Klasifikasi Daun Dengan Metode ANFIS (Adaptive Neuro-Fuzzy Inference System)

1. Mempersiapkan citra latih untuk proses pelatihan

2. Melakukan pelatihan algoritma ANFIS untuk mengklasifikasikan citra daun.

% Abdul Haris Kuspranoto ST. MT.
% www.sinauprogramming.com
clc; clear; close all; warning off all;

image_folder = 'training data';
filenames = dir(fullfile(image_folder, '*.tif'));
total_images = numel(filenames);

feature = zeros(total_images,6);

for n = 1:total_images
    full_name = fullfile(image_folder, filenames(n).name);
    I = imread(full_name);
    Img = im2bw(I,graythresh(I));
    Img = imcomplement(Img);
    Img = imfill(Img,'holes');
    Img = bwareaopen(Img,1000);
    
    % Ekstraksi Ciri Morfologi
    stats = regionprops(Img,'All');
    area = stats.Area;
    perimeter = stats.Perimeter;
    metric = 4*pi*area/(perimeter^2);
    eccentricity = stats.Eccentricity;
    
    % Ekstraksi Ciri Tekstur
    GLCM = graycomatrix(I,'Offset',[0 1; -1 1; -1 0; -1 -1]);
    stats = graycoprops(GLCM,{'contrast','correlation','energy','homogeneity'});
    contrast = mean(stats.Contrast);
    correlation = mean(stats.Correlation);
    energy = mean(stats.Energy);
    homogeneity = mean(stats.Homogeneity);
    
    feature(n,1) = metric;
    feature(n,2) = eccentricity;
    feature(n,3) = contrast;
    feature(n,4) = correlation;
    feature(n,5) = energy;
    feature(n,6) = homogeneity;
end

target = zeros(total_images,1);
target(1:7,:) = 1;
target(8:14,:) = 2;
target(15:21,:) = 3;
target(22:28,:) = 4;

trnData = [feature,target];

numMFs = 2;
mfType = 'gbellmf';
error_goal = 1e-6;
epoch = 120;
trnOpt(1) = epoch;
trnOpt(2) = error_goal;

fismat = genfis1(trnData,numMFs,mfType);
[trnfismat,rmse] = anfis(trnData, fismat, trnOpt);
[x,mf] = plotmf(trnfismat,'input',1);
subplot(2,3,1), plot(x,mf)
xlabel('input 1 (gbellmf)')
[x,mf] = plotmf(trnfismat,'input',2);
subplot(2,3,2), plot(x,mf)
xlabel('input 2 (gbellmf)')
[x,mf] = plotmf(trnfismat,'input',3);
subplot(2,3,3), plot(x,mf)
xlabel('input 3 (gbellmf)')
[x,mf] = plotmf(trnfismat,'input',4);
subplot(2,3,4), plot(x,mf)
xlabel('input 4 (gbellmf)')
[x,mf] = plotmf(trnfismat,'input',5);
subplot(2,3,5), plot(x,mf)
xlabel('input 5 (gbellmf)')
[x,mf] = plotmf(trnfismat,'input',6);
subplot(2,3,6), plot(x,mf)
xlabel('input 6 (gbellmf)')
writefis(trnfismat,'trnfismat')

output = round(evalfis(trnData(:,1:6), trnfismat));

error = numel(find(output~=target));
akurasi_pelatihan = (numel(output)-error)/(numel(output))*100

3. Mempersiapkan citra uji untuk proses pengujian

4. Melakukan pengujian algoritma ANFIS menggunakan fuzzy inference system 

yang dihasilkan dari proses pelatihan. Koding program untuk proses 

pengujian adalah:

5. Membuat tampilan Graphical User Interface (GUI)

% Abdul Haris Kuspranoto
% Website: https://sinauprogramming.com/


function varargout = Classification_Clover_Anfis(varargin)
% CLASSIFICATION_CLOVER_ANFIS MATLAB code for Classification_Clover_Anfis.fig
%      CLASSIFICATION_CLOVER_ANFIS, by itself, creates a new CLASSIFICATION_CLOVER_ANFIS or raises the existing
%      singleton*.
%
%      H = CLASSIFICATION_CLOVER_ANFIS returns the handle to a new CLASSIFICATION_CLOVER_ANFIS or the handle to
%      the existing singleton*.
%
%      CLASSIFICATION_CLOVER_ANFIS('CALLBACK',hObject,eventData,handles,...) calls the local
%      function named CALLBACK in CLASSIFICATION_CLOVER_ANFIS.M with the given input arguments.
%
%      CLASSIFICATION_CLOVER_ANFIS('Property','Value',...) creates a new CLASSIFICATION_CLOVER_ANFIS or raises the
%      existing singleton*.  Starting from the left, property value pairs are
%      applied to the GUI before Classification_Clover_Anfis_OpeningFcn gets called.  An
%      unrecognized property name or invalid value makes property application
%      stop.  All inputs are passed to Classification_Clover_Anfis_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 Classification_Clover_Anfis

% Last Modified by GUIDE v2.5 19-Oct-2020 06:08:38

% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name',       mfilename, ...
    'gui_Singleton',  gui_Singleton, ...
    'gui_OpeningFcn', @Classification_Clover_Anfis_OpeningFcn, ...
    'gui_OutputFcn',  @Classification_Clover_Anfis_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 Classification_Clover_Anfis is made visible.
function Classification_Clover_Anfis_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 Classification_Clover_Anfis (see VARARGIN)

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

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

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


% --- Outputs from this function are returned to the command line.
function varargout = Classification_Clover_Anfis_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)
[nama_file,nama_path] = uigetfile({'*.*'});

if ~isequal(nama_file,0)
    I = imread(fullfile(nama_path,nama_file));
    axes(handles.axes1)
    imshow(I)
    title('Original Image');
    handles.I = I;
    guidata(hObject,handles)
else
    return
end


% --- 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)
I = handles.I;
Img = im2bw(I,graythresh(I));
Img = imcomplement(Img);
Img = imfill(Img,'holes');
Img = bwareaopen(Img,1000);

% Ekstraksi Ciri Morfologi
stats = regionprops(Img,'All');
area = stats.Area;
perimeter = stats.Perimeter;
metric = 4*pi*area/(perimeter^2);
eccentricity = stats.Eccentricity;

% Ekstraksi Ciri Tekstur
GLCM = graycomatrix(I,'Offset',[0 1; -1 1; -1 0; -1 -1]);
stats = graycoprops(GLCM,{'contrast','correlation','energy','homogeneity'});
contrast = mean(stats.Contrast);
correlation = mean(stats.Correlation);
energy = mean(stats.Energy);
homogeneity = mean(stats.Homogeneity);

testData = [metric,eccentricity,contrast,correlation,energy,homogeneity];
trnfismat = readfis('trnfismat.fis');
output = round(evalfis(testData, trnfismat));

axes(handles.axes2)
imshow(Img)
title('Segmentation Result Of Image');

if output == 1
    kelas = 'Clover Class A';
elseif output == 2
    kelas = 'Clover Class B';
elseif output == 3
    kelas = 'Clover Class C';
elseif output == 4
    kelas = 'Clover Class D';
end

set(handles.edit1,'String',kelas)

% --- Executes on button press in pushbutton3.
function pushbutton3_Callback(hObject, eventdata, handles)
% hObject    handle to pushbutton3 (see GCBO)
% eventdata  reserved - to be defined in a future version of MATLAB
% handles    structure with handles and user data (see GUIDATA)
axes(handles.axes1)
cla reset;
set(gca,'XTick',[]);
set(gca,'YTick',[]);

axes(handles.axes2)
cla reset;
set(gca,'XTick',[]);
set(gca,'YTick',[]);

set(handles.edit1,'String','');

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