 66
Clustering Example
![Page 67: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/67.jpg)
12/12/2019 Image Segmentation 67
Clustering Example
![Page 68: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/68.jpg)
12/12/2019 Image Segmentation 68
Clustering Example
![Page 69: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/69.jpg)
12/12/2019 Image Segmentation 69
Clustering Example
![Page 70: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/70.jpg)
12/12/2019 Image Segmentation 70
Clustering Example
D. Comaniciu and P.
Meer, Robust Analysis
of Feature Spaces:
Color Image
Segmentation, 1997.
![Page 71: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/71.jpg)
12/12/2019 Image Segmentation 71
K-Means Clustering Example
Original K=5 K=11
![Page 72: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/72.jpg)
Readings from Book (3rd Edn.)
• Color Processing Chapter-6
![Page 73: Lecture # 09 Color Processing & Clusteringbiomisa.org/wp-content/uploads/2019/10/Lect-9.pdfClustering Example D. Comaniciu and P. Meer, Robust Analysis of Feature Spaces: Color Image](https://reader034.vdocuments.mx/reader034/viewer/2022042709/5f4fcb5e26977e2ec6656eb9/html5/thumbnails/73.jpg)
73
Acknowledgements
Digital Image Processing”, Rafael C. Gonzalez & Richard E. Woods, Addison-Wesley, 2002
Computer Vision: Algorithms and Applications Richard Szeliski
Mat
eria
l in
th
ese
slid
es h
as b
een
tak
en f
rom
, th
e fo
llow
ing
reso
urc
es