Scribd Logo
Upload

Welcome to Scribd!

  • 27 views

    Image Classification Using Edge Detection Withe Fuzzy Logic: Par: Chettouh Safieddine Sohbi Salem Hammoudi Mabrouk

    Uploaded by

    Damri Bachir
    Edge detection is performed using fuzzy logic to classify images. Training involves detecting edges in an image using fuzzy rules, extracting features, and storing in a database along with the class. Testing detects edges in an input image, extracts features, compares to the training database, and identifies the matching class. The algorithm provides concise image classification by transforming images to edge representations using fuzzy logic rules for feature extraction and comparison to stored training data.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Image Classification Using Edge Detection Withe Fuzzy Logic: Par: Chettouh Safieddine Sohbi Salem Hammoudi Mabrouk

    Uploaded by

    Damri Bachir
    27 views16 pages
    Edge detection is performed using fuzzy logic to classify images. Training involves detecting edges in an image using fuzzy rules, extracting features, and storing in a database along with the class. Testing detects edges in an input image, extracts features, compares to the training database, and identifies the matching class. The algorithm provides concise image classification by transforming images to edge representations using fuzzy logic rules for feature extraction and comparison to stored training data.

    Original Title

    Treatment des image

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Edge detection is performed using fuzzy logic to classify images. Training involves detecting edges in an image using fuzzy rules, extracting features, and storing in a database along with the class. Testing detects edges in an input image, extracts features, compares to the training database, and identifies the matching class. The algorithm provides concise image classification by transforming images to edge representations using fuzzy logic rules for feature extraction and comparison to stored training data.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    27 views16 pages

    Image Classification Using Edge Detection Withe Fuzzy Logic: Par: Chettouh Safieddine Sohbi Salem Hammoudi Mabrouk

    Uploaded by

    Damri Bachir
    Edge detection is performed using fuzzy logic to classify images. Training involves detecting edges in an image using fuzzy rules, extracting features, and storing in a database along with the class. Testing detects edges in an input image, extracts features, compares to the training database, and identifies the matching class. The algorithm provides concise image classification by transforming images to edge representations using fuzzy logic rules for feature extraction and comparison to stored training data.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 16

    Image classification using edge

    Detection withe fuzzy logic

    par:
    Chettouh safieddine
    Sohbi salem
    Hammoudi mabrouk

    ALLPPT.com _ Free PowerPoint Templates, Diagrams and Charts


    1. INTRODUCTION
    an edge is defined as an abrupt variation in pixel intensity within an image
    while the process of detecting outlines of an object and boundaries between
    objects and the background in the image is known as edge detection. Edge
    detection is a very important tool widely used in many computer vision and
    image processing applications. Earlier edge detection methods, such as
    Sobel, Prewitt, Kirsch and Robert are based on the calculation of the
    intensity gradient magnitude at each image pixel. In these algorithms,
    the gradient value is compared to the threshold value and a pixel location is
    classified as an edge if the value of the gradient is higher than a threshold.
    Gradient-based edge detectors have a major drawback of being very
    sensitive to noise.
    In order to counter noise problems Canny proposed an approach to edge
    detection in which the image is convolved with the first order derivatives of
    Gaussian filter for smoothing in the local gradient direction followed by
    edge detection and thresholding [Canny 1986]. Extensions of Canny edge
    detector can be found in [Laligant et al. 1994].
    I. INTRODUCTION
    Edge detection represents an extremely important step facilitating
    higher-level image analysis and therefore remains an area of active research,
    with new approaches continually being developed. Recent examples include
    edge detectors using fuzzy logic, neural networks, or wavelets [Sun and
    Sclabassi 1995, Law et al. 1996, Bezdek et al. 1996, Wang et al. 2005].
    Comparison of edge detection approaches and an assessment of their per-
    formance may be found in [Demigny et al. 1995, Ramesh and Haralick 1994].
    In this paper, fuzzy logic based approach to edge.
    II. APPLICATION OF FUZZY LOGIC BASED EDGE DETECTION :

    Fuzzy logic represents a powerful approach to decision making [Zadeh 1965,


    Kaufmann 1975, Bezdek 1981]. Since the concept of fuzzy logic was formu-
    lated in 1965 by Zadeh, many researches have been carried out on its
    application in the various areas of digital image processing such as image
    quality assessment, edge detection, image segmentation, etc. Many tech-
    niques have been suggested by researchers in the past for fuzzy logic-based
    edge
    detection [Cheung and Chan 1995, Kuo, et al. 1997, El-Khamy et al. 2000]. In
    [Zhao, et al. 2001], Zhao, et al. proposed an edge detection technique based
    on probability partition of the image into 3-fuzzy partitions (regions) and the
    principle of maximum entropy for finding the parameters value that result in
    the best compact edge representation of images. In their proposed
    technique the necessary condition for the entropy function to reach its
    maximum is derived. Based on this condition an effective algorithm for
    three-level thresholding is obtained. Several approaches on fuzzy logic based
    edge detection have been reported based on fuzzy If-Then rules [Tao, et al.
    1993, Li 1997].
    II. APPLICATION OF FUZZY LOGIC BASED EDGE DETECTION :

    In most of these methods, adjacent points of pixels are assumed in some classes and
    then fuzzy
    system inference are implemented using appropriate membership function, defined for
    each
    class [Mahani, et al. 2008]. In Liang, et al. [Liang, et al. 2003], adjacent points are as-
    sumed
    as 3×3 sets around the concerned point. By predefining membership function to de-
    tect edges.
    In these rules discontinuity in the color of different 3×3 sets, edges are extracted. It
    uses 5 fuzzy
    rules and predefined membership function to detect edges. In these rules discontinu-
    ity of adjacent point around the concerned point are investigated. If this difference is
    similar to one of predefined sets, the pixel is
    assumed as edge.A similar work is proposed by Mansoori, et al. [Mansoori, et al.
    2006], wherein
    adjacent points of each pixel are grouped in six different set. Then by using of appro-
    priate bell shape membership function, the value from zero to one is determined for
    each group. Based on
    the membership.
    stages of work :

    1-import rgb image


    2-convert color image to grayscal image
    3-convert image to Doubl-prcision Data
    4-calculair Image gradiant
    5-plot the image gradiant
    6-create a fuzzy inferenc system (FIS) for edge detection edgeFIS
    7- specefy the image gradiant Ix and Iy as a input of edgeFIS
    8-specefy a zero-mean guasian membership function of each input
    9- specefy the intesity of te edge detected image as an output of the edgeFIS
    10- specefy the triangular membership function whit and black ,for Iout
    11- specefy FIS rules ,Add rules to make a pixl whit if it belong to a uniform region
    and black otherwis
    12-Evaleat the output of the edge detecter for each row of pixel in I using corespond-
    ing rows Ix and Iy as inputs
    13-plot the original image grayscal
    14- plot the detected edges Ieval
    Result of edge detection :
    Image classification :

    Images are categorized by entering the image into the algorithm, then it
    tells you to which category it belongs
    For image classification there are two algorithms, one for training and one
    for testing

    Training algorithme :
    You enter an RGB image and detect the edges to produce a black and white
    image, then save the image values in the db matrix.
    progremme

    clc;
    clear all;
    close all;
    %% Taking an Image
    [fname, path]=uigetfile('.png','Open an Image as input for training');
    fname=strcat(path, fname);
    im=imread(fname);
    %%%%%%%%%%%%
    Irgb = im;
    Igray = rgb2gray(Irgb);

    figure
    image(Igray,'CDataMapping','scaled')
    colormap('gray')
    title('Input Image in Grayscale')
    I = im2double(Igray);
    Gx = [-1 1];
    Gy = Gx';
    Ix = conv2(I,Gx,'same');
    Iy = conv2(I,Gy,'same');
    figure
    image(Ix,'CDataMapping','scaled')
    colormap('gray')
    title('Ix')
    figure
    image(Iy,'CDataMapping','scaled')
    colormap('gray')
    title('Iy')
    % edgeFIS=mamfis;
    edgeFIS = mamfis('Name','edgeDetection');
    edgeFIS = addInput(edgeFIS,[-1 1],'Name','Ix');
    edgeFIS = addInput(edgeFIS,[-1 1],'Name','Iy');
    sx = 0.1;
    sy = 0.1;
    edgeFIS = addMF(edgeFIS,'Ix','gaussmf',[sx 0],'Name','zero');
    edgeFIS = addMF(edgeFIS,'Iy','gaussmf',[sy 0],'Name','zero');
    edgeFIS = addOutput(edgeFIS,[0 1],'Name','Iout');
    wa = 0.1;
    wb = 1;
    wc = 1;
    ba = 0;
    bb = 0;
    bc = 0.7;
    edgeFIS = addMF(edgeFIS,'Iout','trimf',[wa wb wc],'Name','white');
    edgeFIS = addMF(edgeFIS,'Iout','trimf',[ba bb bc],'Name','black');
    figure
    subplot(2,2,1)
    plotmf(edgeFIS,'input',1)
    title('Ix')
    subplot(2,2,2)
    plotmf(edgeFIS,'input',2)
    title('Iy')
    subplot(2,2,[3 4])
    plotmf(edgeFIS,'output',1)
    title('Iout')
    r1 = "If Ix is zero and Iy is zero then Iout is white";
    r2 = "If Ix is not zero or Iy is not zero then Iout is black";
    edgeFIS = addRule(edgeFIS,[r1 r2]);
    edgeFIS.Rules

    Ieval = zeros(size(I));
    for ii = 1:size(I,1)
    Ieval(ii,:) = evalfis(edgeFIS,[(Ix(ii,:));(Iy(ii,:))]');
    end

    figure
    image(I,'CDataMapping','scaled')
    colormap('gray')
    title('Original Grayscale Image')

    figure
    image(Ieval,'CDataMapping','scaled')
    colormap('gray')
    title('Edge Detection Using Fuzzy Logic')
    %%%%%%%%%%%%%%
    %%im=im2bw(im);
    imshow(Ieval);
    title('Input Image');
    c=input('Enter the Class(Number from 1-12)');
    %% Feature Extraction
    F=FeatureStatistical(Ieval);
    try
    load db;
    F=[F c];
    db=[db; F];
    save db.mat db
    catch
    db=[F c]; % 10 12 1
    save db.mat db
    end
    testing algorithme :
    You enter an RGB image and then the algorithm transforms
    the image using boundary detection (fuzzy logic)
    Then it compares its values to the values in the db array and
    tells you to which class it belongs.
     
    %% Test Image
    clc;
    clear all;
    close all;
    [fname, path]=uigetfile('.png','provide an Image for testing');
    fname=strcat(path, fname);
    im=imread(fname);
    %edge detection using fuzzy logic
    Irgb = im;
    Igray = rgb2gray(Irgb);

    figure
    image(Igray,'CDataMapping','scaled')
    colormap('gray')
    title('Input Image in Grayscale')
    I = im2double(Igray);
    Gx = [-1 1];
    Gy = Gx';
    Ix = conv2(I,Gx,'same');
    Iy = conv2(I,Gy,'same');
    figure
    figure
    image(Ix,'CDataMapping','scaled')
    colormap('gray')
    title('Ix')
    figure
    image(Iy,'CDataMapping','scaled')
    colormap('gray')
    title('Iy')
    % edgeFIS=mamfis;
    edgeFIS = mamfis('Name','edgeDetection');
    edgeFIS = addInput(edgeFIS,[-1 1],'Name','Ix');
    edgeFIS = addInput(edgeFIS,[-1 1],'Name','Iy');
    sx = 0.1;
    sy = 0.1;
    edgeFIS = addMF(edgeFIS,'Ix','gaussmf',[sx 0],'Name','zero');
    edgeFIS = addMF(edgeFIS,'Iy','gaussmf',[sy 0],'Name','zero');
    edgeFIS = addOutput(edgeFIS,[0 1],'Name','Iout');
    wa = 0.1;
    wb = 1;
    wc = 1;
    ba = 0;
    bb = 0;
    bc = 0.7;
    edgeFIS = addMF(edgeFIS,'Iout','trimf',[wa wb wc],'Name','white');
    edgeFIS = addMF(edgeFIS,'Iout','trimf',[ba bb bc],'Name','black');
    figure
    subplot(2,2,1)
    plotmf(edgeFIS,'input',1)
    title('Ix')
    subplot(2,2,2)
    plotmf(edgeFIS,'input',2)
    title('Iy')
    subplot(2,2,[3 4])
    plotmf(edgeFIS,'output',1)
    title('Iout')
    r1 = "If Ix is zero and Iy is zero then Iout is white";
    r2 = "If Ix is not zero or Iy is not zero then Iout is black";
    edgeFIS = addRule(edgeFIS,[r1 r2]);
    edgeFIS.Rules

    Ieval = zeros(size(I));
    for ii = 1:size(I,1)
    Ieval(ii,:) = evalfis(edgeFIS,[(Ix(ii,:));(Iy(ii,:))]');
    end

    figure
    image(I,'CDataMapping','scaled')
    colormap('gray')
    title('Original Grayscale Image')

    figure
    image(Ieval,'CDataMapping','scaled')
    colormap('gray')
    title('Edge Detection Using Fuzzy Logic')
    %%%%%%%%%

    %%im=im2bw(im);
    imshow(Ieval);
    title('Test Image');
    %% Find the class the test image belongs
    Ftest=FeatureStatistical(Ieval);
    %% Compare with the feature of training image in the database
    load db.mat
    Ftrain=db(:,1:2);
    Ctrain=db(:,3);
    for (i=1:size(Ftrain,1));
    dist(i,:)=sum(abs(Ftrain(i,:)-Ftest));
    end
    m=find(dist==min(dist),1);
    det_class=Ctrain(m);
    msgbox(strcat('Detected Class=',num2str(det_class)));

     
     
     

    You might also like