International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
IMAGE DENOISING FOR SPECKLE NOISE
REDUCTION IN ULTRASOUND IMAGES
USING DWT TECHNIQUE
Jaspreet kaur1, Rajneet kaur2
1
Student Masters of Technology, Shri Guru Granth Sahib World University, Fatehgarh Sahib,Punjab
2
HOD and Assistant Professor, Shri Guru Granth Sahib World University, Fatehgarh Sahib,Punjab
ABSTRACT
This paper presents image denoising and Speckle noise reduction model using different wavelets and combination of wiener
filter along with deconvolution filters. Wavelets are the latest research area in the field of image processing and enhancement.
The results show a comparison of Haar, Symlets and Coiflets Wavelets for Image denoising for biomedical images. Wavelet
analysis represents the next logical step: a windowing technique with variable-sized regions. Wavelet analysis allows the use of
long time intervals where we want more precise low-frequency information, and shorter regions where we want high-frequency
information. The main objective of Image denoising techniques is necessary to remove such noises while retaining as much as
possible the important signal features. Introductory section offer brief idea about different available denoising schemes.
Ultrasonic imaging is a widely used medical imaging procedure because it is economical, comparatively safe, transferable, and
adaptable. Though, one of its main shortcomings is the poor quality of images, which are affected by speckle noise. The
existence of speckle is unattractive since it disgrace image quality and it affects the tasks of individual interpretation and
diagnosis. Results are both Qualitative and Quantitative analyses by obtaining the denoised version of the input image by DWT
along with wiener filter Technique and comparing it with the input image used. Quantitative analysis would be performed by
checking attained Mean Square Error estimation and PSNR of the denoised image. Also, elapsed time for these processing
techniques has also been presented. Another important parameter of PSF (Point Spread Function) of restored image is added
to check the level of distortion in output image.
KEYWORDS: Discrete Wavelet Transform, Speckle Noise, Weiner Filter.
1. INTRODUCTION
The rapid increase in the range and use of electronic imaging justifies attention for systematic design of an image
compression and denoising system and for providing the image quality needed in different applications. The basic
measure for the performance of an enhancement algorithm is PSNR, defined as a peak signal to noise ratio. Quality and
compression can also vary according to input image characteristics and content. In medical imaging, such as ultrasound
image is generated, but the basic problem in these images is the introduced speckle noise [2]. Medical images are
usually corrupted by noise in its acquisition and Transmission.
Figure 1: Ultrasound Image corrupted by speckle noise
Speckle noise becomes a dominating factor in degrading the image visual quality and perception in many other images.
Noise is introduced at all stages of image acquisition [3]. There could be noises due to loss of proper contact or air gap
between the transducer probe and body; there could be noise introduced during the beam forming process and also
during the signal processing stage. [4] Speckle is a particular kind of noise which affects all coherent imaging systems
including medical images and astronomical images. The signal and the noise are statistically independent of each
other. Previously a number of schemes have been proposed for speckle mitigation. The rapid increase in the range and
use of electronic imaging justifies attention for systematic design of an image processing system and for providing the
image quality needed in different applications [2]. The basic measure for the performance of an enhancement algorithm
is mean square error or PSNR (Picture Signal to Noise Ratio). However, Quality and compression can also vary
Volume 2, Issue 6, June 2013
Page 384
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
according to input image characteristics and content.In image processing, image is corrupted by different type of
noises. An appropriate method for speckle reduction is one which enhances the signal to noise ratio while conserving
the edges and lines in the image. The sample mean and variance of a single pixel are equal to the mean and variance
of the local area that is centered on that pixel. A vast literature has emerged recently on signal de-noising using
nonlinear techniques, in the setting of speckle noise. The image analysis process can be broken into three primary
stages which are pre-processing, data reduction, and features analysis. Removal of noise from an image is the one of the
important tasks in image processing. Depending on nature of the noise, such as additive or multiplicative noise, there
are several approaches for removal of noise from an image [5]. The main objective of Image denoising techniques is
necessary to remove such noises while retaining as much as possible the important signal features.
2. LITERATURE REVIEW
Digital image acquisition and processing techniques play an important role in current day medical diagnosis. Images of
living objects are taken using different modalities like X-ray, Ultrasound, Computed Tomography (CT), Medical
Resonance Imaging (MRI) etc. [1] Highlights the importance of applying advanced digital image processing techniques
for improving the quality by removing noise components present in the acquired image to have a better diagnosis. [1]
also shows a survey on different techniques used in ultrasound image denoising. [2] has presented the work on use of
wiener filtering in wavelet domain with soft thresholding as a comprehensive technique. Also, [2] compares the
efficiency of wavelet based thresholding (Visushrink, Bayesshrink and Sureshrink) technique in despeckling the
medical Ultrasound images with five other classical speckle reduction filters. The performance of these filters is
determined using the statistical quantity measures such as Peak-Signal-to-Noise ratio (PSNR) and Root Mean Square
Error (RMSE). Based on the statistical measures and visual quality of Ultrasound B-scan images the wiener filtering
with Bayesshrink thresholding technique in the wavelet domain performed well over the other filter techniques.[3] has
presented different filtration techniques (wiener and median) and a proposed novel technique that extends the existing
technique by improving the threshold function parameter K which produces results that are based on different noise
levels. A signal to mean square error as a measure of the quality of denoising was preferred.
3. PROBLEM FORMULATION
To Design and implement a model for image denoising using discrete wavelet transform using multilevel
decomposition approach. Quantitative analysis would be performed by checking attained Peak Signal to Noise Ratio
(PSNR) and Mean Square Error estimation of the denoised image. Speckle noise reduction is another main criterion for
determining the image quality objectively. A comparative analysis of Haar wavelets, Symlets wavelets and Coiflets.
4. RESEARCH METHODOLOGY
4.1 MULTIRESOLUTIONAL ANALYSIS
Wavelet analysis represents the next logical step: a windowing technique with variable-sized regions. Wavelet analysis
allows the use of long time intervals where we want more precise low-frequency information, and shorter regions where
we want high-frequency information.
Figure 2: Wavelet Transform on a signal
The decomposition process can be iterated, with successive approximations being decomposed in turn, so that one
signal is broken down into many lower resolution components. This is called the wavelet decomposition tree.
Figure 3: Multilevel Decomposition
Volume 2, Issue 6, June 2013
Page 385
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
Lifting schema of DWT has been recognized as a faster approach
 The basic principle is to factorize the polyphase matrix of a wavelet filter into a sequence of alternating upper and
lower triangular matrices and a diagonal matrix.
 This leads to the wavelet implementation by means of banded-matrix multiplications
All the wavelet filters use wavelet thresholding operation for denoising [2], [11], [12].Speckle noise is a high-frequency
component of the image and appears in wavelet coefficients. One widespread method exploited for speckle reduction is
wavelet thresholding procedure. The basic Procedure for all thresholding method is as follows:
· Calculate the DWT of the image.
· Threshold the wavelet coefficients. (Threshold maybe universal or sub band adaptive)
· Compute the IDWT to get the denoised estimate.
· There are two thresholding functions frequently used ,i.e. a hard threshold, a soft threshold. The hard- thresholding
is described as
η1 (w) = wI (| w |> T) Where w is a wavelet coefficient, T is the threshold. The
Soft-thresholding function is described as
η2 (w) = (w – sgn (w) T) I (| w | > T )
Where sgn(x) is the sign function of x. The soft-thresholding rule is chosen over hard-thresholding, As for as speckle
(multiplicative nature) removal is concerned a preprocessing step consisting of a logarithmic transform is performed to
separate the noise from the original image. Then different wavelet shrinkage approaches are employed. The different
methods of wavelet threshold denoising differ only in the selection of the threshold.
4.3 Wiener Filter
Wiener filter was adopted for filtering in the spectral domain. Wiener filter (a type of linear filter) is applied to an
image adaptively, tailoring itself to the local image variance. Where the variance is large, Wiener filter performs little
smoothing. Where the variance is small, Wiener performs more smoothing. This approach often produces better results
than linear filtering. The adaptive filter is more selective than a comparable linear filter, preserving edges and other
high-frequency parts of an image. However, wiener filter require more computation time than linear filtering. The
inverse filtering is a restoration technique for deconvolution, i.e., when the image is blurred by a known lowpass filter,
it is possible to recover the image by inverse filtering or generalized inverse filtering. However, inverse filtering is very
sensitive to additive noise. The approach of reducing one degradation at a time allows us to develop a restoration
algorithm for each type of degradation and simply combine them. The Wiener filtering executes an optimal tradeoff
between inverse filtering and noise smoothing. It removes the additive noise and inverts the blurring simultaneously. It
minimizes the overall mean square error in the process of inverse filtering and noise smoothing. The Wiener filtering is
a linear estimation of the original image. The approach is based on a stochastic framework. The orthogonality principle
implies that the Wiener filter in Fourier domain can be expressed as follows:
where Sxx(f1,f2), Snn(f1,f2) are respectively power spectra of the original image and the additive noise, and H(f1,f2) is
the blurring filter. It is easy to see that the Wiener filter has two separate part, an inverse filtering part and a noise
smoothing part. It not only performs the deconvolution by inverse filtering (high pass filtering) but also removes the
noise with a compression operation (low pass filtering). Recently
5. SPECKEL NOISE MODEL
Mathematically the image noise can be represented with the help of these equations below:
Here u(x, y) represents the objects (means the original image) and v(x, y) is the observed image. Here h (x, y; x’, y’)
represents the impulse response of the image acquiring process. The term ŋ(x, y) represents the additive noise which
has an image dependent random components f [g(w)] ŋ1 and an image independent random component ŋ2. A different
type of noise in the coherent imaging of objects is called speckle noise. Speckle noise can be modeled as
V(x, y) = u(x, y)s(x, y) + ŋ(x, y) (4)
Volume 2, Issue 6, June 2013
Page 386
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
Where the speckle noise intensity is given by s(x, y) and ŋ(x, y) is a white Gaussian noise [1]-[3].
6. TYPE OF WAVELETS USED
6.1 Haar Wavelets: Haar wavelet is the first and simplest. Haar wavelet is discontinuous, and resembles a step
function. It represents the same wavelet as Daubechies db1.
Figure 4: Haar Wavelet Function Waveform
6.2 Symlets Wavelet
The Symlets are nearly symmetrical wavelets proposed by Daubechies as modifications to the db family. The properties
of the two wavelet families are similar. There are 7 different Symlets functions from sym2 to sym8. We have used sym2
function shown below.
Figure 5: sym2 Wavelet Function Waveform
6.3 Coiflets Wavelet
Built by I. Daubechies at the request of R. Coifman. The wavelet function has 2N moments equal to 0 and the scaling
function has 2N-1 moments equal to 0. The two functions have a support of length 6N-1.
Figure 6: Coiflet Wavelet Function Waveform
7. RESULTS
Computer simulations were carried out using MATLAB (R2010b). The quality of the reconstructed image is specified
in terms of the Peak Signal-to-Noise, Mean Square Error Elapsed time and PSF. Experimental results are conducted on
50 ultrasound images (kidney, brain, liver, hernia, spine and abdomen). Speckle noise with level 0.4 was added to the
image. In this paper, we show results on two images brain and spine with table of 50 images.
I.
BRAIN IMAGE
USING HAAR WAVELET AND WIENER FILTERS
COEFFICIENTS OF IMAGE
(APPROXIMATION AND DETAIL)
Volume 2, Issue 6, June 2013
ORIGINAL IMAGE
PSF OF ORIGINAL IMAGE
Page 387
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
NOISY IMAGE
DENOISED IMAGE
PSF OF DENOISED IMAGE
USING SYMLETS WAVELET AND WIENER FILTERS
COEFFICIENTS OF IMAGE
(APPROXIMATION AND DETAIL)
NOISY IMAGE
ORIGINAL IMAGE
DENOISED IMAGE
PSF OF ORIGINAL IMAGE
PSF OF DENOISED IMAGE
USING COIFLET WAVELET AND WIENER FILTERS
COEFFICIENTS OF IMAGE
(APPROXIMATION AND DETAIL)
Volume 2, Issue 6, June 2013
ORIGINAL IMAGE
PSF OF ORIGINAL IMAGE
Page 388
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
NOISY IMAGE
WAVELET
HAAR
SYMLET
COIFLET
DENOISED IMAGE
PSF OF DENOISED IMAGE
TABLE 1: RESULTS OF BRAIN IMAGE
MSE
ELAPSED TIME
PSNR
0.0351
16.55 SECONDS
88.7306
0.0917
17.13 SECONDS
84.5626
0.0634
16.95 SECONDS
86.1656
II. SPINE IMAGE
USING HAAR WAVELET AND WIENER FILTERS
COEFFICIENTS OF IMAGE
(APPROXIMATION AND DETAIL)
NOISY IMAGE
ORIGINAL IMAGE
DENOISED IMAGE
PSF OF ORIGINAL IMAGE
PSF OF DENOISED IMAGE
USING SYMLET WAVELET AND WIENER FILTERS
COEFFICIENTS OF IMAGE
(APPROXIMATION AND DETAIL)
Volume 2, Issue 6, June 2013
ORIGINAL IMAGE
PSF OF ORIGINAL IMAGE
Page 389
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
NOISY IMAGE
DENOISED IMAGE
USING COIFLET WAVELET AND WIENER FILTERS
COEFFICIENTS OF IMAGE
(APPROXIMATION AND DETAIL)
NOISY IMAGE
WAVELET
HAAR
SYMLET
COIFLET
ORIGINAL IMAGE
DENOISED IMAGE
PSF OF DENOISED IMAGE
PSF OF ORIGINAL IMAGE
PSF OF DENOISED IMAGE
TABLE 1: RESULTS OF SPINE IMAGE
MSE
ELAPSED TIME
0.0022
14.89 SECONDS
0.0060
16.80 SECONDS
0.0036
15.38 SECONDS
PSNR
99.1405
94.7605
97.0229
GRAPH RESULTS:
GRAPH 1: PSNR AND TIME GRAPH OF BRAIN IAMGE
Volume 2, Issue 6, June 2013
Page 390
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
GRAPH 2: PSNR AND TIME GRAPH OF SPINE IAMGE
GRAPH 3: MSE GRAPH OF BRAIN IMAGE
GRAPH 4: MSE GRAPH OF SPINE IMAGE
IMAGE
TABLE 3: RESULTS OF 50 ULTRASOUND IMAGES
WAVELET USED PSNR
MSE
KJ
HAAR
85.9707
0.0663
ELAPSED
TIME(SECONDS)
16.6
SYMLET
81.7388
0.1757
17.13
COIFLET
83.263
0.1237
16.61
HAAR
78.1435
0.0771
4.84
SYMLET
74.6477
0.1725
5.98
COIFLET
76.727
0.1069
5.47
HAAR
79.613
0.0549
5.9
SYMLET
75.8726
0.13
6.11
COIFLET
77.35
0.0925
5.55
HAAR
78.1061
0.0779
5.4
SYMLET
74.4286
0.1816
6.33
COIFLET
76.0567
0.1248
6.03
HAAR
88.7306
0.0351
16.55
SYMLET
84.5626
0.0917
17.13
COIFLET
86.1656
0.0634
16.95
HAAR
88.6909
0.0354
16.26
COIFLET
84.5531
0.0919
17.56
COIFLET
86.1561
0.0635
16.65
HAAR
79.461
0.057
5.22
SYMLET
75.575
0.1398
5.58
COIFLET
77.0088
0.1005
5.33
KJ000
KJ00
KJ0
KJ1
KJ2
KJ7
Volume 2, Issue 6, June 2013
Page 391
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
KJ8
KJ9
KJ10
KJ11
SPINE
KJ12
KJ13
KJ14
HAAR
76.9364
0.1019
4.72
SYMLET
73.4945
0.225
5.25
COIFLET
75.3794
0.1458
5.05
HAAR
81.5985
0.0719
8.87
SYMLET
78.4944
0.1469
10.03
COIFLET
80.1329
0.1008
9.19
HAAR
82.2858
0.0298
4.77
SYMLET
78.6745
0.0684
5.45
COIFLET
80.808
0.0419
4.85
HAAR
88.7409
0.023
12.58
SYMLET
84.5442
0.0605
13.55
COIFLET
87.2925
0.0321
12.68
HAAR
99.1405
0.0022
14.89
SYMLET
94.7605
0.006
16.8
COIFLET
97.0229
0.0036
15.38
HAAR
87.6692
0.0448
15.89
SYMLET
83.4987
0.1171
16.39
COIFLET
85.3011
0.0773
16.16
HAAR
88.7001
0.0354
15.61
SYMLET
84.5873
0.0912
16.7
COIFLET
86.4531
0.0593
16.05
HAAR
87.4247
0.0469
15.14
SYMLET
83.303
0.1225
16.32
COIFLET
85.0906
0.0812
16.21
IMAGE
WAVELET USED
PSNR
MSE
ELAPSED TIME
KJ15
HAAR
77.6513
0.0867
5.46
SYMLET
73.8652
0.2072
5.91
COIFLET
76.2996
0.1183
5.82
HAAR
78.3735
0.0734
5.58
SYMLET
74.1542
0.194
6.01
COIFLET
75.8904
0.1301
5.61
HAAR
77.8855
0.0821
4.59
SYMLET
73.9627
0.2025
5.82
COIFLET
75.7956
0.1328
5.11
HAAR
81.944
0.0578
7.46
SYMLET
78.0665
0.1411
8.01
COIFLET
79.8413
0.0938
7.65
HAAR
90.2586
0.0374
19.52
SYMLET
86.1474
0.0964
20.24
COIFLET
88.4882
0.0562
19.68
KJ16
KJ17
KJ18
KJ19
Volume 2, Issue 6, June 2013
Page 392
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
KJ20
KJ21
KJ22
KJ23
KJ24
KJ25
KJ26
KJ27
KJ28
KJ29
KJ30
KJ31
KJ32
KJ33
HAAR
89.1287
0.0485
22.29
SYMLET
84.9356
0.1274
25.35
COIFLET
87.1147
0.0771
23.08
HAAR
97.6536
0.018
51.78
SYMLET
93.1123
0.0512
56.73
COIFLET
94.3994
0.0381
55.93
HAAR
91.7505
0.0255
27.92
SYMLET
87.8055
0.0632
28.33
COIFLET
90.4244
0.0346
28.02
HAAR
80.4189
0.0458
4.81
SYMLET
76.6821
0.1084
5.77
COIFLET
78.7799
0.0669
4.83
HAAR
80.3294
0.0469
4.43
SYMLET
76.485
0.1137
5.61
COIFLET
77.5518
0.089
4.92
HAAR
76.1718
0.1222
4.69
SYMLET
72.1154
0.311
5.32
COIFLET
73.4441
0.2291
5.23
HAAR
80.5422
0.0445
5.8
SYMLET
76.7512
0.1065
7.22
COIFLET
78.5807
0.0699
6.29
HAAR
82.4783
0.0285
4.59
SYMLET
78.5285
0.0709
5.04
COIFLET
80.3022
0.0471
4.76
HAAR
77.2679
0.0943
5.02
SYMLET
73.6612
0.2163
6.9
COIFLET
75.5039
0.1415
5.75
HAAR
76.8936
0.1031
5.56
SYMLET
72.8288
0.2628
6.4
COIFLET
74.4114
0.1825
5.91
HAAR
80.4794
0.033
3.81
SYMLET
76.4339
0.0838
4.5
COIFLET
78.3971
0.0533
3.92
HAAR
79.724
0.0537
3.92
SYMLET
75.79
0.1329
4.87
COIFLET
78.1976
0.0763
4.39
HAAR
80.1818
0.0485
4.75
SYMLET
76.4364
0.115
5.03
COIFLET
78.8112
0.0665
4.93
HAAR
77.5477
0.058
4.05
SYMLET
73.4768
0.148
4.28
COIFLET
75.5542
0.0917
4.15
Volume 2, Issue 6, June 2013
Page 393
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
KJ34
KJ35
KJ36
KJ37
KJ38
KJ39
KJ40
KJ41
KJ42
KJ43
KJ44
KJ45
KJ46
KJ47
HAAR
79.6479
0.0547
4.92
SYMLET
76.1274
0.123
5.66
COIFLET
78.2347
0.0757
5.36
HAAR
80.3993
0.0459
4.52
SYMLET
76.4775
0.1132
5.4
COIFLET
78.451
0.0719
4.95
HAAR
81.6237
0.0347
4.37
SYMLET
77.6217
0.0871
5.59
COIFLET
78.5457
0.0704
4.6
HAAR
81.156
0.0385
4.55
SYMLET
77.1558
0.0968
4.92
COIFLET
79.3974
0.0578
4.68
HAAR
78.6948
0.0681
3.51
SYMLET
74.56
0.1764
4.25
COIFLET
76.6259
0.1096
3.96
HAAR
88.3307
0.0451
15.07
SYMLET
84.6692
0.1048
16.64
COIFLET
86.2697
0.0725
15.71
HAAR
85.2681
0.0418
11.4
SYMLET
81.1827
0.1071
12.06
COIFLET
83.3578
0.0649
11.97
HAAR
84.5248
0.0667
14.1
SYMLET
80.4418
0.1709
14.38
COIFLET
82.538
0.1054
14.2
HAAR
75.7312
0.1219
4.07
SYMLET
71.6427
0.3124
4.94
COIFLET
72.7329
0.243
4.86
HAAR
78.5473
0.0702
4.57
SYMLET
74.3486
0.1845
5.08
COIFLET
76.3537
0.1163
4.99
HAAR
78.9252
0.0643
4.3
SYMLET
74.6891
0.1706
5.1
COIFLET
76.1694
0.1213
4.44
HAAR
77.2985
0.0786
3.81
SYMLET
73.365
0.1945
4.5
COIFLET
75.1045
0.1303
4.1
HAAR
80.4149
0.0403
4.98
SYMLET
76.3711
0.1024
5.18
COIFLET
78.5777
0.0616
5.05
HAAR
77.6503
0.0864
5.84
SYMLET
73.844
0.2076
6.59
COIFLET
76.1379
0.1224
6.05
Volume 2, Issue 6, June 2013
Page 394
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
KJ48
KJ49
HAAR
84.476
0.0437
7.2
SYMLET
80.3357
0.1134
8.55
COIFLET
81.6828
0.0831
7.57
HAAR
76.4592
0.1139
3.89
SYMLET
74.1866
0.1922
4.12
COIFLET
75.1999
0.1522
4.07
8. CONCLUSION
Image denoising has been achieved using new technique of wavelet transform in combination with wiener filters and
results have been obtained that could be measured subjectively by viewing the pictures of restored image attained as
above results and checking the PSF of final restored image that shows very less distortion parameter. Also, Image
quality has been measured objectively using MSE value with different wavelets. At the end we conclude that haar
wavelet with wiener filter provide better results than symlets and coiflets wavelet. Haar wavelet is better than coiflets
wavelet and coiflets is better than symlets wavelet.
9. FUTURE SCOPE
In future, work can be done to implement this algorithm of multiresolutional analysis presented in this thesis on other
types of medical imaging like CT Scan, MRI and EEG images under various different kinds of noise like speckle noise,
Gaussian noise, etc. Also, this work could be implemented on an FPGA to build an intelligent model that could be used
for denoising in ultrasound images. Work could be done to minimize the constraints and resource utilization on FPGA
implementation of this model. Also, with slight modifications in the code, efforts can be made to reduce the processing
time of the model.
REFERENCES
[1.] Image Compression using Wavelets: Sonja Grgc, Kresimir Kers, Mislav Grgc, University of Zagreb, IEEE
publication, 1999
[2.] M. Antonini, M. Barlaud, P. Mathieu, and I. Daubechies, Image coding using wavelet transform, IEEE Trans.
Image Processing, vol. 1, pp.205-220, 1992.
[3.] P.L. Dragotti, G. Poggi, and A.R.P. Ragozini, Compression of multispectral images by three-dimensional SPIHT
algorithm, IEEE Trans. on Geoscience and remote sensing, vol. 38, No. 1, Jan 2000.
[4.] Thomas W. Fry, Hyperspectral image compression on recon_gurable platforms, Master Thesis, Electrical
Engineering, University of Washington, 2001.
[5.] S-T. Hsiang and J.W. Woods, Embedded image coding using zeroblocks of subband/wavelet coefficients and
context modeling, IEEE Int. Conf. on Circuits and Systems (ISCAS2000), vol. 3, pp.662-665, May 2000.
[6.] A. Islam and W.A. Pearlman, An embedded and efficient low-complexity hierarchical image coder, in Proc. SPIE
Visual Comm. and Image Processing, vol. 3653, pp. 294-305, 1999.
[7.] B. Kim and W.A. Pearlman, An embedded wavelet video coder using three-dimensional set partitioning in
hierarchical tree, IEEE Data Compression Conference, pp.251-260, March 1997.
[8.] Y. Kim and W.A. Pearlman, Lossless volumetric medical image compression, Ph.D Dissertation, Department of
Electrical, Computer,and Systems Engineering, Rensselaer Polytechnic Institute, Troy, 2001.
[9.] J. Li and S. Lei, Rate-distortion optimized embedding, in Proc. Picture Coding Symp., Berlin, Germany, pp. 201206, Sept. 10-12, 1997.
[10.] S. Mallat, Multifrequency channel decompositions of images and wavelet models, IEEE Trans. Acoust., Speech,
Signal Processing, vol. 37, pp.2091-2110, Dec. 1989.
[11.] A.N. Netravali and B.G. Haskell, Digital pictures, representation and compression, in Image Processing, Proc. of
Data Compression Conference, pp.252-260, 1997.
[12.] E. Ordentlich, M. Weinberger, and G. Seroussi, A low-complexity modeling approach for embedded coding of
wavelet coef_cients, in Proc. IEEE Data Compression Conf., Snowbird, UT, pp. 408-417, Mar. 1998.
[13.] W.A. Pearlman, Performance bounds for subband codes, Chapter 1 in Subband Image Coding, J. W. Woods and
Ed. Klvwer. Academic Publishers, 1991.
[14.] Proposal of the arithmetic coder for JPEG2000, ISO/IEC/JTC1/SC29/WG1 N762, Mar. 1998.
[15.] A. Said and W.A. Pearlman, A new, fast and ef_cient image codec based on set partitioning in hierarchical trees,
IEEE Trans. on Circuits and Systems for Video Technology 6, pp. 243-250, June 1996.
Volume 2, Issue 6, June 2013
Page 395
International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com
Volume 2, Issue 6, June 2013
ISSN 2319 - 4847
[16.] P. Schelkens, Multi-dimensional wavelet coding algorithms and implementations, Ph.D dissertation, Department
of Electronics and Information Processing, Vrije Universiteit Brussel, Brussels, 2001.
[17.] J.M. Shapiro, Embedded image coding using zerotrees of wavelet coef_cients, IEEE Trans. Signal Processing, vol.
41, pp.3445-3462, Dec. 1993.
[18.] D. Taubman, High performance scalable image compression with EBCOT, IEEE Trans. on Image Processing, vol.
9, pp.1158-1170, July,2000.
[19.] I.H. Witten, R.M. Neal, and J.G. Cleary, Arithmetic coding for data compression, Commun. ACM, vol. 30, pp.
520-540, June 1987.
[20.] J.W. Woods and T. Naveen, Alter based bit allocation scheme for subband compression of HDTV, IEEE
Transactions on Image Processing, IP-1:436-440, July 1992.November 7,
Volume 2, Issue 6, June 2013
Page 396