Texture Analysis – Gray-Level Co-Occurrence Matrix (GLCM) – GUI Matlab


Analisis tekstur merupakan salah satu jenis ekstraksi ciri yang didasarkan pada ciri statistik citra. Analisis tekstur dapat dilakukan dengan metode ekstraksi ciri orde satu, ekstraksi ciri orde dua, filter gabor, transformasi wavelet, dsb.

Berikut ini merupakan pemrograman gui matlab untuk analisis tekstur menggunakan metode Gray-Level Co-Occurrence Matrix (GLCM) yang merupakan ciri statistik orde dua. Ekstraksi ciri dilakukan berdasarkan parameter contrast, correlation, energy, dan homogeneity.

Tampilan GUI Matlab untuk analisis tekstur citra menggunakan metode Gray-Level Co-Occurrence Matrix (GLCM) adalah sebagai berikut:

1. Gray-Level Co-Occurrence Matrix (GLCM) dengan pixel distance = 1
1

2. Gray-Level Co-Occurrence Matrix (GLCM) dengan pixel distance = 2 2

3. Gray-Level Co-Occurrence Matrix (GLCM) dengan pixel distance = 3 3
Source code dan citra untuk ekstraksi ciri tekstur menggunakan metode GLCM dapat diunduh pada laman berikut ini: Source Code

Sedangkan tampilan source code nya adalah:

function varargout = Texture_Analysis(varargin)
% TEXTURE_ANALYSIS MATLAB code for Texture_Analysis.fig
% TEXTURE_ANALYSIS, by itself, creates a new TEXTURE_ANALYSIS or raises the existing
% singleton*.
%
% H = TEXTURE_ANALYSIS returns the handle to a new TEXTURE_ANALYSIS or the handle to
% the existing singleton*.
%
% TEXTURE_ANALYSIS('CALLBACK',hObject,eventData,handles,...) calls the local
% function named CALLBACK in TEXTURE_ANALYSIS.M with the given input arguments.
%
% TEXTURE_ANALYSIS('Property','Value',...) creates a new TEXTURE_ANALYSIS or raises the
% existing singleton*. Starting from the left, property value pairs are
% applied to the GUI before Texture_Analysis_OpeningFcn gets called. An
% unrecognized property name or invalid value makes property application
% stop. All inputs are passed to Texture_Analysis_OpeningFcn via varargin.
%
% *See GUI Options on GUIDE's Tools menu. Choose "GUI allows only one
% instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help Texture_Analysis

% Last Modified by GUIDE v2.5 11-Aug-2015 10:46:06

% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name', mfilename, ...
    'gui_Singleton', gui_Singleton, ...
    'gui_OpeningFcn', @Texture_Analysis_OpeningFcn, ...
    'gui_OutputFcn', @Texture_Analysis_OutputFcn, ...
    'gui_LayoutFcn', [] , ...
    'gui_Callback', []);
if nargin && ischar(varargin{1})
    gui_State.gui_Callback = str2func(varargin{1});
end

if nargout
    [varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
    gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT


% --- Executes just before Texture_Analysis is made visible.
function Texture_Analysis_OpeningFcn(hObject, eventdata, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% varargin command line arguments to Texture_Analysis (see VARARGIN)

% Choose default command line output for Texture_Analysis
handles.output = hObject;

% Update handles structure
guidata(hObject, handles);
movegui(hObject,'center');

% UIWAIT makes Texture_Analysis wait for user response (see UIRESUME)
% uiwait(handles.figure1);


% --- Outputs from this function are returned to the command line.
function varargout = Texture_Analysis_OutputFcn(hObject, eventdata, handles)
% varargout cell array for returning output args (see VARARGOUT);
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure
varargout{1} = handles.output;


% --- Executes on button press in pushbutton1.
function pushbutton1_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
[filename,pathname] = uigetfile({'*.*'});

if ~isequal(filename,0)
    Info = imfinfo(fullfile(pathname,filename));
    if Info.BitDepth == 1
        msgbox('Citra masukan harus citra RGB atau Grayscale');
        return
    elseif Info.BitDepth == 8
        Img = imread(fullfile(pathname,filename));
        axes(handles.axes1)
        cla('reset')
        imshow(Img)
        title('Grayscale Image')
    else
        Img = rgb2gray(imread(fullfile(pathname,filename)));
        axes(handles.axes1)
        cla('reset')
        imshow(Img)
        title('Grayscale Image')
    end
else
    return
end

handles.Img = Img;
guidata(hObject,handles);

% --- Executes on button press in pushbutton2.
function pushbutton2_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton2 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
Img = handles.Img;
pixel_dist = str2double(get(handles.edit1,'String'));
GLCM = graycomatrix(Img,'Offset',[0 pixel_dist; -pixel_dist pixel_dist; -pixel_dist 0; -pixel_dist -pixel_dist]);
stats = graycoprops(GLCM,{'contrast','correlation','energy','homogeneity'});

Contrast = stats.Contrast;
Correlation = stats.Correlation;
Energy = stats.Energy;
Homogeneity = stats.Homogeneity;

data = get(handles.uitable1,'Data');
data{1,1} = num2str(Contrast(1));
data{1,2} = num2str(Contrast(2));
data{1,3} = num2str(Contrast(3));
data{1,4} = num2str(Contrast(4));
data{1,5} = num2str(mean(Contrast));

data{2,1} = num2str(Correlation(1));
data{2,2} = num2str(Correlation(2));
data{2,3} = num2str(Correlation(3));
data{2,4} = num2str(Correlation(4));
data{2,5} = num2str(mean(Correlation));

data{3,1} = num2str(Energy(1));
data{3,2} = num2str(Energy(2));
data{3,3} = num2str(Energy(3));
data{3,4} = num2str(Energy(4));
data{3,5} = num2str(mean(Energy));

data{4,1} = num2str(Homogeneity(1));
data{4,2} = num2str(Homogeneity(2));
data{4,3} = num2str(Homogeneity(3));
data{4,4} = num2str(Homogeneity(4));
data{4,5} = num2str(mean(Homogeneity));

set(handles.uitable1,'Data',data,'ForegroundColor',[0 0 0])

function edit1_Callback(hObject, eventdata, handles)
% hObject handle to edit1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)

% Hints: get(hObject,'String') returns contents of edit1 as text
% str2double(get(hObject,'String')) returns contents of edit1 as a double


% --- Executes during object creation, after setting all properties.
function edit1_CreateFcn(hObject, eventdata, handles)
% hObject handle to edit1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles empty - handles not created until after all CreateFcns called

% Hint: edit controls usually have a white background on Windows.
% See ISPC and COMPUTER.
if ispc && isequal(get(hObject,'BackgroundColor'), get(0,'defaultUicontrolBackgroundColor'))
    set(hObject,'BackgroundColor','white');
end

Save

Advertisements

Posted on August 11, 2015, in Pengenalan Pola, Pengolahan Citra and tagged , , , , , , , , , , , , , , , , , , , , , , , , , , . Bookmark the permalink. 113 Comments.

  1. Assalamualaikum mas adi
    saya mau bertanya, apabila saya ingin menggunakan segmentasi otsu lalu di ekstrak menggunakan GLCM apa bisa ?
    kalau tidak bisa karena gambar hasil segmentasi berupa gambar biner, apa bisa gambar biner tersebut di revert kembali menjadi grayscale agar dapat di ekstrak GLCM ? dengan catatan sudah tersegmentasi

  2. mas, mau nanya apakah ada refensi di web ini masalah algoritma labelling component ? seperti algoritma pemisahan label pada citra

  3. assalamualaikum mas adi. untuk metode GLCM sendiri apakah ukuran piksel juga akan berpengaruh bila piksel yang saya gunakan berbeda pada setiap data?
    jika dinalarkan pembentukan cooncurance sendiri mengacu pada bitDepthnya.

    • Waalaikumsalam malek
      Utk pembuatan matriks kookurensi pada glcm dg ukuran matriks masukan yg berbeda2 akan tetap menghasilkan matriks kookurensi dg ukuran yg sama tetapi nilai yg ada pada matriks kookurensi akan berbeda karena nilai tsb diperoleh dari frekuensi kemunculan intensitas piksel
      Jika ukuran matriks masukan kecil maka nilai yg ada pada matriks kookurensi akan sedikit
      Sedangkan jika ukuran matriks masukan besar maka nilai yg ada pada matriks kookurensi akan banyak

    • sip makasih banyak mas adi infonya 🙂 🙂

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: