FEATURE EXTRACTION OF AN IMAGE BY USING ADAPTIVE FILTERING AND
MORPOLOGICAL SEGMENTATION
Anil kumar.M1 Fahimuddin
shaik2 Abdul Rahim.B3
1.
Post
graduate student, Dept. of E.C.E, A.I.T.S, Rajampet, AP.
2.
Assistant
professor, Dept. of E.C.E AITS, Rajampet, A.P.
3.
H.O.D,
Dept. of E.C.E AITS, Rajampet, A.P.
ABSTRACT:
For enhancing an image various
enhancement schemes are used which includes gray scale manipulation, filtering
and Histogram Equalization, Where Histogram equalization is one of the well
known image enhancement technique. It became a popular technique for contrast
enhancement because it is simple and effective. The basic idea of Histogram
Equalization method is to remap the gray levels of an image.
Here using morphological segmentation
we can get the segmented image. Morphological reconstruction is used to segment
the image.
Comparative analysis of different
enhancement and segmentation will be carried out. This comparison will be done
on the basis of subjective and objective parameters. Subjective parameter is
visual quality and objective parameters are Area, Perimeter, Min and Max intensity, Avg Voxel Intensity, Std Dev of
Intensity, Eccentricity, Coefficient of skewness, Coefficient of Kurtosis,
Median intensity, Mode intensity.
Keywords - Histogram Equalization, Segmentation, Morphological Reconstruction .
I. INTRODUCTION:
Medical
image enhancement technologies have become popular since
advanced medical equipments were used in the
medical field. Image processing can be defined as a
process that transforms a degraded image to another image of better quality in
order to facilitate its posterior interpretation. Image processing techniques
can be then applied in order to facilitate the interpretation of images by
further using computer vision algorithms. Therefore, in this context, image
processing can be considered to be a preprocessing stage for computer vision [3].
The process involved in making an image more interpretable for particular
application is image enhancement.
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. The principal objective of image enhancement is to modify
attributes of an image to make it more suitable for a given task and a specific
observer. 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. Moreover, observer-specific factors, such as the experience,
will introduce a great deal of subjectivity into the choice of image
enhancement methods. There exist many techniques that can enhance a digital
image without spoiling it. The enhancement methods can broadly be divided in to
the following two categories:
1. Spatial Domain Methods
2. Frequency Domain Methods
In spatial domain techniques
[5], we directly deal with the image pixels. The pixel values are manipulated
to achieve desired enhancement. In frequency domain methods, the image is first
transferred in to frequency domain. It means that, the Fourier Transform of the
image is computed first. All the enhancement operations are performed on the
Fourier transform of the image and then the Inverse Fourier transform is
performed to get the resultant image. These enhancement operations are performed
in order to modify the image brightness, contrast or the distribution of the
grey levels. As a consequence the pixel value (intensities) of the output image
will be modified according to the transformation function applied on the input
values.
Morphological
image processing is a
collection of non-linear operations related to the shape or morphology of
features in an image. Morphological operations rely only on the relative
ordering of pixel values, not on their numerical values, and therefore are especially
suited to the processing of binary images. Morphological operations can also be
applied to grayscale images such that their light transfer functions are
unknown and therefore their absolute pixel values are of no or minor interest.
In this paper we will have Literature survey
of image enhancement and image segmentation, proposed method, experimental
results, statistical analysis of results; finally we will end with our
conclusion.
II. BACKGROUND:
Before going to details of the
proposed method, we present some background topics of image enhancement which
include CLAHE and Image segmentation.
A. Image Enhancement:
Image enhancement [1] is the
simplest and most appealing areas of digital image processing. Basically, the main
idea behind enhancement techniques [3] is to bring out detail that is obscured,
or simply to highlight certain features of interest in an image. We have
proposed the following CLAHE, gamma correction techniques to enhance the
medical images.
B. Contrast
Limited Adaptive Histogram Equalization (CLAHE) :
Contrast Limited Adaptive Histogram Equalization 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, which is rarely used in practice. In
the case of contrast limited histogram equalization, the contrast limiting
procedure has to be applied for each neighborhood from which a transformation
function is derived. Contrast limited histogram equalization was developed to
prevent the over amplification of noise, which is a problem in adaptive
histogram equalization.
C. Image segmentation:
Segmentation [7] subdivides
an image into its constituent regions or objects. The level to which the subdivision
is carried depends. That is, segmentation should stop when the objects of
interest in an application have been isolated .Segmentation of nontrivial
images is one of the most difficult tasks in image processing. Segmentation
accuracy determines the eventual success or failure of computerized analysis
procedures. For this reason, considerable care should be taken to improve the probability
of rugged segmentation. In some situations, such as industrial inspections
applications, at least some measure of control over the environment is possible
in times. The experienced image processing system designer invariably pays
considerable attention to such opportunities. In other applications, such as
autonomous target acquisition, the system designers have no control of the
environment. Then the usual approach is to focus on selecting the types of
sensors most likely to enhance the objects of interest while diminishing the
contribution of irrelevant image details. A good example is the use of infrared
imaging by military to detect objects with strong heat signatures, such as
equipment and troops in motion.
Image
segmentation algorithms generally are based on one of two basic properties of
intensity values: discontinuity and similarity. In the first category, the approach
is to partition an image based an abrupt change in intensity, such as edges in
an image. The principal approaches in the second category are based on
partitioning an image into regions that are similar according to set of
predefined criteria. Thresholding, region growing, and region splitting and
merging are methods in this category. There are several techniques for
detecting the three basic types of gray-level discontinuities in an digital image:
point, line and edge detection.
D. Morphological Reconstruction:
Reconstruction [8] is a morphological transformation involving two images
and a structuring element (instead of a single image and structuring element).
One image, the marker, is the starting point for the transformation. The other
image, the mask, constrains the transformation. The structuring element used
defines connectivity. In this section we use 8-connectivity (the default),
which implies that B in the following discussion is a 3x3 matrix of 1s, with
the center defined at coordinates (2, 2).
In this section we deal with binary images;
If G is the
mask and
F is the
marker, the reconstruction of G from F,
denoted
(F), is defned by the following
iterative procedure:
1.
Initialize
h1 to be the marker image, F.
2.
Create
the structuring element: B = ones (3).
3.
Repeat:
until
4.
(F)
=
Marker F must be a subset of G: F
E. Opening and Closing
by Reconstruction:
In morphological opening, erosion typically
removes small objects, and the sub-sequent dilation tends to restore the shape
of the objects that remain. However, the accuracy of this restoration depends
on the similarity between the shapes and the structuring element. The method
discussed in this section, opening by reconstruction, restores the original
shapes of the objects that remain after erosion. The opening by reconstruction
of an image G using structuring element B, is defined as
(b) opening the image
(d) closing the image
(e) Closing by Reconstruction
III. PROPOSED
WORK:
Figure . 1 : Block
Diagram of Proposed work
The proposed method
is used to enhance and segment the medical image. We use the Contrast limited adaptive Histogram Equalization
(CLAHE) to enhance the medical images, and Morphological
techniques for segment the Enhanced medical image.
IV.
EXPERIMENTAL RESULTS :
Here we can
use some medical image modalities like MRI, CT scan, ECG etc. For example here
we are using an image of Talc embolism in a 26-year-old woman. The patient had
a 4-year history of heroin and methadone abuse which is Thin-section (1.5-mm
collimation) CT scan (mediastinal window) obtained at the subcarinal level
shows coalescent areas of increased attenuation (progressive massive fibrosis)
posteriorly in both lungs. Note also the areas of high attenuation within the
masses (arrow), a finding that suggests talc deposition.
Figure 2.(a,b,c,d) shows experimental results. Figs. 2.a
is original image, Figs.
2.b is enhanced image via CLAHE, Figs.2.c is Segmented Image by Reconstruction and Fig.2.d.
is superimposed on original image.
Figure.2(a)
Original CT Image
Figure.2(b) Enhanced Image by CLAHE
Figure.2(c) Segmented Image by Reconstruction
Figure.2(d) superimposed
on original image
V.
STATISTICAL ANALYSIS :
The performance of the
proposed method was rigorously evaluated using quality metrics like Area, Perimeter, Min and Max intensity,
Avg Voxel Intensity, Std Dev of Intensity, Eccentricity, Coefficient of
skewness, Coefficient of Kurtosis, Median intensity, Mode intensity.
Table1: Quality Assessment metrics for original image
Area
|
4975
|
Perimeter
|
325.0554
|
Min Intensity
|
45
|
Max Intensity
|
245
|
Avg Voxel Intensity
|
212.1672
|
Std Dev of Intensity
|
25.5892
|
Eccentricity
|
0.7844
|
Coefficient
of skewness
|
-1.3619
|
Coefficient of kurtosis
|
5.0113
|
Median Intensity
|
224
|
Mode Intensity
|
223
|
Table2: Quality Assessment metrics for segmented image.
Area
|
4317
|
Perimeter
|
314.6178
|
Min Intensity
|
0
|
Max Intensity
|
255
|
Avg Voxel Intensity
|
238.1828
|
Std Dev of Intensity
|
46.5425
|
Eccentricity
|
0.7933
|
Coefficient of skewness
|
-3.0504
|
Coefficient of kurtosis
|
11.338
|
Median Intensity
|
255
|
Mode Intensity
|
255
|
By observing Area, Perimeter, Min and Max intensity, Avg Voxel
Intensity, Std Dev of Intensity, Eccentricity, Coefficient of skewness,
Coefficient of Kurtosis, Median intensity, Mode intensity the changes
occurred after processing is easily revealed.
VI.
CONCLUSION :
In this paper we proposed image enhancement
method and image segmentation using Morphological techniques.
By observing all of the above quality
assessment metrics for “CT of Lungs” image, we can conclude that CLAHE
enhancement method is having less noise and having more contrast. The enhanced
image is segmented by using Morphological techniques. By the segmentation we
can get the segmented image and it is superimposed on the original image, to
get the perfect outlined structure of the talc deposition in the image.
REFERENCES:
1.
Rajesh Garang ,Bhavna Mittal, Sheetal Garg “Histogram
Equalization Techniques For Image Enhancement” ,IJECT vol.
2,Issue1,march2011.
2.
H. Hassanpour* and S. Asadi Amiri , “Image Quality Enhancement Using Pixel-Wise Gamma Correction Via Svm Classifier’’ September
14, 2011.
3.
K.
Ikeuchi; C. Schnörr; M. Hebert; C. Schmid,"International Journal of Computer Vision"ISSN:
0920-5691,Journal no. 11263.
4.
Raman
Maini and Himanshu Aggarwal,"A Comprehensive Review of Image Enhancement
Techniques " JOURNAL OF COMPUTING, VOLUME 2, ISSUE 3, MARCH 2010, ISSN
2151-9617
5.
P.Nithyanandam,
T.Ravichandran, N.M.Santron &
E.Priyadarshini ,"A Spatial
Domain Image Steganography Technique Based on Matrix Embedding and Huffman
Encoding" International Journal of Computer Science and Security
(IJCSS), Volume (5) : Issue (5) : 2011.
6.
Etta
D.Pisano,Shuquan Zong, Bradley M.Hemminger,Marla DeLuca,R.Eugene
Johnston,KeithMuller,M.Patricia Braeuning and Stephen M.Pizer,"Contrast Limited Adaptive Histogram
Equalization image processing to improve the detection of simulated
spiculations in dense mammograms"Journal of Digital Imaging November
1998, Volume 11, Issue 4, pp 193-200
7.
Biplab
Banerjee, Tanusree Bhattacharjee &
Nirmalya Chowdhury "Color Image Segmentation Technique Using “Natural
Grouping” of Pixels"International Journal of Image Processing(IJIP),
Volume(4): Issue(4).
8.
David
Valencia and Antonio Plaza,"efficient
implementation of morphological opening and closing by reconstruction on
multi-core parallel systems",IEEE Xplore 2009,Page 1-4, E-ISBN :
978-1-4244-4687-2
10. www.mipav.cit.nih.gov
M.Anilkumar born in Nellore, A.P, India in 1989. He received B.Tech Degree in Electronics &Communication Engg. From J.N.T.University, Anantapur, India. Presently he is pursuing M.Tech (DECS) from Annamacharya Institute of Technology & Sciences, Rajampet, A.P., India.His research interests include Biomedical engineering, Image Processing and Communication Systems.
B Abdul Rahim born in Guntakal, A.P, India in 1969. He received the
B.E in Electronics & Communication Engineering from Gulbarga University in
1990. M.Tech (Digital Systems &Computer Electronics) from Jawaharlal Nehru
Technological University in 2004. He is currently working towards Ph.D. degree
from JNT University, Anantapur. He has
published papers in international journals and conferences. He is a member of
professional bodies like IEEE,EIE, ISTE, IACSIT, IAENG etc. His research interests include Fault Tolerant
Systems, Embedded Systems and parallel processing. He achieved “Best Teacher
Award” for his services by Lions Club, Rajampet.