Tr 00069 by dbpublications

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017

Image Maximization Using Multi Spectral Image Fusion Technique Ms. SAVITHA, PG Scholar, VTU University Karnataka Email ID:savib87@gmail.com

ABSTRACT (PCA) and wavelet transform (WT) image This paper reports a detailed study of a set of

image

fusion algorithms

for

its

implementation. The paper explains the theory and implementation of the effective image

fusion

experimental

algorithm

results.

and

Based

the

research and development of some image quality metrics, the fusion algorithm is evaluated. The report is an image fusion algorithm that evaluates and implements image quality metrics that are used to evaluate the implementation.

have

been

applied

hyperspectral and low spatial resolution satellite images with high spatial and low spectral resolution images to obtain a fusion

graph

with

apply and render the results of image fusion algorithms. The subjective (visual) and objective evaluation of the fusion image has been carried out to assess the success of the method. The objective evaluation methods include correlation coefficient (CC), root mean square error (RMSE),

relative

global

dimension

synthesis error (ERGAS) The results show that the PCA method performs better on the top of the spectral

In this study, two different image fusion techniques

fusion MATLAB is used to build the GUto

increased

spatial

resolution Like, while keeping spectral

information, and is less successful in increasing the spatial resolution. The WT is performed after the IHS transformation to improve the spatial resolution and is performed with respect to the preservation of the spectral information after the PCA and WT methods.

information as much as possible. These techniques are raw component analysis

I. INTRODUCTION Image processing techniques focus primarily on enhancing the quality of

IDL - International Digital Library

1|P a g e

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017 images or a set of images and deriving maximum information from them. Image fusion is a technique for generating highquality images from a set of available images.example indicates that it will appear relatively dark.

II. IMAGE PROCESSING Description:A visual representation of the (object or scene or person or abstract) produced on the surface. The data representing the two-dimensional scene. The eye can sense the spectral response mode because it is a true multispectral sensor (ie, it is sensed in more than one place in the spectrum). Although the actual

An image is an artifact, such as a twodimensional image, having a look that is similar to some subject, usually a physical object or person.

function of the eye is quite complex, it actually does have three independent types

1) Sample and quantize: Make moderate

of detectors that can be effectively

readings at evenly spaced locations in both

considered to be responsive to red, green

the x and y directions Visualized by

and blue wavelength regions. These are the

placing an regularly spaced grid over the

primary colors of the additive, and the

analog image.

eyes respond to the sensation of the other colors to produce other colors

2) Quantize Intensity: quantize the sampled values of intensity to arrive at a signal that is discrete in both position and amplitude. 3) Encoding: translate data to binary form. The process of analog to digital signal translation is completed by encoding the

IDL - International Digital Library

2|P a g e

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017 quantized values into a binary chain.

location. 5. Note that the three primary colors

Gray Scale Image Once a grayscale image has been obtained

are red, green, and blue. They are

and digitized, it is stored as a two-

stated as primary because any color

dimensional array in computer storage.

of light consists of a mixture of frequencies contained in the three "primary" color ranges an example of quantizing consider

a color image computer

imaging

systems that utilize 24 bit color. 6. For 24 bit color each of the three primary color

concentration

allowed one byte of storage per pixel for a total of three bytes per

Fig.: Gray Scale Image

pixel. Color Image

7. Each

1. To digitize a grayscale image, we

color

has

permitted

numerical range from 0 to 255, for

look at the overall concentration

example 0=no red, 255=all red.

level of the sensed light and record

8. The combinations that can be made with 256 levels for each of the

as a function of position. 2. To digitize a color image the

three primary colors amounts to

concentration of each of the three

over 16 million distinct colors

primary colors must be noticeable

ranging from white (R,G,B) =

of the incoming light.

(255,255,255) to black (R,G,B) =

3. One way to carry out this is to filter

(0,0,0).

the light sensed by the sensor so

9. Majority of computers store color

that it lies within the wavelength

digital image information in three

range of a definite color.

dimensional arrays. The first two

4. We can detect the intensity of that

indexes in this array specify the

specific color for that definite

row and column of the pixel and the third index specifies the color

IDL - International Digital Library

3|P a g e

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017 "plane" where 1 is red, 2 is green,

IV. DIM ARRAY FOR 24 BIT

and 3 is blue.

III.

COLOR

Block Diagram of System Design

Fig: 3D array for 24 bit color Software Requirements The images obtained from the different resources have spatial addiction but due to their different spectral quality, they also exhibit difference in information content. The information contained in panchromatic images

depends

the

multispectral

Software 

fusion of this dissimilar data contributes to

 

of images with dissimilar temporal, spectral

Language

Software Packages

Hardware Requirements 

Processor

INTEL Core 2 Duo 32 bit 

Output device

Color

monitor 

Network hardware

Network Interface Card

and spatial resolution IDL - International Digital Library

MATLAB 7.0 and above

location are obtained at different periods of times. This provides us with a large volume

Operating System

MATLAB programming language

the understanding of the objects observed. For many applications, images of the same

the

Windows XP/07/Vista

characteristics of the illuminated surface object as well as on the signal itself. The

for

implementation and testing

reflectivity of the object illuminated by sun light. SAR image intensities depend on the

necessities

4|P a g e

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017 

RAM



Input device

1 GB

detail subband are then combined and the fusion

image

reconstructed

performing inverse wavelet transform.

Keyboard and mouse

Since the coefficient distribution in the

V. Principal

Components

Analysis (Pca)

detail subband is averaged to zero, the fusion result does not change the radiance

PCA is a general-purpose statistical

of the original multi-spectral image. The

technique that converts multivariable

simplest method is based on the choice of

data with associated variables into

higher

multivariable

literature presents various other methods.

data

with

irrelevant

value

coefficients,

but

the

variables. These new variables are obtained as a linear combination of the original variables. PCA has been widely used in image coding, image data compression, image enhancement and image fusion.

Satellite Image Fusion Enhancement – GUI Design

VI. Wavelet Transform (WT) The wavelet coefficients from the MS approximation subband and the PAN IDL - International Digital Library

5|P a g e

Figure– Image enhancement GUI design Copyright@IDL-2017

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017

Figure:–

Image

enhancement

Programmed GUI

Fig: Image enhancement Resultant Output using PCA method

Flow

chart

for

PCA

based

IMAGE fusion Figure :– Image enhancement working GUI design

Figure:– Image enhancement Working Environment

IDL - International Digital Library

6|P a g e

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017 

Whether each identifiable function is a controllable entity or should be busted down into smaller parts.



The structure diagram is also used to associate elements that contain running streams or threads.



It is usually developed as a hierarchical

map,

but

other

representations are allowed. 

The representation must describe the subdivision of the configuration system as a subsystem

Flow chart for Image fusion based WT The structured flow chart provides an overall strategy for structured projects. It details the development of each module in detail design and coding. These specific application modules and their designs are shown in the figure. Structure description 

The range and difficulty of the system.



Number of readily identifiable functions and unitss within each function.

IDL - International Digital Library

7|P a g e

IDL - International Digital Library Of Technology & Research Volume 1, Issue 5, May 2017

Available at: www.dbpublications.org

International e-Journal For Technology And Research-2017 http://dx.doi.org/10.1016/S15662535(01)00036-7. 2. J. Hill et al., “A local correlation approach for the fusion of remote sensing data with different

spatial

resolution

forestry

applications,” in Proc. of Int. Archives of Photogrammetry and Remote Sensing, Vol. 32, Part

7-4-3

W6,

pp.

167–174,

ISPRS,

Valladolid, Spain (1999). 3. S. Klonus and M. Ehlers, “Image fusion using the Ehlers spectral characteristics preservation algorithm,” GIsci. Rem. Sens. 44(2),

93–116

(2007),

http://dx.doi.org/10.2747/1548- 1603.44.2.93. 4. B. Aiazzi et al., “Context-driven fusion of high

spatial

and

spectral

resolution

imagesbased on oversampled multiresolution analysis,” IEEE Trans. Geosci. Rem. Sens.

CONCLUSION Finally, from the above analysis and comparison, it can be concluded that the improved IHS algorithm can preserve the

40(10),

2300–2312

(2002),

http://dx.doi.org/10.1109/TGRS.2002.803623. 5. L. Alparone et al., “Comparison of pansharpening algorithms: outcome of the

spectral characteristics of the source multi-

2006 GRS-S data-fusion contest,” IEEE Trans.

spectral image and the high spatial

Geosci. Rem. Sens. 45(10), 3012–3021 (2007),

resolution of the source panchromatic

http:// dx.doi.org/10.1109/TGRS.2007.904923.

image, which is suitable for the fusion of

6. B. Aiazzi et al., “A comparison between

IRS P5 and P6 images. In PC and standard

global and context-adaptive pansharpening of

REFERENCES

multispectral images,” IEEE Geosci.Rem.

1. T. M. Tu et al., “A new look at IHS-like

Sens.

image fusion methods,” Inform. Fusion 2(3),

http://dx.doi.org/

177–186

IDL - International Digital Library

(2001),

8|P a g e

Lett.6(2),

302–306

(2009),

10.1109/LGRS.2008.2012003