IMAGE FUSION BY WAVELET METHOD
Under the esteemed guidance of
D.Ravikrishna Reddy M.Tech, (P.hD)
Presented by
B.RAJESH BABU 07X91A0429
Y.MAHENDRA 08X95A0404
V.VENKATA RAO 07X91A0457
R.SUDHEER 07X91A0443
OBJECTIVE:
The fusion image is the process of combining two or
more images into a single image. Wavelet transform
fusion is the most common form of transform image
fusion.
Image fusion improves geometric corrections and
sharpness the image. It also replace the data.
Digital image processing:
An image may be defined as a two dimensional function f(x,y).where x,y
are the spatial coordinates
The amplitude of f at pair of coordinates (x,y) is called intensity or gray
level of image
A gray scale image is a function I(x,y) of two spatial coordinates of the
image plane
I(x,y) f the is the intensity of the image at point (x , y)
FOURIER AND WAVELET ANALYSIS OF IMAGES:
Fourier analysis:
Fourier analysis is a mathematical technique for transforming our view of
the signal from time based to frequencey based.
It is a serious draw back, in transforming to the frequency domain time
information lost.
Short-Time Fourier Analysis:
Dennis Gabor (1946) adapted the Fourier transform to analyze only a small
section of the signal at a time—a technique called windowing the signal.
Gabor’s adaptation, called the Short-Time Fourier Transform (STFT), maps
a signal into a two-dimensional function of time and frequency
Wavelet Analysis:
A wavelet is a waveform of effectively limited duration that has an average
value of zero.
Sinusoids do not have limited duration — they extend from minus to plus
infinity. And where sinusoids are smooth and predictable, wavelets tend to
be irregular and asymmetric.
Wavelet Analysis Representation:
Wavelet analysis allows the use of long time intervals where we want more
precise low-frequency information, and shorter regions where we want
high-frequency information.
Fig. Time, Frequency, STFT & Wavelet Domain Representations
The Continuous Wavelet Transform:
which is the sum over all time of the signal f(t) multiplied by a complex
exponential.
What’s continuous about the continuous wavelet transform:
The CWT is also continuous in terms of shifting during computation, the
analyzing wavelet is shifted smoothly over the full domain of the analyzed
function.
Discrete Wavelet Transform:
An efficient way to implement this scheme using filters was developed in
1988 by Mallat.
Calculating wavelet coefficients at every possible scale is a fair amount of
work, and it generates an awful lot of data.
For many signals, the low-frequency content is the most important
part. It is what gives the signal its identity.
One-Stage Filtering:
Fig.1 One stage filtering Fig.2 Example For One Stage Filtering
Multiple-Level Decomposition:
The decomposition process can be iterated, with successive approximations
being decomposed in turn, so that one signal is broken down into many lower
resolution components. This is called the wavelet decomposition tree.
Fig. Multilevel Decomposition Fig. Wavelet Decomposition Tree
Wavelet Reconstruction:
Discrete wavelet transform can be used to analyze or decompose signals and
images.
Up sampling is the process of lengthening a signal component by inserting
zeros between samples:
Fig. Samples Representation
Reconstruction Filters:
Up sampling is the process of lengthening a signal component by inserting
zeros between samples.
Multi-step Decomposition and Reconstruction:
IMAGE FUSION:
Objectives of Image Fusion Schemes:
Related Research Fields of Image Fusion:
Computer Vision
Automatic object detection
Image processing
Robotics
Fusion Rules
• Input images need to be combined to form a new set of coefficients to be
used for backward transform.
Implementing wavelet transform:
Wavelet transform based image fusion involves three steps; forward transform,
coefficient combination and backward transform.
Different wavelets used in the image fusion:
Inputs are
1.multispectral image
2.panchromatic image
Fig. Fusion of the wavelet transforms of two images.
Wavelet Decomposition:
Images are treated as two-dimensional signals, they change horizontally and
vertically, and thus 2D wavelet analysis must be used for images.
Decomposition of Saturn Image to level 1:
Result:
Panchromatic image Multispectral image Fused image using orthogonal
wavelet
Conclusion:
Fusion image contains the useful information of the original
image and the detailed information is greatly improved judging by
visual apperception. The fusion result of WT-based fusion method
loses more spectrum information.
Relatively, the final image of our fusion algorithm is more
natural and it is more advantageous to further image segmentation
and recognition.
ANY
?????
THANK YOU
