International Journal of Engineering Trends and Technology (IJETT) Volume 4 Issue 10 - Oct 2013

ISSN: 2231-5381 http://www.ijettjournal.org Page 4348

A Hybrid Method For Enhancement Of MRI
Knee Images
U.Pavan Kumar
#1
, P.Padmaja
*2


Assistant Professor,
Department of ECE,
Sri Vidyanikethan Engineering College, Tirupati, India.

Abstract Pre-processing is the basic step to reconstruct
the image with some useful feature. This technique is
essential for the enhancement of knee images which
increases the efficiency of the subsequent tasks of the knee
recognition system. In this paper, an hybrid approach is
proposed which is a combination of contrast stretching
and adaptive thresholding that simultaneously adjusts the
intensity level of knee images using boundaries is
developed. The validation of proposed system is carried
out based on the defined parameter matrices. The
experimental results shows that the proposed method
proves efficient when compared to other traditional
methods.
Keywords Image enhancement, Histogram equalization,
Contrast stretching, intensity adjustment, Adaptive
Thresholding.

I. INTRODUCTION
The application of digital image processing techniques for the
problemof automatic knee classification began two decades
ago and it has since been proceeding in earnest. In industrial
this technology found some of its earlier applications to be
widely used. Image sequence processing techniques are used
to solve problems in Medical field. In recent times computer
vision methodologies and pattern recognition techniques have
been applied towards automated procedures of knee
recognition [2,3]. It helps in the development of an automatic
method that can correctly discriminate and recognize knee
shapes of different species. These applications require high
accuracy for the estimation of dynamic changes. Automatic
classification and recognition system for knee is essential and
useful since it can facilitate fast learning of MRI knee [4,7].
Knee images normally changes to blurred images by the
presence of noise, low or high contrast both in the edge area
and image area. Preprocessing an image include, removal of
noise, edge or boundary enhancement, automatic edge
detection, automatic contrast adjustment and segmentation. As
multiple noise damages the quality of nature images,
improved enhancement technique is required for improving
the contrast stretch in knee images. Mostly the images in
natural surface posses low contrast as the features have a low
range of reflectance in any waveband which effects the further
development process. Generally the method includes the
following steps: preprocessing, feature extraction,
classification and recognition. However, blurness and
presence of unwanted noise on knee images result in false
classification. Thus image pre-processing such as image
enhancement techniques are highly needed to improve the
quality of knee image.
Image enhancement is basically improving the interpretability
or perception of information in images for human viewers and
providing `better' input for other automated image processing
techniques [1,5]. During this process, one or more attributes of
the image are modified. The choice of attributes and the way
they are modified are specific to a given task. Image
enhancement techniques are used to highlight certain features
(i) increasing the contrast, (ii) changing the brightness level of
an image so that the image looks better. In this paper, a hybrid
approach [12] that simultaneously removes noise, adjusts
contrast and enhances boundaries is presented.
The paper is organized as follows, Section 2 of the paper
introduces the concept of traditional enhancement techniques
which improves the pixel intensities. Section 3 explains the
working of contrast stretching and adaptive threshold method.
The proposed hybrid model for improving the pixel intensities
and improve the quality of blur is explained in section 4.
Section 5 discusses the experimentation, their performance
measurement and results. Finally, the conclusions and
references are discussed in section 6.
II. ENHANCEMENT TECHNIQUES
Image enhancement processes consist of a collection
of techniques that seek to improve the visual appearance of an
image or to convert the image to a formbetter suited for
analysis by a human or machine [6]. Meanwhile, the term
image enhancement is mean as the improvement of an image
appearance by increasing dominance of some features or by
decreasing ambiguity between different regions of the
image[7,13]. Some enhancement techniques are shown in
figure1.
International Journal of Engineering Trends and Technology (IJETT) Volume 4 Issue 10 - Oct 2013

ISSN: 2231-5381 http://www.ijettjournal.org Page 4349



Fig. 1 Different Types of Image Enhancement Techniques.

Contrast stretching is the image enhancement technique that
commonly used for digital images. Till now contrast
stretching process plays an important role in enhancing the
quality and contrast of medical images [10, 11]. This study
proposes 5 techniques for contrast enhancement based on
local contrast, global contrast, partial contrast, bright and dark
contrast.
A. Contrast Stretching Technique
The contrast of an image is the distribution of its dark and
light pixels. A low-contrast image exhibits small differences
between its light and dark pixel values. The histogramof a
low-contrast image is narrow. Since the human eye is
sensitive to contrast rather than absolute pixel intensities, a
perceptually better image could be obtained by stretching the
histogramof an image so that the full dynamic range of the
image is filled.
The basic idea behind contrast stretching [5] is to linearly
increase or decrease the contrast of the given image. This can
be done by specifying the input/output relationship. For
example, observe the following input/output relationship
shown in figure 5 below. In this figure the intensities of the
pixel have been normalized from0(black) to 1(White). Input
image intensity (x-axis) is denoted by r while output image
intensity (y-axis) is denoted bys.



Fig. 2 Pixel Intensities
In this figure 2, small dynamic range input intensity (as
represented by the difference between r2 and r1) is being
mapped to a wider dynamic range at the output image (as
represented by the difference between s2 and s1). Thus, one
can see that the transformation function has stretched the
contrast of the input image. In this manner, one can see that
some of the darker or black pixels are mapped to brighter
pixels.
A few observations that are made fromthe mapping function
[5] are given below:
1. If s1 equals to r1 and s2 equals to r2, then output image will
be exactly identical to the input image. In this case there is no
change in the contrast between the output and input image.
2. If s1 =0, s2 =1, and r1 =r2 then output image will consist
of only black (0) and white (1) pixels. This function is known
as the binarizing function.
3. If r1 >s1 and r2 <s2 (as shown in figure 4), then all pixels
in between r1 and r2 of the input image will be stretched
between the pixels s1 and s2 of the output image. Pixels less
than r1 in the input image will be darker in the output image
and pixels greater than r2 in the output image will appear
brighter in the output image.
4. If r1 <s1 and r2 >s2, then all pixels in between r1 and r2 of
the input image will be compressed in between pixels s1 and
s2 of the output image. Pixels less than r1 (dark pixels) in the
input image will be brighter in the output image and pixels
greater than r2 (bright pixels) in the output image will appear
darker in the output image.
B. Adaptive Threshold Method
Thresholding is called adaptive thresholding when
different thresholds are used for different regions in the image
[6,14]. This may also be known as local or dynamic
thresholding. The local mean m(x, y) and standard deviation
s(x, y) adapt the value of the threshold according to the
contrast in the local neighborhood of the pixel. When there is
high contrast in some region of the image, s(x, y)~R which
results in t(x, y) ~m(x, y). the result is same as that of
Niblacks method. However, the difference comes in when the
contrast in the local neighborhood is quite low. In that case the
threshold t(x, y) goes below the mean value thereby
successfully removing the relatively dark regions of the
background. The parameter k controls the value of the
threshold in the local window such that the higher the value of
k, the lower the threshold fromthe local mean m(x, y).
III. PROPOSED ENHANCEMENT TECHNIQUES FOR
KNEE IMAGES
The proposed knee image enhancement technique consists
of the following 4 steps











Fig. 3 Proposed Enhancement method for knee image
a)The knee images are acquired directly by
digital equipments.

b)The obtained images are saved by .dcm

c)Convert the knee image into grayscale image

d) Finally the proposed technique is processed
towards the grayscale image .
International Journal of Engineering Trends and Technology (IJETT) Volume 4 Issue 10 - Oct 2013

ISSN: 2231-5381 http://www.ijettjournal.org Page 4350

The above figure 3 shows the proposed approach for knee
image enhancement. Contrast stretching is normalization
technique, aims to improve the image through stretching the
range of intensity values. Those intensity values are rescaled
usually through the analysis image histogram. Generally
contrast stretching is employed when the gray level
distribution is narrow, due to poor illumination, lack of
dynamic range in image sensor. The technique aims to adjust
histogram to achieve the higher separation between
foreground and background gray level distribution. However
it is difficult to remove noise when gray levels are similar to
object. So, in contrast stretching the image intensity is
adjusted and the enhanced image is obtained which is noisy
and the details of object in images are not well clearly.
To separate the objects from image the foreground and
background separation is done to extract the objects.
Thresholding is a basic and frequently applied technique for
gray level image separation. In the gray level of regions the
image are distinguishable from the background. The enhanced
image obtained after intensity adjustment can be threshold in
order to obtain selected features of interest from the
background. Threshold is implemented in frequency domain.

IV. EXPERIMENTAL SET UP AND RESULTS

The experiments are conducted using matlab 7.1.
Knee images are taken as benchmark images. To test the
accuracy of the filtering algorithms, four steps are followed.
i) First, an uncorrupted Knee image is taken as input.
ii) Secondly speckle noise and Gaussian noise is added
alternatively to a knee image.
iii) Thirdly, filtering algorithmis applied to noisy image.
iv) Fourth, the performance evaluation is estimated based on
the parameters PSNR, MSE, UQI, Energy .
The reconstruction of an image has the dimensions of 256
pixel intensity. Most of the images used are knee images with
different shapes. Normally the value of PSNR, Energy & UQI
must be high which produces good quality image. Whereas
the MSE and ET value must be low value to act as a good
algorithm.
A. Peak Signal To Noise Ratio
The PSNR is defined in logarithmic scale, in dB. It is
the ratio of peak signal power to noise power. Since the MSE
represents the noise power and the peak signal power, it is
unity in case of normalized image signal. The image metric
PSNR is defined as:

PSNR =10log
10
[
MAX
I
2
MSL
(1)






Table I
PARAMETER EVALUATION USING ENHANCEMENT METHOD

PARAMETER MSE PSNR UQI
HIST 13.4696 42.8749 0.4793
AHIST 4.1386 47.9998 0.889
CS 254.9805 30.1033 0.5267
AT 255 30.1030 -3.2638


The above table 1 shows the parameter evaluation
using enhancement method. The proposed method gives
suitable results on the basis of PSNR, MSE, UQI.
B. Mean Square Error
The MSE is defined as
MSE =
1
mn
I(i,j) K(i,j)
2
(2)
n-1
j=0
m-1
I=0

For two mn monochrome images I and K, one of the images
is considered a noisy approximation of the other.

The MSE value must be low for a better image. The proposed
method gives suitable results by producing low MSE value.

C. UQI

UQI measures image similarity across distortion
types. Distortions in UQI are measured as a combination of
three factors; Loss of correlation, Luminance distortion and
Contrast distortion. Let {xi} and {yi} =1,2,...,N be the original
and the test image signals, respectively. The universal quality
index [] is defined as

UQI =
4
xy
xy
|
x
2
+
y
2
][(x)
2
+(y)
2
]
(3)

Where

X

=
1
N
X
I
N
I=1
,Y

=
1
N
Y
I
N
I=1
,

x
2
=
1
N-1
(x
I
x)
2 N
I=1
,

y
2
=
1
N-1
(y
I
y)
2 N
I=1
,
o
x
=
1
N-1
(x

x)(y

y)
N
=1



The dynamic range of UQI is [-1,1]. The best value 1 is
achieved if and only if yi=xi for all i=1,2,,N. The lowest
value if -1 occurs when yi=2 x xi for all i=1,2,,N.




International Journal of Engineering Trends and Technology (IJETT) Volume 4 Issue 10 - Oct 2013

ISSN: 2231-5381 http://www.ijettjournal.org Page 4351






Original HE





AHE CS






AT PM

Fig. 4 Image results for different Enhancement Methods.


V. CONCLUSION
This paper focused on the preprocessing step of MRI Knee
Images. Knee images normally changes to blurred images by
the presence of noise and low or high contrast both in the edge
area and image area. Preprocessing an image include removal
of noise, edge or boundary enhancement, automatic edge
detection, automatic contrast adjustment and segmentation. As
multiple noise damages the quality of nature images,
improved enhancement technique is required for improving
the contrast stretch in knee images The image enhancement is
an important step discussed. In this paper, an approach that
simultaneously adjusts contrast and enhances boundaries is
presented. Experimental results shows the proposed method
gives suitable results when compared to other traditional
method taken for study.
REFERENCES

[1] M. Sepasian, W. Balachandran and C. Mares, Image Enhancement
for Fingerprint Minutiae-Based Algorithms Using CLAHE, Standard
Deviation Analysis and Sliding Neighborhood, Proceedings of the
World Congress on Engineering and Computer Science 2008 WCECS
2008, October 22 - 24, 2008, San Francisco, USA,
[2] Zhixin Shi , Srirangaraj Setlur , Venu Govindaraju, Digital
Enhancement of PalmLeaf Manuscript Images using Normalization
Techniques, IEEE conference, Computer Vision, Graphics & Image
Processing, 2008, P.687-692.
[3] Manpreet Kaur, J asdeep Kaur, J appreet Kaur, Survey of Contrast
Enhancement Techniques based on HistogramEqualization, (IJ ACSA)
International J ournal of Advanced Computer Science and Applications,
Vol. 2, No. 7, 2011, P.138-141.
[4] David Menotti, Laurent Najman, J acques Facon, and Arnaldo de A.
Arajo, Multi-Histogram Equalization Methods for Contrast
Enhancement and Brightness Preserving, IEEE Transactions on
Consumer Electronics, Vol. 53, No. 3, 2007, P.1186-1193.
[5] R.Sharmila, R. Uma, A New Approach To Image Contrast
Enhancement using Weighted Threshold HistogramEqualization with
Improved Switching Median Filter, International J ournal Of Advanced
Engineering Sciences and Technologies Vol No. 7, No. 2, 2011, P. 206
211.
[6] Tarek A. Mahmoud, Stephen Marshall, Medical Image Enhancement
Using Threshold Decomposition Driven Adaptive Morphological
Filter, 16th European Signal Processing Conference (EUSIPCO 2008),
EURASIP, 2008,
[7] Raman Maini and Himanshu Aggarwal, A Comprehensive Review of
Image Enhancement Techniques, J ournal of Computing, Vol.2, No. 3,
2010, P.8-13.
[8] Zhou Wang, Alan.C. Bovik, A Universal Quality Index, IEEE Signal
Processing Letters,Vol. 20, 2002,P. 1-4.
[9] H.D. Cheng, Huijuan Xu, A novel fuzzy logic approach to contrast
enhancement, Pattern Recognition, Vol. 33, 2000, P.809-819.
[10] J . Najeer Ahamed, V. Rajamani, Design of Hybrid Filter for Denoising
Images Using Fuzzy Network and Edge Detecting, American J ournal
of Scientific Research. No.3,2009, P.5-14.
[11] Sonia Goyal, Seema, Region Based Contrast Limited Adaptive HE
with Additive Gradient for Contrast Enhancement of Medical Images
(MRI), International J ournal of Soft Computing and Engineering
(IJ SCE), Vol.1, No.4, 2011, P.154-157.
[12] Muthu Selvi, Roselin and Dr.Kavitha, A Hybrid Image Enhancement
Technique for Noisy Di DimImages Using Curvelet and Morphology,
International J ournal of Engineering Science and Technology, Vol.
2,No.7, 2010, P. 2997-3002 .
[13] J ayamala K. Patil1 , Raj Kumar, Advances In Image Processing For
Detection Of Plant Diseases, J ournal of Advanced Bioinformatics
Applications and Research, Vol 2, No.2, 2011, P. 135-141.
[14] Mehmet Sezgin, Bulent Sankur, Survey over image thresholding
techniques and quantitative performance evaluation, J ournal of
Electronic Imaging, Vol.13, No.1, 2004, P.146165.