DIGITAL IMAGE ENHANCEMENT WITH FUZZY INFERENCE SYSTEM

Presented by Devendra SB Co-ordinator Mr. Chandrashekar M V

B.E., M.Tech., M.I.S.T.E

Guided by Mr.Keerthi Prasad G

Asst. Prof., Dept of IS&E
B.E.,M,Tech

Asst. Prof., Dept of IS&E

ABSTRACT

Present day application requires various version kinds of images and

pictures as sources of information for interpretation and analysis. Whenever an image is converted from one form to another, such as, digitizing, scanning, transmitting, storing, etc. Some form of degradation occurs at the output. Hence, the output image has to undergo a process called image enhancement. Image enhancement technique is basically improving the perception of information in images for human viewers and providing 'better' input for other automated image processing techniques.

Contd

This thesis presents a new approach for image enhancement with fuzzy inference system. These techniques can manage the vagueness and ambiguity efficiently.

Fuzzy logic is a powerful tool to represent and process human knowledge in form of fuzzy if-then rules.
Compared to other filtering techniques, fuzzy filter gives the better performance and is able to represent knowledge in a comprehensible way.

CONTENTS
Introduction Existing system Proposed system Architecture Advantages Application area Conclusion Future Scope References

INTRODUCTION
Image can be contaminated with different types of reasons. noise, for different

For example, noise can occur because of the circumstances of recording with electronic cameras, dust in front of the lens, because of the circumstances of transmission or storage, copying, scanning, etc.. Image enhancement is to improve the interpretability or perception of information in images for human viewers, or to provide `better' input for other automated image processing techniques.

 Image Enhancement (IE) transforms images to provide better representation of the subtle details. It is an indispensable tool for researchers in a wide variety of fields including medical imaging, art studies, forensics and atmospheric sciences.

EXISTING SYSTEM

Image enhancement techniques are divided into four broad categories: * * * * Spatial Domain Method. Frequency Domain Method. Fuzzy Image Enhancement. Fuzzy Rule Based Image enhancement

Contd

Spatial domain methods

Direct manipulation of image pixels

Some of the techniques of spatial domain method Point operations Histogram equalization and matching Applications of histogram-based enhancement

Contd.
Frequency domain method Manipulation of Fourier transform or wavelet transform of an image

Frequency domain techniques

Unsharp masking Homomorphic filtering

FUZZY IMAGE ENHANCEMENT

Fuzzy image enhancement is based on gray level mapping into a fuzzy plane, using a membership function.
The aim is to generate an image of higher contrast than the original image by giving a larger weight to the gray levels that are closer to the mean gray. An image f of size M x N and L gray levels can be considered as an array of fuzzy singletons, each having a value of membership .

INPUT IMAGE

The membership function characterizes

a suitable property of image like darkness, edginess, textural property etc..

IMAGE FUZZIFICATION

The basic principles of fuzzy image enhancement scheme are illustrated in fig

MEMBERSHIP

below.
DE-FUZZIFICATION

ENHANCED IMAGE

FUZZY RULE -BASED FOR IMAGE ENHANCEMENT

If we interpret the image features as linguistic variables, then we can use fuzzy if-then rules to segment the image into different regions.
A simple fuzzy segmentation rule may seem as follows:
IF the pixel is dark AND Its neighborhood is also dark AND homogeneous THEN it belongs to the background.

Disadvantages of Spatial domain method Sometimes it shifts image boundaries during sharpening Only manipulates the pixel

Disadvantages of Frequency domain method Not a good method for contrast enhancement Only manipulates the frequency
Disadvantages of Fuzzy image enhancement and Rule based enhancement These methods are caused by the vagueness and ambiguity.

FUZZY FILTERING (PROPOSED ALGORITHM)

This system proposes a new filtering algorithm for image enhancement method based on fuzzy inference system. The process of fuzzy inference involves all of the pieces that are described in the previous sections: membership functions and ifthen rules. Fuzzy filters provide promising result in image processing tasks that cope with some drawbacks of classical methods. Fuzzy filter is capable of dealing with vague and uncertain information

FUZZY INFERENCE SYSTEM (FIS)

Fuzzy inference is the process of formulating the mapping from a given
input to an output using fuzzy logic, the mapping then provides a basis from which decisions can be made. The process of fuzzy interface involves all of the pieces that are membership functions, If-Then Rules etc

ARCHITECTURE

Read the image

Add noise to the image Pre-processing task Normalization of pixel values

Calculate the size of the original image

Convert it into the the gray scale if it is RGB image

Apply fuzzy interface engineering

Perform morphological operation on image

Compare the enhanced image with original image

WORKING MODEL

1.Read the image. I = imread('eight.tif')

2. Add noise to it. J = imnoise(I,' salt & pepper');

3. After adding noise we need to calculate the size of the original image.
To find the size of the image simply type size(img);

4.Convert it into the gray scale if it is RGB image.

Convert an RGB image to a grayscale image. I = imread('board.tif'); J = rgb2gray(I);

5. Perform morphological operations on image. BW = imread('circles.png');

BW2 = bwmorph(BW,'remove');

6. Apply fuzzy inference engineering. anfis and the ANFIS Editor GUI apply fuzzy inference techniques to data modelling. The shape of the membership functions depends on parameters, and changing these parameters change the shape of the membership function.

7. Normalization of pixel values. Get component position in pixels Syntax position = getpixelposition(handle) position = getpixelposition(handle,recursive) position = getpixelposition(handle) gets the position, in pixel units, of the component with handle handle. position = getpixelposition(handle,recursive) gets the position as above. If recursive is true, the returned position is relative to the parent figure of handle.
h1 = uicontrol('Style','PushButton','Units','Position',[.1 .1 .5 .2]); pos1 = getpixelposition(h1)
pos1 = 18.6000 12.6000 88.0000 pos1 = getpixelposition(h1,true) pos1 = 79.6000 53.6000 88.0000 23.2000
23.2000

8. Compare enhanced image with original image.

EXPERIMENTAL RESULT

The output of this proposed method (system) is shown in figure below that the enhanced image is better than the original image.

ADVANTAGES

1. Fuzzy techniques are powerful tools for knowledge representation and processing.

2. Fuzzy techniques can manage the vagueness and ambiguity efficiently.

APPLICATION AREAS
1. In forensics IE is used for identification, evidence gathering and crime scene investigation are enhanced to help in identification of culprits and protection of victims.

2. In atmospheric sciences IE is used to reduce the effects of haze, fog and mist weather for meteorological observations.

APPLICATION AREAS

3. It helps in detecting shape and structure of remote objects in environment sensing. Satellite images undergo image restoration and enhancement to remove noise.

4. For real time sharpening and contrast enhancement several cameras have inbuilt IE functions.

CONCLUSION

The fuzzy interface system is powerful tool for formulation of expert system in a comprehension way. The proposed technique used fuzzy if-then rules are a sophisticated bridge between human knowledge on the one side of the numerical framework of the computers on the other side. The proposed technique is able to overcome the drawbacks of spatial and frequency domain. The proposed technique is able to improve the contrast of the image

FUTURE OF TECHNOLOGY

In the future the existing systems can be modified

by fuzzy set theory application.

Modification of fuzzy rules can produce better results. Neuro-fuzzy can be used to enhance the images

REFERENCES
[1] Rao, D.H., Panduranga, P.P. A survey on image enhancement techniques: classical spatial filter, neural network, cellular neural network, and fuzzy filter KLS Gogte Inst. of Technol., Belgaum, PP: 2821 2826, 2006. [2] Hanmandlu, M., Jha, D. An optimal fuzzy system for color image enhancement Volume: 15, PP: 2956 2966,2006. [3] Li. H, Yang H.S. Fast and reliable image enhancement using fuzzy relaxation technique Systems, Man and Cybernetics, Volume:19, PP: 1276-1281,1989. [4] Gopalan Sasi, Nair S Madhu and Sebastian Souriar Approximation Studies on Image Enhancement Using Fuzzy Technique International Journal of Advanced Science and Technology, Vol. 10, 2009.

[5] Sattar, F., Tay, D.B.H. Enhancement of document images using multiresolution and fuzzy 56 Digital Image Enhancement with Fuzzy Interface System Copyright 2012 MECS I.J. Information Technology and Computer Science, 2012, 10, 51-56 logic techniques Signal Processing Letters, Volume: 6, PP: 249 252, 1999.

[6] Bin Mansoor, A., Khan, Z., Khan, A. An application of fuzzy morphology for enhancement of aerial images Advances in Space Technologies, PP: 143 - 148, 2008. [7] Fa-Shen Leou, Kuei-Ann Wen, Image enhancement based on the visual model using the concept of fuzzy set Circuits and Systems, Volume: 5, Page(s): 2581 - 2584, 1992. [8] Fuzzy Logic Toolbox Users Guide 19952011 The MathWorks, Inc. [9] Chowdhury, M.M.H., Islam, M.E.; Begum, N.; Bhuiyan, M.A.-A. digital image enhancement with fuzzy rule based filtering PP:1-3,2007. [10] Russo, F., Ramponi, G. a fuzzy operator for the enhancement of blurred and noisy images Volume: 4, PP: 1169 1174,1995. [11] Yan Solihin, Leedham, C.G.; Sagar, V.K. A fuzzy based handwriting extraction technique for handwritten document pre-processing TENCON '96. Proceedings. Volume: 2, Page(s): 927 - 932, 1996.

Thank You