EC 703:
IMAGE PROCESSING AND
COMPUTER VISION
By:
1
Rahul K Patel
ECE Department
I.I.I.T, Surat
IMAGE RESTORATION
ENHANCEMENT V/S. RESTORATION
Image Enhancement:
A process which aims to improve bad
Images so they will “look” better.
Image Restoration
Restoration attempts to recover an image that has
been degraded by using a priori knowledge of
the degradation phenomenon. Thus, estoration
techniques are oriented toward modeling the
degradation and applying the inverse process in
order to recover the original image.
MODEL OF IMAGE DEGRADATION AND
RESTORATION
The purpose of image restoration is to restore a
degraded/distorted image to its original content and quality.
Distinctions to Image Enhancement
Image restoration assumes a degradation model that is
known or can be estimated.
Original content and quality ≠ Good looking
if H is a linear, position-invariant operator, then
the degraded image is given in the spatial
domain by
where h(x, y) is the spatial representation of
the degradation function.
in the frequency domain
NOISE MODELS
Most types of noise are
modeled as known probability
density functions
Noise model is decided based
on understanding of the physics
of the sources of noise.
Gaussian: poor illumination
Rayleigh: range image
Gamma, exp: laser imaging
Impulse: faulty switch during
imaging,
Uniform is least used.
Parameters can be estimated
based on histogram on small
flat area of an image
RESTORATION IN THE PRESENCE
OF NOISE ONLY-SPATIAL FILTERING
g(x,y)=f(x,y)+n(x,y);
G(u,v)=F(u,v)+N(u,v);
ARITHMATIC MEAN FILTER
f’(x,y)=1/mn* Σ g(s,t)
(s,t) єSXY
Noise is reduced as a result of
blurring
GEOMATRIC MEAN FILTER
f’(x,y)= [Π g(s,t)] 1/mn
(s,t) єSXY
Geometric mean filter achieves
smoothing comparable to the
arithmetic mean filter, but it tends to
loss less image detail in the process.
HARMONIC MEAN FILTER
f’(x,y)=mn/ [Σ 1/g(s,t)]
(s,t) єSXY
The harmonic mean filter works well for
salt noise, but fails for pepper noise. It
does well also with other types of noise
like Gaussian noise.
CONTRAHARMONIC MEAN
f’(x,y)= [Σ g(s,t)] Q+1
(s,t) єSXY
--------------------------------
[Σ g(s,t)] Q
(s,t) єSXY
Where Q is called order of the filter
This filter is well suited for reducing or virtually
eliminating the effects of salt and peppers noise.
Q=0 it becomes arithmetic mean, and Q = -1
become harmonic mean.
Selection of sign of Q depend on the noise type,
noise is dark or light.
If wrong sign of Q is selected it gives improper results
Order Statistics filter
MEDIAN FILTER
• f’(x,y)=median{g(s,t)}
(s,t) єSXY
• For bipolar and unipolar impulse
noise (salt and pepper noise) median
filter provide excellent noise-
reduction capabilities, with
considerably less blurring than linear
smoothing filters of similar size.
MAX AND MIN FILTERS
f’(x,y)=max{g(s,t)}
(s,t) єSXY
This filter is useful for finding the brightest
point in an image. Reducing peeper noise.
f’(x,y)=min{g(s,t)}
(s,t) єSXY
This filter is used for finding the darkest point
in an image. It reduces salt noise.
MIDPOINT FILTER
f’(x,y)=1/2*[max {g(s,t)} +min{g(s,t)} ]
(s,t) єS (s,t) єS
This filter combines order statistics and averaging.
This filter works best for randomly distributed noise,
like Gaussian and uniform noise.
ALPHA-TRIMMED MEAN FILTER
Suppose that we delete the d/2 lowest and d/2
highest gray-level values of g(s,t) in the
neighborhood.
f’(x,y)=1/(mn-d)*Σ gr(s,t)
( s,t) єSXY
d can range from 0 to mn-1. d=0, the filter
reduces to arithmetic mean filter. If we choose
d=(mn-1)/2, the filter becomes the median
filter.
It is useful in situations involving multiple
types of noise, such as a combination of salt-
and-pepper and Gaussian noise.