This full-text paper was peer-reviewed and accepted to be presented at the IEEE ICCSP 2015 conference.
Fuzzy type Image Fusion using hybrid DCT FFT based Laplacian Pyramid Transform Rajesh Kumar Kakerda, Mahendra Kumar, Garima Mathur, R P Yadav, Jagdish Prasad Maheshwari reducing the increasing volume of information while at the Abstract-
This
fusion technique (DCT)
paper
using
presents
hybrid
a
fuzzy
discrete
type
Cosine
transform
Fast Fourier Transform (FFT) based
pyramid. It is concluded that
fusion
with
image
laplacian
higher
level
of
pyramid provides better fusion quality. This technique can be
same time extracting all the useful information from the source images.
Multi-sensor
data
often
presents
complementary
information, so image fusion provides an effective method to enable comparison and analysis of data. The aim of image
used for fusion of fuzzy images as well as multi model image
fusion, apart from reducing the amount of data, is to create
fusion.
new
The proposed
implement This
is
and
paper
algorithm is very
could also
be
used
provided
for
simple,
real
easy
to
time applications.
comparatively
studied between
proposed and previous existing technique and validation of the proposed algorithm as Peak Signal to Noise Ratio (PSNR), Root Mean Square Error (RMSE) and Correlation (CORR) .
Index Terms-Correlation, Fuzzy type image, Hybrid DCT
images that are more suitable for the purposes of
human/machine perception, and for further image-processing tasks
such
as
segmentation,
object
detection
or
target
recognition in applications such as remote sensing and medical imaging. For example, visible-band and infrared images may be fused to aid pilots landing aircraft in poor visibility [3, 5,7]. Finally, the performance of the image fusion scheme is
FFT, PSNR, RMSE.
evaluated as tradeoffs between true image and fused image. In previous I.
O
INTRODUCTION
vital role in defence as well as in civilian applications
because diversity of sensors available and these working in spectral
bands.
Image
fusion,
where
multiple
registered images are combined together to increase the information content, is a promising research area. Numerous image fusion algorithms such as multi-resolution [1, 2 ], multi scale
[3]
and
statistical
signal
when apply
fuzzy type images, the
performance criterion is poor, so this paper proposed a novel
FF late, multi sensor data fusion is found to play a
different
techniques
processing
[4,5,6]
based
hybrid
military applications for which they were developed. The result of the use of these techniques is a increase of the amount of data available. Image fusion provides an effective way of
Rajesh Kumar Kakerda is M.Tech Scholar with the Department of Electronics & Communication Engineering, JEC, Kukas Jaipur, India (corresponding author e-mail:
[email protected]). Mahendra Kumar is Faculty with Department of Electronics & Communication Engineering, University College of Engineering, RTU, Kota, India. (corresponding author e-mail:
[email protected]). Garima Mathur is HOD with the Department of Electronics & Communication Engineering, JEC, Kukas Jaipur, India (e-mail:
[email protected]). R P Yadav is Professor with the Department of Electronics & Communication Engineering, MNIT, Jaipur, India (e-mail: rp
[email protected]). Jagdish Prasad Maheshwari is M.Tech Scholar with the Department of Electronics & Communication Engineering, JEC, Kukas Jaipur, India (corresponding author e-mail:
[email protected]).
Laplacian
pyramid
transform
discussed
Proposed
DCT-FFT
based
laplacian
pyramid
transform. Different Fusion Performance evaluation criterion presented in section III. Results and comparatively study of techniques is described in section IV and conclusions are presented in Sections V. II.
The developments in the field of sensing technologies multi as remote sensing, medical imaging, machine vision and the
based
remainder of the paper is organized as follows: In Section II,
techniques are presented and evaluated. sensor systems have become a reality in a various fields such
DCT-FFT
technique which provide fused image with better quality. The
PROPOSED DCT-FFT BASED LAPLACIAN PYRAMID TRANSFORM
Laplacian pyramid:
The Laplacian pyramid was first introduced as a model for binocular
fusion
in
human stereo vision
[3],
where the
implementation used a Laplacian pyramid and a maximum selection
rule
at
each
point
of
the
pyramid
transform.
Essentially, the procedure involves a set of band-pass copies of an image is referred to as the Laplacian pyramid due to its similarity to a Laplacian operator. Each level of the Laplacian pyramid is recursively constructed from its lower level by applying the following four basic steps: blurring ( low-pass filtering);sub-sampling (reduce size); interpolation (expand); and differencing ( to subtract two images pixel by pixel). In the Laplacian
pyramid,
the
lowest
level
constructed from the original image [5].
978-1-4799-8081-9/15/$31.00 © 2015 IEEE
1049
of
the
pyramid
is
This full-text paper was peer-reviewed and accepted to be presented at the IEEE ICCSP 2015 conference.
Fast Fourier Transform (FFT):
The FFT is applied on spatial domain image to obtain FFT coefficients [4]. The features that are extracted from FFT coefficients are real part, imaginary part, magnitude value and Discrete Fourier Transform ( DFT),
E(gk)
R(gk_l)
phase angle. The FFT computation is fast compared to since the number of
multiplications required to compute N-point DFT are less i.e., 2 only ( N/2 ) [log2N] in FFT as against N in DFT.
gk-I
The features of DWT are obtained from approximation band only. The features of FFT are computed using the magnitude values. Discrete Cosine Transform (DCT)
Discrete cosine transform ( DCT) is an important transform
R(gL)
in image processing. Large DCT coefficients are concentrated in the low frequency region; hence, it is known to have excellent energy compactness properties. The 2D discrete cosine transform Z
of an image or 2D signal
(u, v)
z(x, y)
of
size MxN is defined as [5]:
Z(u, v)
=
a(u)a(v) cos
Where
a(v)
a(u)
=
R(go)
� � z(x,y)COS (7r(2X+l)U) 2M
M-IN-I
=
(7r(2Y+l)V) O: