Overview

 Image restoration
 Image denoising
 Image deblurring
 Image enhancement
 Spatial domain
 Frequency domain
 Image interpolation
Theme: bad-looking images good-looking images

1
Image Denoising
 Introduction
 Impulse noise removal
 Median filtering
 Additive white Gaussian noise removal
 2D convolution and DFT
 Periodic noise removal
 Band-rejection and Notch filter

2
Introduction
 Where does noise come from?
 Sensor (e.g., thermal or electrical
interference)
 Environmental conditions (rain, snow etc.)
 Why do we want to denoise?
 Visually unpleasant
 Bad for compression
 Bad for analysis

3
Noisy Image Examples

thermal interference electrical interference

4
Noise Modeling
 Simplified assumptions
 Noise is independent of signal
 Noise types
 Independent of spatial location
 Impulse noise
 Additive white Gaussian noise
 Spatially dependent
 Periodic noise

5
Noise Removal Techniques
 Linear filtering
 Nonlinear filtering

Recall

Linear system

6
Image Denoising
 Introduction
 Impulse noise removal
 Median filtering
 Additive white Gaussian noise removal
 2D convolution and DFT
 Periodic noise removal
 Band-rejection and Notch filter

7
 Impulse Noise (salt-pepper
Noise)
Definition

Each pixel in an image has the probability of p/2 (0<p<1) being

contaminated by either a white dot (salt) or a black dot (pepper)

 255 with probability of p/2

 noisy pixels
Y (i, j )   0 with probability of p/2
 X (i, j ) with probability of 1-p clean pixels

1  i  H ,1  j  W X: noise-free image, Y: noisy image

Note: in some applications, noisy pixels are not simply black or white,
which makes the impulse noise removal problem more difficult

8
 Numerical Example
P=0.1

128 128 128 128 128 128 128 128 128 128 128 128 255 0 128 128 128 128 128 128
128 128 128 128 128 128 128 128 128 128 128 128 128 128 0 128 128 128 128 0
128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128
128 128 128 128 128 128 128 128 128 128 128 128 0 128 128 128 128 128 128 128
128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128
128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128
128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128
128 128 128 128 128 128 128 128 128 128 0 128 128 128 128 255 128 128 128 128
128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 255
128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 128 255 128 128

X Y

Noise level p=0.1 means that approximately 10% of pixels are contaminated by
salt or pepper noise (highlighted by red color)

9
 MATLAB Command
>Y = IMNOISE(X,'salt & pepper',p)

Notes:

 The intensity of input images is assumed to be normalized to [0,1].

If X is double, you need to do normalization first, i.e., X=X/255;
If X is uint8, MATLAB would do the normalization automatically
 The default value of p is 0.05 (i.e., 5 percent of pixels are contaminated)
 imnoise function can produce other types of noise as well (you need to
change the noise type ‘salt & pepper’)

10
Impulse Noise Removal Problem

filtering denoised ^
X
algorithm image

^
Can we make the denoised image X as close
Noisy image Y
to the noise-free image X as possible?

11
Median Operator
 Given a sequence of numbers {y1,…,yN}
 Mean: average of N numbers
 Min: minimum of N numbers
 Max: maximum of N numbers
 Median: half-way of N numbers

Example y  [50,0,52,255,54,55,56]

sorted  [0,50,52,54,55,56,255]
y

median( y )  54

12
 1D Median Filtering
y(n)

… …

W=2T+1

xˆ (n)  median[ y (n  T ),..., y (n),..., y (n  T )]

MATLAB command: x=median(y(n-T:n+T));

Note: median operator is nonlinear

13
 Numerical Example
T=1: 
y  [50,0,52,255,54,55,56]


Boundary y  [50,50,0,52,255,54,55,56,56]
Padding

ˆ
x  [50,50,52,54,54,55,55]

14
 2D Median Filtering

x(m,n)

W: (2T+1)-by-(2T+1) window
xˆ (m, n)  median[ y (m  T , n  T ),..., y (m  T , n  T ),...,
y (m, n),..., y (m  T , n  T ),..., y (m  T , n  T )]
MATLAB command: x=medfilt2(y,[2*T+1,2*T+1]);

15
 Numerical Example
225 225 225 226 226 226 226 226 0 225 225 226 226 226 226 226
225 225 255 226 226 226 225 226 225 225 226 226 226 226 226 226
226 226 225 226 0 226 226 255 225 226 226 226 226 226 226 226
255 226 225 0 226 226 226 226 226 226 225 225 226 226 226 226
225 255 0 225 226 226 226 255 225 225 225 225 226 226 226 226
255 225 224 226 226 0 225 226 225 225 225 226 226 226 226 226
226 225 225 226 255 226 226 228 225 225 225 226 226 226 226 226
226 226 225 226 226 226 226 226 226 226 226 226 226 226 226 226

^
Y X

Sorted: [0, 0, 0, 225, 225, 225, 226, 226, 226]

16
Image Example
P=0.1

denoised ^
Noisy image Y X
image
3-by-3 window
17
 Image Example (Con’t)

noisy
clean
(p=0.2)

3-by-3 window 5-by-5 window

18
Reflections
 What is good about median operation?
 Since we know impulse noise appears as
black (minimum) or white (maximum) dots,
taking median effectively suppresses the
noise
 What is bad about median operation?
 It affects clean pixels as well
 Noticeable edge blurring after median
filtering
19
Idea of Improving Median Filtering
 Can we get rid of impulse noise without
affecting clean pixels?
 Yes, if we know where the clean pixels are
or equivalently where the noisy pixels are
 How to detect noisy pixels?
 They are black or white dots

20
Median Filtering with Noise Detection
Noisy image Y

Median filtering
x=medfilt2(y,[2*T+1,2*T+1]);

Noise detection
C=(y==0)|(y==255);

Obtain filtering results

xx=c.*x+(1-c).*y;

21
 Image Example

noisy
clean
(p=0.2)

w/o with
noise noise
detection detection

22