This document proposes a new algorithm to reduce striping noise in hyperspectral images. It uses an orthogonal subspace approach to estimate and remove the striping component while preserving useful signal. The algorithm avoids artifacts and accounts for how striping relates to signal intensity. It is experimentally shown to effectively reduce striping noise on real data from airborne and satellite sensors.
2. ABSTRACT
In this paper, a new algorithm for striping noise
reduction in hyper spectral images is proposed.
The new algorithm exploits the orthogonal
subspace approach to estimate the striping
component and to remove it from the image,
preserving the useful signal. The algorithm does
not introduce artifacts in the data and also takes
into account the dependence on the signal
intensity of the striping component. The
effectiveness of the algorithm in reducing
striping noise is experimentally demonstrated on
real data acquired both by airborne and satellite
hyper spectral sensors.
3. Types of Digital images
Binary Images
Two possible values for each pixel.
Greyscale Images
Each pixel carries only the intensity information
Colour Images
Combination of three colours primarily R,G,B
4. Image Noise
Noise in a image , is any degradation in an
image signal, caused by the external
disturbance while an image is being sent from
one place to another place via Satellite,
Wireless or Network Cables.
Causes :
Electronic transfer
Sensor Heat
Etc…
5. Image on the right has more
noise than the image on the left.
6. Types of Image Noise
Impulsive Noise
Black and White pixel noise.
Gaussian Noise
Random values added to an image.
Speckle Noise
Random values multiplies to an image.
Periodic Noise
Periodic disturbance
7. Impulsive Noise
Sharp and sudden disturbance in image signal
Randomly scatted white and black pixels in an
image
Faulty image memory locations and impaired
sensors
Reason for Impulsive Noise
By memory cell failure.
9. Gaussian Noise
It also called “normal noise model”.
It is statistical noise having a probability
density function equal to that of the normal
distribution.
Fuzzy filter is used to remove Gaussian noise.
Reason for Impulsive Noise
Transmission(electronic circuit noise).
11. Existing System
The existing system available for fuzzy filters
for noise reduction deals with fat-tailed noise
like impulse noise and median filter.
Only Impulse noise reduction using fuzzy
filters
Gaussian noise is not specially concentrated
It does not distinguish local variation due to
noise and due to image structure.
12. Proposed System
The proposed system presents a new technique for
filtering narrow-tailed and medium narrow-tailed noise
by a fuzzy filter. The system,
First estimates a “fuzzy derivative” in order to be less
sensitive to local variations due to image structures such
as edges
Second, the membership functions are adapted
accordingly to the noise level to perform “fuzzy
smoothing.”
For each pixel that is processed, the first stage
computes a fuzzy derivative. Second, a set of 16 fuzzy
rules is fired to determine a correction term. These rules
make use of the fuzzy derivative as input.
13. System requirements
Hardware requirement
System : Pentium IV 2.4 GHz.
Hard Disk : 40 GB.
Ram : 256 Mb.
Software requirement
Operating system : Windows and other
Front End : JAVA
Tool : NETBEANS IDE
14. Filtering
Filteringimagedatais a standardprocess
used in
almost all image processing systems.
Filters are used to remove noisefrom digital
image
while keeping the details of image preserved.
The choice of filter is determined by
the nature of the task performed by filter .
Filter behavior .
16. Median filtering
Median filter is a simple and power ful non-linear
filter.
It is used for reducing the amount of intensity
variation between one pixel and the other pixel.
In this filter, we replaces pixel value with the
median value.
The medianis calculated by first sorting all the
pixel values into ascendingorder and then replace
the pixel being calculated with the middlepixel
value
17. Median filtering
Advantages
It is easy to implement.
Used for de-noising different types of noises.
Disadvantages
Median filter tends to remove image details
when the impulse noise percentage is more
than 0.4 %.
18.
19. Mean filtering
Mean filtering is a simple, and easy to
implement method of smoothing images, i.e.
reducing the amount of intensity variation
between one pixel and the next. It is often
used to reduce noise in images.
The idea of mean filtering is simply to
replace each pixel value in an image with the
mean value of it’s neighbors, including itself .
Mean filter can effectively remove the
Gaussian Noise.
20. Mean filtering
Advantage:
Easy to implement
Used to remove the impulse noise.
Disadvantage:
It does not preserve details of image. Some
details are removes of image with using the
mean filter.
21.
22. Fuzzy filtering
It is used to remove both Gaussian noise and
Impulsive noise while preserving edges. We
show that such a Fuzzy filter gives superior
results when compared Mean filter, Median
filter and other Fuzzy filters.
Fuzzy filter can effectively remove both
Gaussian Noise and Impulsive Noise.
25. Modules used
Pre Processing
Member function
Fuzzy Smoothing
Get Clear Gray Image
26. Module Description
Pre Processing
First estimates a “fuzzy derivative” in order to
be less sensitive to local variations due to
image structures such as edges
Second, the membership functions are
adapted accordingly to the noise level to
perform “fuzzy smoothing.”
27. Memberfunction
For each pixel that is processed, the first stage
computes a fuzzy derivative. Second, a set of
fuzzy rules is fired to determine a correction
term. These rules make use of the fuzzy
derivative as input.
Fuzzy sets are employed to represent the
properties, and while the membership functions
for and is fixed, the membership function for are
adapted after each iteration.
28. Fuzzy Smoothing
Set the calculated member function value from
processing of gray scale Image to the negative
pixel area
Get ClearGray Image
To view the clear image by user this very
particular module is used.
29. Input PGM Image
Read image and get max gray level
Calculate the member function
Set the gray level in negative pixel as calculated
From member function
Output clear image
41. Conclusion
Enhancement of an noisy image is necessary
task in image processing.
Filters are used best for removing noise from
the images.
The decision to apply a which particular filter
is based on the different noise level at the
different test pixel location or performance
of the filter scheme on a filtering mask.
42. Future Enhancement
The proposed system is capable of handling
both narrow tailed and medium narrow tailed
noises, where as existing system does not.
The system can be implemented in space
research photography, where there will be
chances of noises occurred.