Download Fig 2(d) - Academic Science,International Journal of Computer

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Charge-coupled device wikipedia , lookup

BSAVE (bitmap format) wikipedia , lookup

Computer vision wikipedia , lookup

Dither wikipedia , lookup

Edge detection wikipedia , lookup

Hold-And-Modify wikipedia , lookup

Anaglyph 3D wikipedia , lookup

Indexed color wikipedia , lookup

Medical imaging wikipedia , lookup

Stereoscopy wikipedia , lookup

Stereo display wikipedia , lookup

Spatial anti-aliasing wikipedia , lookup

Image segmentation wikipedia , lookup

Histogram of oriented gradients wikipedia , lookup

Image editing wikipedia , lookup

Medical image computing wikipedia , lookup

Transcript
Contrast Enhancement of Medical Images - A Review
Priya Thamman
PURCITM, Punjabi University,
Patiala, India
[email protected]
Ashish Verma
Dept of CSE & IT,SSIET, PTU
Dera Bassi, India
[email protected]
ABSTRACT
Imaging is one of the most important application areas of
digital image processing. Processing of various medical images
is very much helpful to visualize and extract more details like
fractures, tumors and cancers from the image. There are many
techniques available for enhancing the contrast of medical
image. For enhancement of medical images, Contrast
Enhancement is one of the most acceptable method. Different
contrast enhancement techniques i.e. Linear Stretch, Histogram
Equalization, Convolution mask enhancement, Region based
enhancement, Adaptive enhancement are already available.
Choice of Method depends on characteristics of image. This
research work deals with contrast enhancement of X-Ray
images and presents here a review of different contrast
enhancement techniques so that max information will be
visible.
Adaptive histogram equalization (AHE) is a computer image
processing technique used to improve contrast in images. It
differs from ordinary histogram equalization in the respect that
the adaptive method computes several histograms, each
corresponding to a distinct section of the image, and uses them
to redistribute the lightness values of the image. It is therefore
suitable for improving the local contrast of an image and
bringing out more detail.
Keywords
The size of the neighbourhood region is a parameter of the
method. It constitutes a characteristic length scale: contrast at
smaller scales is enhanced, while contrast at larger scales is
reduced.
Image Enhancement, Contrast, Histogram Equalization,
Adaptive Histogram Equalization, X ray medical images.
However, AHE has a tendency to over amplify noise in
relatively homogeneous regions of an image. A variant of
adaptive histogram equalization called contrast limited
adaptive histogram equalization (CLAHE) prevents this by
limiting the amplification. The properties of AHE are
1. INTRODUCTION
Medical imaging is the technique and process used to create
images of the human body (or parts and function thereof) for
clinical purposes (medical procedures seeking to reveal,
diagnose, or examine disease) or medical science (including the
study of normal anatomy and physiology). Although imaging of
removed organs and tissues can be performed for medical
reasons, such procedures are not usually referred to as medical
imaging, but rather are a part of pathology.
Due to the nature of histogram equalization, the result value of
a pixel under AHE is proportional to its rank among the pixels
in its neighbourhood. This allows an efficient implementation
on specialist hardware that can compare the center pixel with
all other pixels in the neighbourhood. An unnormalized result
value can be computed by adding 2 for each pixel with a
smaller value than the center pixel, and adding 1 for each pixel
with equal value.
Medical imaging is often perceived to designate the set of
techniques that noninvasively produce images of the internal
aspect of the body. In this restricted sense, medical imaging can
be seen as the solution of mathematical inverse problems. This
means that cause (the properties of living tissue) is inferred
from effect (the observed signal). In the case of
ultrasonography the probe consists of ultrasonic pressure waves
and echoes inside the tissue show the internal structure. In the
case of projection radiography, the probe is X-ray radiation
which is absorbed at different rates in different tissue types
such as bone, muscle and fat.
When the image region containing a pixel's neighbourhood is
fairly homogeneous, its histogram will be strongly peaked, and
the transformation function will map a narrow range of pixel
values to the whole range of the result image. This causes AHE
to over amplify small amounts of noise in largely homogeneous
regions of the image.
Contrast enhancement is used to improve the perceptibility of
objects. It enhances the brightness difference of scene between
objects and their backgrounds. Contrast enhancements are
typically performed as a contrast stretch followed by a tonal
enhancement, although these could both be performed in one
step. A contrast stretch improves the brightness differences
uniformly across the dynamic range of the image. Tonal
enhancements improve the brightness differences in the shadow
(dark), midtone (grays), or highlight (bright) regions at the
expense of the brightness differences in the other regions.
Contrast Limited AHE
Contrast Limited AHE (CLAHE) differs from ordinary
adaptive histogram equalization in its contrast limiting. This
feature can also be applied to global histogram equalization,
giving rise to contrast limited histogram equalization (CLHE),
which is rarely used in practice. In the case of CLAHE, the
contrast limiting procedure has to be applied for each
neighbourhood from which a transformation function is
derived. CLAHE was developed to prevent the over
amplification of noise that adaptive histogram equalization can
give rise to.
1
It is achieved by limiting the contrast enhancement of AHE.
The contrast amplification in the vicinity of a given pixel value
is given by the slope of the transformation function. It is
proportional to the slope of the neighbourhood cumulative
distribution function (CDF) and therefore to the value of the
histogram at that pixel value. CLAHE limits the amplification
by clipping the histogram at a predefined value before
computing the CDF. This limits the slope of the CDF and
therefore of the transformation function. The value at which the
histogram is clipped, the so-called clip limit, depends on the
normalization of the histogram and thereby on the size of the
neighbourhood region. Common values limit the resulting
amplification to between 3 and 4 times the histogram mean
value.
It is advantageous not to discard the part of the histogram that
exceeds the clip limit but to redistribute it equally among all
histogram bins.
J. B. Zimmerman [1] suggested Adaptive histogram
equalization (AHE), a method of contrast enhancement which
is sensitive to local spatial information in an image, has been
proposed as a solution to the problem of the inability of
ordinary display devices to depict the full dynamic intensity
range in some medical images. It is automatic, reproducible,
and simultaneously displays most of the information contained
in the grayscale contrast of the image. However, it has not been
known whether the use of AHE causes the loss of diagnostic
information relative to the commonly-used method of intensity
windowing. In the current work, AHE and intensity windowing
are compared using psychophysical observer studies.
W. M. Morrow [2] checked that diagnostic features in
mammograms vary widely in size and shape. Classical image
enhancement techniques cannot adapt to the varying
characteristics of such features. An adaptive method is
proposed for enhancing the contrast of mammographic features
of varying size and shape. The method uses each pixel in the
image as a seed to grow a region. The extent and shape of the
region adapt to local image gray-level variations, corresponding
to an image feature. The contrast of each region is calculated
with respect to its individual background. Contrast is then
enhanced by applying an empirical transformation based on
each region’s seed pixel value, its contrast, and its background.
A quantitative measure of image contrast improvement is also
defined based on a histogram of region contrast and used for
comparison of results. Using mammogram images digitized at
high resolution (less than 0.1 mm pixel size), it is shown that
the visibility of microcalcification clusters and anatomic details
is considerably improved in the processed images Here
transformation is applied on each pixel so that both back and
foreground changes and results are better than Zimmerman
method.
S.D. Chen [3] told that histogram equalization (HE) is widely
used for contrast enhancement. However, it tends to change
(MMBEBHE) to provide maximum brightness preservation.
BBHE separates the input image's histogram into two based on
input mean before equalizing them independently. This paper
proposes to perform the separation based on the threshold level,
which would yield minimum Absolute Mean Brightness Error
(AMBE - the absolute difference between input and output
mean). An efficient recursive integer-based computation for
AMBE has been formulated to facilitate real time
implementation. Simulation results using sample image which
represent images with very low, very high and medium mean
brightness show that the cases which are not handled well by
HE, BBHE and Dualistic Sub Image Histogram Equalization
(DSIHE), can be properly enhanced by MMBEBHE. Besides,
MMBEBHE also demonstrate comparable performance with
BBHE and DSIHE. This algorithm shows better results than
previous methods.
N. Kanwal [4] studied that medical imaging is one of the most
important application areas of digital image processing.
Processing of various medical images is very much helpful to
visualize and extract more details from the image. Many
techniques are available for enhancing the quality of medical
image. For enhancement of medical images, Contrast
Enhancement is one of the most acceptable methods. Different
contrast enhancement techniques i.e. Linear Stretch, Histogram
Equalization, Convolution mask enhancement, Region based
enhancement, Adaptive enhancement are already available.
Choice of Method depends on characteristics of image. This
paper deals with contrast enhancement of X-Ray images and
presents here a new approach for contrast enhancement based
upon Adaptive Neighborhood technique. A hybrid
methodology for enhancement has been presented.
Comparative analysis of proposed technique against the
existing major contrast enhancement techniques has been
performed and results of proposed technique are promising.
The problem is here as this algorithm enhances two much in
low grained region so if breakage or crack in the bone then it is
not possible to visualize the crack in the bone.
N.J. Dhinagar et. al. [5] suggested that ultrasound images,
though easy to obtain, have inherent flaws due to low frequency
tissue image aberrations such as poor contrast caused by the
presence of the granular speckle noise. The proposed algorithm
aims to improve the ability to differentiate between healthy and
malignant conditions via the use of homomorphic filtering and
Otsu’s gray-level histogram thresholding. The characteristics of
the Gaussian window function are adaptively changed based on
the input ultrasound image samples taken from different
medical ultrasonography scans. A cost estimation function
helps establish the adaptability of the filter by means of
calculating the mean and variance of local windows and
correspondingly evaluate the most discriminative part of the
image sample in process. Signal to noise ratio is adopted as an
image quality measure of the enhancement operation.
Experimental results show the effectiveness of the
homomorphic filtering and the robustness of the overall system
as a useful diagnostic tool.
the brightness of an image and hence, not suitable for consumer
electronic products, where preserving the original brightness is
essential to avoid annoying artifacts. Bi-histogram equalization
(BBHE) has been proposed and analyzed mathematically that it
can preserve the original brightness to a certain extends.
However, there are still cases that are not handled well by
BBHE, as they require higher degree of preservation. This
paper proposes a novel extension of BBHE referred to as
Minimum Mean Brightness Error Bi-Histogram Equalization
2
Table 1: The comparison of various parameters with different
contrast enhancement techniques.
2. PARAMETERS USED
(i)
PSNR=
(ii)
10 log 10
2552
MSE
Mean Square Error (MSE)
MSE =
(iii)
Parameter
PSNR
MSE
CONTRAST
Peak Signal to Noise Ratio (PSNR)
1
MN
 x
M
N
j 1 k 1
 x' j , k 
2
j ,k
Fig 1 (b)
21.51
458.69
3.8985
Fig 1 (c)
17.8882
1057.5
3.6902
Fig 1(d)
Infinity
0.00
0.00
The parameter values show that linear stretching performs
better than histogram equalization and contrast limited adaptive
histogram equalization. The peak signal to noise ratio should be
maximum and mean square error should be minimum.
Absolute Contrast Error (ACE)
Absolute Contrast Error is the difference between the
deviations of the original image and the enhanced image.
3. COMPARISON OF ALGOGRITHMS
Fig 2:(a)
Fig 1:(a)
Fig 1:(b)
Fig 2:(c)
Fig 1:(c)
Fig 2:(b)
Fig 2:(d)
Fig 1:(d)
Fig 1: (a) Original Image, (b) Histogram image, (c) CLAHE
image, (d) Linear Contrast Stretching
Fig 2: (a) Original Image, (b) Histogram image, (c) CLAHE
image, (d) Linear Contrast Stretching
3
Table 2: The comparison of various parameters with different
contrast enhancement techniques.
Parameter
Fig 2 (b) Fig 2 (c) Fig 2(d)
PSNR
7.7030
19.20
Infinity
MSE
1103.5
1057.5
0.00
CONTRAST 3.8985
3.6902
0.00
The parameter values show that linear stretching performs
better than histogram equalization and contrast limited
adaptive histogram equalization. The peak signal to noise
ratio should be maximum and mean square error should be
minimum.
4. ACKNOWLEDGMENTS
I express my sincere gratitude to the ashish verma who helped
me a lot to prepare this paper. He is reviewer of reputed
international journals. His areas of research include image and
video processing, algorithmic computation, design of
programming languages and compilers, game theory and
organic computing.
5. REFERENCES
[1] Zimmerman, J. B., Pizer, S. M., Staab, E.V., Perry, J. R.,
McCartney, W. and Brenton, B. C., “An Evaluation of
the Effectiveness of Adaptive histogram equalization for
contrast enhancement”, IEEE Transaction on Medical
Imaging,, Vol. 7, No. 4, 1988, pp. 304-312.
[2] Morrow, W.M., Paranjape, R.B., Rangayyan, R.M.,
Desautels, J.E.L., “Region-based contrast enhancement
of mammograms”, IEEE transactions on Medical
Imaging, Vol. 11, No. 3, 1992, pp. 392-406.
[3] Chen, Soong-Der and Ramli, Abd. Rahman, “Minimum
Mean Brightness Error Bi-Histogram Eualization in
Contrast Enhancement”, IEEE Transactions on
Consumer Electronics, Vol. 49, No. 4, 2003, pp. 13101319.
[4] N. Kanwal, A. Girdhar, S. Gupta, “Region Based
Adaptive Contrast Enhancement of Medical X-Ray
Images”, ICBBE, Vol. 10, 2011, pp 1- 5.
[5] N. J. Dhinagar and M. Celenk, “Ultrasound Medical
Image Enhancement and Segmentation using Adaptive
Homomorphic Filtering and Histogram Thresholding”,
IEEE EMBS, 2012, pp. 349- 353.
4