(IJCNS) International Journal of Computer and Network Security, 105
Vol. 2, No. 10, 2010
Analysis of the Performance of Registration of
Mono and Multimodal Brain Images using Fast
Walsh-Hadamard Transform
D.Sasikala1 and R.Neelaveni2
1
Assistant Professor, Department of Computer Science and Engineering,
Bannari Amman Institute of Technology, Sathyamangalam. Tamil Nadu-638401, India.
anjansasikala@gmail.com
2
Assistant Professor, Department of Electrical and Electronics Engineering,
PSG College of Technology, Coimbatore, Tamil Nadu -641004, India.
Abstract: Image registration has great significance in
medicine. Hence numerous techniques were developed. This
paper introduced a method for medical image registration using
Fast Walsh-Hadamard transform and measured their
performance using correlation coefficient and time taken for
registration. This algorithm can be used to register images of
the same or different modalities. Each image bit is lengthened
in terms of Fast Walsh-Hadamard basis functions. Each basis
function is a concept of determining various aspects of local
structure, e.g., horizontal edge, corner, etc. These coefficients
are normalized and used as numerals in a chosen number
system which allows one to form a distinct number for each type
of local structure. The research outcomes show that Fast Walsh
-Hadamard transform accomplished better results than the
conventional Walsh transform in time domain. In addition Fast
Walsh-Hadamard transform established medical image
registration consuming less time and more correlation
coefficient. Since in Medical Images information is very
important than time, hence Correlation Coefficient is used as a
measure. It proves that Fast Walsh Hadamard Transform is
better than Walsh Transform in terms of both the measures.
Keywords: Walsh Transform, Fast Walsh-Hadamard
Transform, Local Structure, Medical Image Registration,
Normalization.
1. Introduction
Digital image processing is building up the basic
machine that could achieve the visual functions of all, that
is, it is an enhancement by improving image quality by
filtering the noise and restoration of images by performing
compression to save storage area and channel capacity
during transmission. It is a rapidly growing field with
emergent applications in many areas of science and
engineering. The main principle of registration is to
combine the sets of data with the deviations if any or with
their similarities into a single data. These sets of data are
obtained by sampling the same scene or object at different
times or from different perspectives, in different co-ordinate
systems. The purpose of registration is to envision a single
data merged with all the details about these sets of data
acquired at different times or perspectives or co-ordinate
systems. Such data is very vital in medicine for doctors to
prepare for surgery. The most familiar and significant
classes of image analysis algorithm with medical
applications [1,3] are image registration and image
segmentation. In Image analysis technique, the same input
gives out fairly detail description of the scene whose image
is being considered. Hence the image analysis algorithms
perform registration as a part of it towards producing the
description. Also in single subject analysis, the statistical
analysis is done either before or after registration. But in
group analyses, the statistical analysis is done after
registration. Though registration transforms the different
sets of data into one co-ordinate system, it’s required for
comparison or integration.
Generally registration is the most difficult tasks among
all in image processing. It is because aligning images to
overlap the common features and differences if any are to be
emphasized for immediate visibility to the naked eye.
There is no general registration [1-17] algorithm that
work reasonably well for all images. A suitable registration
algorithm for the particular problem must be chosen or
developed, as they are adhoc in nature. The algorithms can
be incorporated explicitly or implicitly or even in the form
of various parameters. This step determines the success or
failure of image analysis. The method generally involves
determining a number of corresponding control points in the
images and, from the correspondences, determining a
transformation function that will determine the
correspondence between the remaining points in the images.
This technique may be classified based on four different
aspects given as follows: (i) the feature selection (extracting
features from an image) using their similarity measures and
a correspondence basis, (ii) the transformation function, (iii)
the optimization procedure, and (iv) the model for
processing by interpolation.
Amongst the numerous algorithms developed for image
registration so far, methods based on image intensity values
are particularly excellent as they are simple to automate as
solutions to optimization problems. Pure translations, for
example, can be calculated competently, and universally, as
the maxima of the cross correlation function between two
images [11] [15] [17]. Additional commands such as
rotations, combined with scaling, shears, give rise to
nonlinear functions which must be resolved using iterative
nonlinear optimization methods [11].
In the medical imaging field, image registration is
regularly used to combine the complementary and
synergistic information of images attained from different
106
modalities. A widespread problem when registering image
data is that one does not have direct access to the density
functions of the image intensities. They must be estimated
from the image data. A variety of image registration
techniques have been used for successfully registering
images that are unoccluded. This is generally practiced with
the use of Parzen windows or normalized frequency
histograms [12].
The work proposed in this paper uses Fast Walsh-
Hadamard Transform (FWHT) [18, 19] for image
registration. The coefficients obtained are normalized to
determine a unique number which in turn represents the
digits in a particular range. The experiments conducted on
clinical images show that proposed algorithm performed
well than the conventional Walsh Transform(WT) method
in medical image registration. In addition, this paper
provides a comparative analysis of Fast Walsh-Hadamard
transform and Walsh transform in Medical image
registration in terms of correlation coefficient and time
taken for registration.
The remainder of the paper is ordered as follows.
Section 2 provides an overview on the related work for
image registration. Section 3 explains Walsh transform in
image registration. Section 4 describes the proposed
approach for image registration using Fast Walsh-Hadamard
Transform. Section 5 illustrates the experimental results to
prove the efficiency of the proposed approach in image
registration in terms of correlation coefficient and time
taken for registration and Section 6 concludes the paper
with a discussion.
2. Related Works
This section of paper provides a quick look on the
relevant research work in image registration.
An automatic scheme using global optimization
technique for retinal image registration was put forth by
Matsopoulos et al. in [1]. A robust approach that estimates
the affine transformation parameters necessary to register
any two digital images misaligned due to rotation, scale,
shear, and translation was proposed by Wolberg and Zokai
in [2]. Zhu described an approach by cross-entropy
optimization in [3]. Jan Kybic and Michael Unser together
put forth an approach for fast elastic multidimensional
intensity-based image registration with a parametric model
of the deformation in [4]. Bentoutou et al. in [5] offered an
automatic image registration for applications in remote
sensing. A novel approach that addresses the range image
registration problem for views having low overlap and
which may include substantial noise for image registration
was described by Silva et al. in [6]. Matungka et al.
proposed an approach that involved Adaptive Polar
Transform (APT) for Image registration in [7, 10]. A
feature-based, fully non supervised methodology dedicated
to the fast registration of medical images was described by
Khaissidi et al. in [8]. Wei Pan et al. in [9] proposed a
technique for image registration using Fractional Fourier
Transform (FFT).
3. Walsh Transform
The Walsh, Haar [13], etc are examples of orthogonal
transforms. The coefficients of such an extension point
(IJCNS) International Journal of Computer and Network Security,
Vol. 2, No. 10, 2010
toward the effectiveness of the occurrence of the analogous
structure at the particular position. If these coefficients are
normalized by the dc coefficient of the expansion, i.e., the
local average gray value of the image, then they measure
purely the local structure independent of modality. Walsh
basis functions correspond to local structure, in the form of
positive or negative going horizontal or vertical edge, corner
of a certain type, etc. In addition, registration schemes based
on wavelet coefficient matching do not present a general
mechanism of combining the matching results across
different scales.
Suppose if there are two images I1 and I2, in which I1 is
assumed to represent the reference image whereas I2
represents an image that has to be deformed to match I1.
First, we consider around each pixel, excluding border
pixels, a 3X3 neighborhood and compute from it, the nine
Walsh coefficients (3X3 WT of a 3X3 image patch). If ‘f’ is
the input image, the matrix of coefficients ‘g’ computed for
it using equation (1),
g = (W −1 ) T . fW −1 (1)
Matrix contains the coefficients of the expansion of the
image, in terms of the basis images formed by taking the
vector outer products of the rows of matrix W and its inverse
W-1. These basis images are shown in Fig. 1(a). These
coefficients are denoted by a00, a01, a02, a10, a11, a12, a20, a21,
a22, and in a matrix form as shown in Fig. 1(b). These
coefficients take the value in the range [0, 9]. Moreover
normalization given by equation (2) makes the method
robust to global levels of change of illumination.
αij = aij / a00 (2)
However, the information having dense features and
rigid body transformation allows for plenty of redundancy in
the system and makes it robust to noise and bad matches of
individual pixels which effectively represent lack of local
information. One may construct a unique number out of
eight numbers if one uses these numbers as the digits of the
unique number. The number of levels depends on the
number system adopted. If one decide to stick with the
decimal system, and then the normalized coefficients are
quantized so that they take integer values in the range [0, 9].
(a). WTs basis images for a 3X3 images
a0 a0 a0
0 1 2
a1 a1 a1
0 1 2
a2 a2 a2
0 1 2
(b). Nine coefficients in matrix form
Figure 1. Walsh Transformation
In Figure 1(a) the coefficients along the first row and the
first column are of equal importance, as they measure the
presence of a vertical or a horizontal edge, respectively. The
 (IJCNS) International Journal of Computer and Network Security, 107
Vol. 2, No. 10, 2010

remaining four coefficients measure the presence of anumber. This unique number can then be used as feature for
corner. image registration. The implementation of FWHT readily
The following ordering of coefficients are used in images, reduces the time consumption for medical image registration
Ordering IA α01, α 10, α 20, α 02, α 11, α 21, α 12, α 22 when comparing the same with conventional WT technique for
Ordering IB α 10, α 01, α 02, α 20, α 11, α 12, α 21, α 22 image registration.
Ordering IIA α 22, α 21, α 12, α 11, α 02, α 20, α 10, α 01
Ordering IIB α 22, α 12, α 21, α 11, α 20, α 02, α 01, α 10 5. Experimental Result
The performance of the FWHT is better than the WT in terms A series of experiments is performed using medical
of Correlation Coefficient(CC) and Time taken for registration images. The tests are performed using different images of
of mono and multimodal image registration. different sizes. A set of CT and MR medical images which
depict the head of the same patient is considered. The
The drawbacks of WT were found to be as follows: original size of these images is given as pixels. In order to
(i) Errors are present in the final registration stage. remove the background parts and the head outline, the
(ii) Consumes more CPU time for registration as lot of original images are cropped, creating sub-images of
calculations are involved. This is the major drawback when different dimension pixels. The algorithms are evaluated by
compared to FWHT. determining the CC and Time taken for registration.
The CC is a statistical measure of how well trends in
The advantages of FWHT were found to be as follows: the predicted values follow trends in past actual values. It is
(i) More reliable as produces least error results in the final a measure of how well the predicted values from a forecast
registration stage when compared to WT. model “fit” with the real-life-data. As the strength of the
(ii)Consumes very less CPU time for registration as calculations relationship between the predicted values and actual values
are performed using divide and conquer method. This is the increases, so does the CC. Thus higher the CC the better it
major advantage when compared to WT. is.
(iii)The performance of the FWHT is better than the WT in Correlation Coefficient
terms of CC for monomodal and multimodal image registration.
The Computed Tomography (CT) or Magnetic Resonance
(MR) images represent monomodal images and CT-CT, CT-MR,
and MR-MR images represent real multimodal pairs and the
successful registration shows that FWHT produce accurate
results while the measures correlation coefficient and time taken
for registration are considered in a diversity of image sets,
without any tuning in the preprocessing step.
4. Proposed Approach

4.1 Fast Walsh Hadamard Transform

A fast transform algorithm can be considered as a sparse
factorization of the transform matrix, and refer to each factor as (i)Correlation Coefficient and Time taken for registration
a stage. The proposed algorithms have a regular interconnection for Monomodal images:
pattern between stages, and consequently, the inputs and outputs For the evaluation of the algorithm, MR T2-Registered
for each stage are addressed from or to the same positions, and images are used.
the factors of the decomposition, the stages, have the property of (a)MRI T2-Registered –Sagittal Image 400 x 419 - 88.8kB.
being equal between them. The 2X2 Hadamard matrix is defined
as H2 by equation (3) as
1 1 
H2 =   (3) A set of
1 − 1
Figure 2. MRI T2-Registered –Sagittal Image 400 x 419 -
radix-R factorizations in terms of identical sparse matrices can 88.8kB Using FWHT
be rapidly obtained from the FWHT property that relates the
matrix H with its inverse and is given in equation (4), The results of WT and FWHT are obtained. Figure
HR n = R n ( HR n ) −1 (4) 3.shows the pictorial outputs from the WT that are different from
n Figure 2 and outputs from the FWHT is same as Figure 2.
Where HR = radix-R Walsh Hadamard transform;
Rn = radix-R factorizations;
n = input element;
The FWHT is utilized to obtain the local structure of the
images. This basis function can be effectively used to obtain the
digital numbers in the sense of coefficients [18] [19]. If these
coefficients are normalized by the dc coefficient of the
expansion, i.e., the local average gray value of the image, then
they measure purely the local structure independent of modality.
These numbers are then normalized to obtain the unique
108 (IJCNS) International Journal of Computer and Network Security,
Vol. 2, No. 10, 2010
Image for S.No 2
(ii)Correlation Coefficient and Time taken for registration
for Multimodal images:
(i) Sagittal 840 x 754 - 69k - jpg CT & Sagittal 500 x 500 -
72k - jpg MRI – WT
Image for S.No 4

a) Registered Image obtained using WT

Image for S.No 5

b) Difference in images obtained using WT

Figure 3. MRI T2-Registered –Sagittal Image 400 x 419 - Figure 6. Images obtained using WT
88.8kB using WT
(ii) Sagittal 840 x 754 - 69k - jpg CT & Sagittal 500 x 500 -
72k - jpg MRI – FWHT
Table 1.Represents results of WT & FWHT using CC.
S. X in Y in Angle in CC after CC after
No mm mm degrees registration registration
for WT for FWHT
1 4 -10 9 0.8342 0.8343
2 -12 -7 13 0.8459 0.8464
a) Registered Image obtained using FWHT
3 5 -7 5 0.0416 0.8864
4 -14 -15 2 0.8933 0.8934
5 -8 -7 1 0.2542 0.9426

1 b) Difference in images obtained using FWHT

0.9
0.8 Figure 7. Images obtained using FWHT
0.7
0.6
WT
CC

0.5
0.4
FWHT
(iii) Sagittal 500 x 500 - 72k - jpg MRI & Sagittal 840 x 754 -
0.3
0.2 69k - jpg CT - WT
0.1
0
1 2 3 4 5
Ima ges

Figure 4. Comparison of WT & FWHT using CC.

Table 2.Represents Time consumption for Image Registration a) Registered Image obtained using WT
using WT & FWHT
S X in Y in Angle in Elapsed Elapsed
No mm mm degrees Time in Time in
seconds seconds
for WT for
FWHT b) Difference in images obtained using WT
1 4 -10 9 138.297 6.829 Figure 8. Images obtained using WT
2 -12 -7 13 135.922 7.328
3 5 -7 5 133.406 6.328 (iv) Sagittal 500 x 500 - 72k - jpg MRI & Sagittal 840 x 754 -
4 -14 -15 2 136.000 6.750
69k - jpg CT - FWHT
5 -8 -7 1 141.125 6.125

160
140
120
Time in Secs

100
WT
80
60
FW HT
a) Registered Image obtained using FWHT
40
20
0
1 2 3 4 5
I ma ge s

Figure 5. Comparison of WT & FWHT in terms of time.

From the above analysis it proves that the performance of b) Difference in images obtained using FWHT
the FWHT is better than the WT in terms of time and Figure 9. Images obtained using FWHT
Correlation Coefficient.
 (IJCNS) International Journal of Computer and Network Security, 109
Vol. 2, No. 10, 2010
(v) Axial 320 x 420 - 40k - jpgCT Figure 13. Images obtained using FWHT
Axial 553 x 642 - 38k – jpg-MRI - WT
(ix) Sagittal 432 x 427 - 41k – jpg- CT
Frontal 400 x 400 - 18k – jpg- MRI –WT

a) Registered Image obtained using WT

a) Registered Image obtained using WT

b) Difference in images obtained using WT

Figure 10. Images obtained using WT
b) Difference in images obtained using WT
(vi) Axial 320 x 420 - 40k - jpgCT Figure 14. Images obtained using WT
Axial 553 x 642 - 38k – jpg-MRI - FWHT
(x) Sagittal 432 x 427 - 41k – jpg- CT
Frontal 400 x 400 - 18k – jpg- MRI –FWHT

a) Registered Image obtained using FWHT

a) Registered Image obtained using FWHT

b) Difference in images obtained using FWHT

Figure 11. Images obtained using FWHT
b) Difference in images obtained using FWHT
(vii) Axial 553 x 642 - 38k – jpg-MRI Figure 15. Images obtained using FWHT
Axial 320 x 420 - 40k - jpgCT –WT
(xi) Frontal 400 x 400 - 18k – jpg- MRI
Sagittal 432 x 427 - 41k – jpg- CT- WT

a) Registered Image obtained using WT

a) Registered Image obtained using WT

b) Difference in images obtained using WT

b) Difference in images obtained using WT Figure 16. Images obtained using WT
Figure 12. Images obtained using WT (xii) Frontal 400 x 400 - 18k – jpg- MRI
(viii) Axial 553 x 642 - 38k – jpg-MRI Sagittal 432 x 427 - 41k – jpg- CT- FWHT
Axial 320 x 420 - 40k - jpgCT – FWHT

a) Registered Image obtained using FWHT

a) Registered Image obtained using FWHT

b) Difference in images obtained using FWHT b) Difference in images obtained using FWHT
Figure 17. Images obtained using FWHT
110 (IJCNS) International Journal of Computer and Network Security,
Vol. 2, No. 10, 2010

The FWHT is better than the WT in terms of Time and

Table 3: Represents results for WT & FWHT using CC Correlation Coefficient as their values are maximized for
both monomodal and multimodal images.
S. CC after CC after registration
No registration for Fast Walsh 6. Conclusion
for Walsh Hadamard Transform
Transform This paper proposes the application of FWHT for
1 -0.0459 0.5330 monomodal and multimodal medical image registration.
2 0.1838 0.4429 This transform reduces the time consumption in image
3 0.0130 0.6752 registration. Therefore it proves to be a better approach for
4 -0.0498 0.7483
5 -0.0557 0.5452
medical image registration than any other conventional WT.
6 -0.0837 0.5638 The coefficients obtained using this transform are then
normalized to obtain the unique number. The unique
0.8 number represents the local structure of an image. Moreover
0.6 this unique number indicates the feature of an image for
0.4 WT
image registration. The experimental results revealed the
CC
0.2 FWHT fact that the application of FWHT performs well in image
0 registration. The future work concentrates on Mutual
-0.2 1 2 3 4 5 6 Information and its application for image registration with
Images the analysis of its performance of monomodal and
multimodal brain images using FWHT. Also to further
Figure 18. Comparison of WT & FWHT using CC. improve the results by using some other transforms that use
Table 4.Represents Time consumption for Image Registration correlation coefficients.
using WT & FWHT
References
S. Elapsed Time Elapsed Time in
[1] George K. Matsopoulos, Nicolaos A. Mouravliansky,
No in Secs after Secs after Konstantinos K. Delibasis, and Konstantina S. Nikita,
registration registration “Automatic Retinal Image Registration Scheme Using
for Walsh for Fast Walsh Global Optimization Techniques,” IEEE Transactions
Transform Hadamard on Information Technology in Biomedicine, vol. 3, no.
Transform
1 647.359000 39.843000 1, pp. 47-60, 1999.
2 196.437000 9.516000 [2] G. Wolberg, and S. Zokai, “Robust image registration
3 41.015000 4.531000 using log-polar transform,” Proceedings of
4 318.922000 18.297000 International Conference on Image Processing, vol. 1,
5 114.438000 8.047000 pp. 493-496, 2000.
6 125.140000 7.453000 [3] Yang-Ming Zhu, “Volume Image Registration by
Cross-Entropy Optimization,” IEEE Transactions on
In this work, it is observed from the results that FWHT
Medical Imaging, vol. 21, no. 2, pp. 174-180, 2002.
gives better results when compared to WT in terms of Time
[4] Jan Kybic, and Michael Unser, “Fast Parametric Elastic
and CC.
Image Registration,” IEEE Transactions on Image
The results of WT and FWHT are obtained and Figures
Processing, vol. 12, no. 11, pp. 1427-1442, 2003.
show the pictorial outputs from the WT that is different
[5] Y. Bentoutou, N. Taleb, K. Kpalma, and J. Ronsin, “An
from outputs from the FWHT. The registration of these
Automatic Image Registration for Applications in
images shows that there is loss of information in pixels
Remote Sensing,” IEEE Transactions on Geosciences
while registering images using WT due to less CC. But the
and Remote Sensing, vol. 43, no. 9, pp. 2127-2137,
rest of the images have the outputs for FWHT.
2005.
800 [6] Luciano Silva, Olga R. P. Bellon, and Kim L. Boyer,
600 “Precision Range Image Registration Using a Robust
400
WT Surface Interpenetration Measure and Enhanced
FWHT
200
Genetic Algorithms,” IEEE Transactions on Pattern
0
Analysis and Machine Intelligence, vol. 27, no. 5, pp.
Time in 1 2 3 4 5 6 762-776, 2005.
Seconds
Images [7] R. Matungka, Y. F. Zheng, and R. L. Ewing, “Image
registration using Adaptive Polar Transform,” 15th
Figure 19.Comparison of WT & FWHT in terms of time IEEE International Conference on Image Processing,
The loss of information in pixels of the FWHT is very ICIP 2008, pp. 2416-2419, 2008.
less when compared to WT this is due to more CC of FWHT [8] G. Khaissidi, H. Tairi and A. Aarab, “A fast medical
than WT. Hence FWHT is better when compared to WT for image registration using feature points,” ICGST-GVIP
image registration. Also registration time of FWHT is best Journal, vol. 9, no. 3, 2009.
when compared to WT. [9] Wei Pan, Kaihuai Qin, and Yao Chen, “An Adaptable-
Multilayer Fractional Fourier Transform Approach for
Image Registration,” IEEE Transactions on Pattern
 (IJCNS) International Journal of Computer and Network Security, 111
Vol. 2, No. 10, 2010

Analysis and Machine Intelligence, vol. 31, no. 3, pp. R. Neelaveni is presently working as a
400-413, 2009. Assistant Professor, Department of EEE,
[10] R. Matungka, Y. F. Zheng, and R. L. Ewing, “Image PSG College of Technology, Coimbatore.
registration using Adaptive Polar Transform,” IEEE She has a Bachelor’s degree in ECE, a
Master’s degree in Applied Electronics and
Transactions on Image Processing, vol. 18, no. 10, pp.
PhD in Biomedical Instrumentation. She has
2340-2354, 2009. 19 years of teaching experience and has
[11] Jr. Dennis M. Healy, and Gustavo K. Rohde, “Fast guided many UG and PG projects. Her
Global Image Registration using Random Projections,” research and teaching interests includes
4th IEEE International Symposium on Biomedical Applied Electronics, Analog VLSI, Computer Networks, and
Imaging: From Nano to Macro, ISBI 2007, pp. 476- Biomedical Engineering. She is a Life member of Indian Society
479, 2007. for Technical Education (ISTE). She has published several
[12] C. Fookes and A. Maeder, “Quadrature-Based Image research papers in national and international Journals and
Registration Method using Mutual Information,” IEEE Conferences.
International Symposium on Biomedical Imaging: Nano
to Macro, vol. 1, pp. 728-731, 2004.
[13] M. Petrou and P. Bosdogianni, Image Processing—The
Fundamentals. New York: Wiley, 1999.
[14] Pere Marti-Puig, “A Family of Fast Walsh Hadamard
Algorithms With Identical Sparse Matrix
Factorization,” IEEE Transactions on Signal Processing
Letters, vol. 13, no. 11, pp. 672-675, 2006.
[15] J. L. Moigne, W. J. Campbell, and R. F. Cromp, “An
automated parallel image registration technique based
on correlation of wavelet features,” IEEE Trans. Geosci.
Remote Sens., vol. 40, no. 8, pp. 1849–1864, Aug.
2002.
[16] J. P. W. Pluim, J. A. Maintz, and M. A. Viergever,
“Image registration by maximization of combined
mutual information and gradient information,” IEEE
Trans. Med. Imag., vol. 19, no. 8, pp. 899–814, Aug.
2000.
[17] Z. Zhang, J. Zhang, M. Liao, and L. Zhang, “Automatic
registration of multi-source imagery based on global
image matching,” Photogramm. Eng. Remote Sens.,
vol. 66, no. 5, pp. 625–629, May 2000.
[18] M. Bossert, E. M. Gabidulin, and P. Lusina, “Space-
time codes based on Hadamard matrices proceedings,”
in Proc. IEEE Int. Symp. Information Theory, Jun. 25–
30, 2000, p. 283.
[19] L. Ping, W. K. Leung, and K. Y. Wu, “Low-rate turbo-
Hadamard codes,” IEEE Trans. Inf. Theory, vol. 49, no.
12, pp. 3213–3224, Dec. 2003.

Author’s Profile
D.Sasikala is presently working as Assistant
Professor, Department of CSE, Bannari
Amman Institute of Technology,
Sathyamangalam. She received B.E.( CSE)
from Coimbatore Institute of Technology,
Coimbatore and M.E. (CSE) from
Manonmaniam Sundaranar University,
Tirunelveli. She is now pursuing Phd in Image
Processing. She has 11.5 years of teaching experience and has
guided several UG and PG projects. She is a life member of ISTE.
Her areas of interests are Image Processing, System Software,
Artificial Intelligence, Compiler Design.