ABSTRACT: of the brightness scale may be utilized.

ABSTRACT: This paper attempts to undertake thestudy of two types of the contrast enhancement. Contrast enhancement procedurescan be grouped into two broad categories. Namely, linear and non-linear.

Inlinear enhancement techniques, the mathematical implementation is on the basisof uniform slope, while in non-linear method, the enhancement is done using avarying slope. In linear enhancement techniques, the commonly used the min-maxstretch, percentile stretch and piecewise, while non-linear techniques arehistogram equalization, adaptive equalization, log arithmetic contrastenhancement.Keywords:linear contrast enhancement, non-linear contrast enhancementI.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

                 INTRODUCTION         The operation of contrast enhancement bringsabout a change in the original values so that the full range of the brightnessscale may be utilized. This helps in increasing the distinguishability betweenobjects and their background. It is observed that contrast stretch is asubjective in nature and hence often a trial and error procedure. One of themost important quality factors in satellite images comes from its contrast.Contrast is created by the difference in luminance reflected from two adjacentsurfaces.

In visual perception, contrast is determined by the difference in thecolor and brightness of an object with other objects. The contrast enhancementhas been two types, They are,·       Linear contrast enhancement·       Non-linear contrast enhancementI.                 LINEARCONTRAST ENHANCEMENT       The type referred a contrast stretching,linearly expands the original digital values of the remotely sensed data into anew distribution.

By expanding the original input values of the image, thetotal image of sensitivity of the display device can be utilized. Linearcontrast enhancement also makes subtle variations within the data obvious.these  types of  enhancement are best applied to remotelysensed images with Gaussian or non-Gaussian histograms, meaning, all thebrightness values fall within a narrow range of histogram and only mode is apparent.There are three methods of linear contrast enhancement.a.   Min-Maxlinear contrast enhancement            This technique is simplest enhancement. Whenusing the minimum-maximum linear contrast the original minimum and maximumvalues of the data are assigned a newly specified set of values that utilizethe full range of available brightness values. The min-max contrast stretch orenhancement greatly improves the contrast of most of the original brightness values,but, there is loss contrast of the extreme high and low ends.

This method isapplying with respect to image application type,G(x,y)=(f(f,y)-min)/max-min). a.     Percentile linear contrastenhancement        Many times, it is observed that the tails ofinput histogram are long.

   This virtually leads to no improvement inthe image quality even after min-max stretch has been performed. This can becarried out on a percentage basis, where 1% or %5 of the data on both the endsof cut off. A standard deviation from the mean is often used to push the tailsof the histogram beyond the original minimum and maximum values. b.    Piece-wise linear contrastenhancement     The above two techniques of linear enhancements are suitable when thehistogram of the input image is unimodel in nature. It has only one the peak.

However, this may not be normal case, and histogram is multi-model in natureindicating that there are more than one object in the image. A piece-wiselinear contrast occupying difference gray scale ranges can be enhanced.I.                 NONLINEAR CONTRAST ENHANCEMENT  Nonlinear contrast enhancement often involveshistogram equalization through the use of an algorithm .the nonlinear contraststretch method has one major disadvantage.

Each value in the input images canhave several values in the output images, so that objects in the original scenelose their correct relative brightness value. There are three methods ofnonlinear contrast enhancement. .Histogram equalization          Histogram equalization is widelyused for contrast Manipulation in digital image processing due it is simple implementation.It requires minimum information from the analyst. In this enhancement, theoriginal histogram is readjusted to produce a uniform population density ofpixels along the horizontal grey value axis. The technique ensures that theentropy of the images an indicator of the image information is increased.

Inthis method, first of all the target number of pixel in each brightness levelof the equalized histogram is calculated by the dividing the total number ofpixels in the images with the total number of brightness levels is designed. b.    Adaptiveequalization                 Adaptive histogram equalization where you candivide the image into several rectangular domains, compute an equalizinghistogram and modify levels so that they match across boundaries. Depending onthe nature of the nonlinear uniformly of the image. Adaptive histogramequalization uses the histogram equalization mapping function supported over acertain size of local window to determine each enhanced value. It acts of localoperation.b.   Logarithmiccontrast enhancement           This transformation is a veryuseful nonlinear contrast enhancement.

Here the output pixel brightness valueswill be generated from input pixel brightness values following some logarithmicexpressions         BVout=alog (BVin)+bThis transformation only highlightsthen features lying in the darker region of the histogram. Lists same of theadvantages and important characteristics of logarithmic contrast enhancement,as given below.       Ø Itenhances low contrast edges, thus making low contrast details more distinctØ Itprovides a contrast to signal to noise ratio.Ø Itusually provides a more equal distribution of grey values.Ø Ittransforms multiplicative noise into additive noise. I.

                 CONCLUSION                         In this paper, studies take the contrastenhancement and its types. The first contrast enhancement is linear contrast enhancementanother enhancement is nonlinear contrast enhancement .in first enhancementfrom the linear contrast enhancement studies are explained and experimentsmax-min methods, percentile contrast method and piecewise contrast method thebest method in linear contrast enhancement. And second case of enhancementstudy is explained and experiments are carried out for different techniques inhistogram equalization method, adaptive equalization and logarithmic contrastenhancement is the best study is remote processing techniques in the nonlinearcontrast enhancement.