Professional Documents
Culture Documents
part-2Final-Chapter 3 - Intensity Transformations and Spatial Filtering-Updates
part-2Final-Chapter 3 - Intensity Transformations and Spatial Filtering-Updates
4/28/2019
2 Histogram Processing
3.1- Background
3.8- Using Fuzzy Techniques for Using Histogram Statistics for Image Enhancement
Intensity Transformations and
Spatial Filtering
4/28/2019
Histogram Processing
3 (What is Histogram?)
A histogram is an accurate representation of the distribution of
numerical data. It is an estimate of the probability distribution
of a continuous variable (quantitative variable)
3.1- Background
3.1- Background
3.1- Background
3.1- Background
Transformation Functions 4
3.5
2.5
2
3.4- Fundamentals of Spatial
1.5
Filtering
1
0.5
3.5 - Smoothing Spatial Filters 0
3.1- Background
5000
3.4- Fundamentals of Spatial
4000
Filtering
3000
1000
Histogram equalization:
s T (r ), 0 r 1
r T 1 ( s), 0 s 1
4/28/2019
19
Histogram Equalization
3.1- Background
( L 1) pr ( w)dw ( L 1) pr (r )
3.5 - Smoothing Spatial Filters ds dT (r ) d r
3.6- Sharpening Spatial Filters dr dr dr 0
3.1- Background
Where rk is the kth gray level and nk is the number of pixels in the
image having gray level rk
Normalized histogram: P(rk)=nk/n
Histogram of an image represents the relative frequency of occurrence of
various gray levels in the image where n is the total size of image=M*N=64*64
K=0,1,2….7 (gray level image, intensity=2^3= 8, histogram values for 3 bit)
4/28/2019
24 Histogram Equalization
3.1- Background
3.1- Background
4/28/2019
Histogram Equalization
27
4/28/2019
Histogram Equalization
28
Histogram
Cumulative
Normalized Histogram
4/28/2019
29 Histogram Equalization
transformed intensity
gk = (L-1) * T(k).
To encompass the
whole dynamic range.
4/28/2019
Histogram Equalization
30
4/28/2019
Histogram Equalization
31
3.1- Background
4/28/2019
33 Histogram Equalization
4/28/2019
Histogram Processing
34
3.1- Background
3.8- Using Fuzzy Techniques for Using Histogram Statistics for Image Enhancement
Intensity Transformations and
Spatial Filtering
4/28/2019
Adaptive
35
Contrast Enhancement (ACE)
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.8- Using Fuzzy Techniques for Using Histogram Statistics for Image Enhancement
Intensity Transformations and
Spatial Filtering
4/28/2019
40
Histogram Matching (Specification)
Histogram equalization produces a transformation function that is adaptive in
the sense that it is based on the histogram of a given image.
Histogram equalization has a disadvantage which is that it can generate only one type
of output image.
With Histogram Specification, we can specify the shape of the histogram that we wish
the output image to have.
4/28/2019
Histogram Matching (Specification)
41
3.1- Background
3.4- Fundamentals of Spatial Let the initial image histogram be pr, the desired image
Filtering histogram be pz.
3.5 - Smoothing Spatial Filters
Let T be the function that equalizes the original image and
3.6- Sharpening Spatial Filters G be the function that equalizes the desired image.
– r: The initial image intensity.
3.7- Combining Spatial – s: The image intensity after equalization
Enhancement Tools
– z: The image intensity of the desired image.
3.8- Using Fuzzy Techniques for – v: The image intensity after equalization of the
Intensity Transformations and desired image.
Spatial Filtering
4/28/2019
42
Histogram Matching (Specification)
3.1- Background
r
3,3- Histogram Processing
s T (r ) ( L 1) pr ( w)dw
0
3.4- Fundamentals of Spatial
Filtering
z
3.5 - Smoothing Spatial Filters G( z ) ( L 1) pz (t )dt s
0
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
Image is dominated by large, dark areas, resulting in a
3.2- Some Basic Intensity
Transformation Functions histogram characterized by a large concentration of pixels
in pixels in the dark end of the gray scale
3,3- Histogram Processing
3.1- Background
3.1- Background
3.1- Background
3.8- Using Fuzzy Techniques for Using Histogram Statistics for Image Enhancement
Intensity Transformations and
Spatial Filtering
4/28/2019
Local Histogram Processing
53
3.1- Background
3.1- Background
Local enhancement:
Histogram using a local neighborhood, for example 7*7
3.2- Some Basic Intensity neighborhood
Transformation Functions
3.1- Background
3.6- Sharpening Spatial Filters However, the small squares were too close in gray level to
the larger ones, and their sizes were too small to influence
global histogram equalization significantly.
3.7- Combining Spatial
Enhancement Tools
So, when we use the local enhancement technique, it reveals
the small areas.
3.8- Using Fuzzy Techniques for
Intensity Transformations and
Spatial Filtering Note also the finer noise texture is resulted by the local
processing using relatively small neighborhoods. 4/28/2019
Local Histogram Processing
56
3.1- Background
3.1- Background
3.8- Using Fuzzy Techniques for Using Histogram Statistics for Image Enhancement
Intensity Transformations and
Spatial Filtering
4/28/2019
58 Using Histogram Statistics
3.1- Background
3.2- Some Basic Intensity Use of histogram statistics for image enhancement:
Transformation Functions r denotes a discrete random variable
3,3- Histogram Processing P(ri) denotes the normalized histogram component
corresponding to the ith value of r
3.4- Fundamentals of Spatial
L 1
m ri p (ri )
Filtering
Mean:
3.5 - Smoothing Spatial Filters i 0
L 1
3.6- Sharpening Spatial Filters
The nth moment: n (r ) (ri m) n p (ri )
i 0
3.7- Combining Spatial
Enhancement Tools
L 1
3.8- Using Fuzzy Techniques for The second moment: 2 (r ) (ri m) 2 p (ri )
Intensity Transformations and i 0
Spatial Filtering
4/28/2019
59 Using Histogram Statistics
3.1- Background
3,3- Histogram Processing Global enhancement: The global mean and variance are
measured over an entire image
3.4- Fundamentals of Spatial
Filtering
Local enhancement: The local mean and variance are used
3.5 - Smoothing Spatial Filters as the basis for making changes
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
4/28/2019
66 Fundamentals of Spatial
Filtering
3.1- Background
3.1- Background
3.1- Background
3.1- Background
Vector Representation of Linear Filtering:
3.2- Some Basic Intensity
Transformation Functions
4/28/2019
77 Smoothing Spatial Filters
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
4/28/2019
86
Sharpening Spatial Filters
3.1- Background
3.1- Background
2 f
3.7- Combining Spatial
f ( x 1) f ( x 1) 2 f ( x)
Enhancement Tools
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.2- Some Basic Intensity Use of second derivatives for enhancement-The Laplacian:
Transformation Functions
Development of the method
3,3- Histogram Processing
2 f 2 f
3.4- Fundamentals of Spatial f 2 2
2
Filtering
x y
3.5 - Smoothing Spatial Filters
2 f
3.6- Sharpening Spatial Filters
f ( x 1, y ) f ( x 1, y ) 2 f ( x, y )
3.7- Combining Spatial
x 2
Enhancement Tools
3.1- Background
is negative
3.6- Sharpening Spatial Filters
g ( x, y )
if the center coefficien t
3.7- Combining Spatial
Enhancement Tools f ( x, y ) 2 f ( x, y ) of the Laplacian mask
3.8- Using Fuzzy Techniques for is positive
Intensity Transformations and
Spatial Filtering
4/28/2019
93 Laplacian
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.1- Background
3.5 - Smoothing Spatial Filters f(x,y) : The image, f̄(x,y): The blurred image
3.1- Background
3.2- Some Basic Intensity Using first-order derivatives for (nonlinear) image
Transformation Functions sharpening, The gradient:
The gradient:
3,3- Histogram Processing
f
g x x
3.4- Fundamentals of Spatial f f
Filtering g y
y
3.5 - Smoothing Spatial Filters
The magnitude is rotation invariant (isotropic)
3.6- Sharpening Spatial Filters
1
f 2 f 2 2
M ( x, y ) g x g y
3.8- Using Fuzzy Techniques for
Intensity Transformations and x y
Spatial Filtering
4/28/2019
Using First-Order Derivative for
103
(Nonlinear) Image Sharpening - The
Gradient
3.1- Background
3.1- Background
3.1- Background
3.1- Background
4/28/2019
108 Combining Spatial
Enhancement Tools
3.1- Background