gambar 2

Gambar

XvxQJt1hL-MGueUgiIZI5CnLdvucuP7IawkwfA/s320/IOU.png"/>

finger print 2

im=double(rgb2gray(imread('biometrik3.jpg')))/255;
[b c]=size(im);
m=sum(sum(im))/(b*c);
v = sum(sum((im-m).*(im-m)))/(b*c);
m0=0.5;
v0=v*0.1;
T=zeros(b,c);

for i=1:b
    for j=1:c
        if im(i,j)>m
            T(i,j) =m0+(v0/v*(im(i,j)-m).^2).^0.5;
        else
             T(i,j) =m0-(v0/v*(im(i,j)-m).^2).^0.5;
        end
    end
end
figure(1),imshow(im)
figure(2),imshow(T)
w=20;
nb=b/w;
mb=zeros(nb,nb);
vb=zeros(nb,nb);

for i=1:nb
    for j=1:nb
        g=im((i-1)*w+1:(i-1)*w+w,(j-1)*w+1:(j-1)*w+w);
        mb(i,j)=sum(sum(g));
        vb(i,j)=sum(sum((g-mb(i,j)).^2))/(w*w); 
    end
end

Gmean=sum(sum(mb))/(nb*nb);
Vmean=sum(sum(vb))/(nb*nb);
NGFrg=sum(sum(mb>Gmean));
TGFrg=sum(sum(mb(mb>Gmean)));
GFrg=TGFrg/NGFrg

NVFrg=sum(sum(vb>Vmean));
TVFrg=sum(sum(vb(vb>Vmean)));
VFrg=TGFrg/NGFrg


NGBkg=sum(sum(mb<=Gmean));
TGBkg=sum(sum(mb(mb<=Gmean)));
GBkg=TGBkg/NGBkg

NVBkg=sum(sum(vb<=Vmean));
TVBkg=sum(sum(vb(vb<=Vmean)));
VBkg=TVBkg/NVBkg
mm=mb>GFrg
vv=vb>VFrg

gg =mm&vv

gg=not(gg)
im2 =im;
for i = 1:nb
    for j=1:nb
        if gg(i,j)==0
            im2((i-1)*w+1:(i-1)*w+w,(j-1)*w+1:(j-1)*w+w)=0;
        end
    end
   
end
figure(10);imshow(im2)
mskx=[0 0 0;-1 0 1;0 0 0];
Gx = conv2(im2,mskx,'same')/2;
msky=[ 0 -1 0;0 0 0;0 1 0];
Gy = conv2(im2,msky,'same')/2;
c=complex(Gx,Gy);
Gms=zeros(nb,nb);
for i = 1:nb
    for j = 1:nb
        cb= c((i-1)*w+1:(i-1)*w+w,(j-1)*w+1:(j-1)*w+w);
       
        Gms(i,j)= sum(sum(cb));
    end
end
Gmsx=real(Gms);
Gmsy=imag(Gms);
Teta=zeros(nb,nb);
[bb cc]=find(Gmsx>=0);
Teta(bb,cc)= 0.5*pi+0.5*atan(Gmsy(bb,cc)./Gmsx(bb,cc));
[bb cc]=find(Gmsx<0 amp="" msy="">=0);
Teta(bb,cc)= 0.5*pi+0.5*atan(Gmsy(bb,cc)./Gmsx(bb,cc))+pi;
[bb cc]=find(Gmsx<0 amp="" msy="" p="">Teta(bb,cc)= 0.5*pi+0.5*atan(Gmsy(bb,cc)./Gmsx(bb,cc))-pi;


figure(10);imshow(im2)

hold on



for i =1 : nb
    for j =1:nb
        y0 = (i-1)*w + w/2;
        x0 = (j-1)*w + w/2;
        y1 = (i-1)*w + w/2+w/2*sin(Teta(i,j));
        x1 = (j-1)*w + w/2+w/2*cos(Teta(i,j));;
        x=[x0 x1];
        y=[y0 y1];
        plot(x,y,'b','LineWidth',1);
    end
end
hold off

Align

download di sini

fingerprint 1

im=double(rgb2gray(imread('biometrik2.png')))/255;
[b c] = size(im);

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% M=0;
% for (i=1:b)
%     for (j=1:c)
%         M=M+im(i,j);
%     end
% end
% M=M/(b*c);
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
M=sum(sum(im))/(b*c);       
V=sum(sum((im-M).^2))/(b*c);
M0=0.3;
V0=V/5;
T=[];
for (i=1:b)
    for (j=1:c)
        if im(i,j)>M
            T(i,j) = M0+(V0/V*(im(i,j)-M)^2)^0.5;
        else
            T(i,j) = M0-(V0/V*(im(i,j)-M)^2)^0.5;
        end
    end
end


figure(1);imshow(im);
figure(2);imshow(T);
w=15;
nmax=b/w;
mmax=c/w;
mb=[];
vb=[];
for m =1:nmax
    for n =1:mmax
        ib= im((m-1)*w+1:(m-1)*w+w,(n-1)*w+1:(n-1)*w+w);
        mb(m,n)= sum(sum(ib))/(w*w);
        vb(m,n) = sum(sum((ib-mb(m,n)).^2))/(w*w);
    end
end
GM=sum(sum(mb))/(nmax*mmax);
VM=sum(sum(vb))/(nmax*mmax);
GFRG=sum(mb(mb>GM))/length(mb>GM);
VFRG=sum(vb(vb>VM))/length(vb>VM);
GBKG=sum(mb(mb<=GM))/length(mb<=GM);
VBKG=sum(vb(vb<=VM))/length(vb<=VM);

for i =1:nmax
    for j=1:mmax
        if ((mb(i,j)        im((m-1)*w+1:(m-1)*w+w,(n-1)*w+1:(n-1)*w+w)=0;
       
        end
    end
end
figure(100)
imshow(im)

Fourier

download disini

Pesawat 2

#include

void Pesawat(int x,int y,float s)
{
    moveto(-1*s+x,0*s+y);
      lineto(1*s+x,0*s+y);
      lineto(1*s+x,5*s+y);
      lineto(-1*s+x,5*s+y);
      lineto(-1*s+x,0*s+y);

      moveto(-3*s+x,1*s+y);
      lineto(3*s+x,1*s+y);
      lineto(3*s+x,2*s+y);
      lineto(-3*s+x,2*s+y);
      lineto(-3*s+x,1*s+y);

      moveto(-2*s+x,4*s+y);
      lineto(2*s+x,4*s+y);
      lineto(2*s+x,5*s+y);
      lineto(-2*s+x,5*s+y);
      lineto(-2*s+ Pesawat(x,y,100);x,4*s+y);
}


main()
{
    int x,y;
    int x1,y1;
    float s;
    s=20;
    x=100;
    y=100;
    x1=40;
    y1 =500;
   initwindow(500,500);
   while(!kbhit())
   {
      cleardevice();
      x=mousex();
      y=mousey();
      Pesawat(x,y,10);
      Pesawat(x1,y1,20);
      y1=y1-10;
      if (y1<0 p="">      {
          y1=500;
          x1=x1+50;
      }


      //xp=mousex();
      //yp=mousey();
      // circle(xp,yp,20);

      // circle(x,y,20);
      // x=x+2;
      // if(x>500)
      // {
      //     x=0;
       //}
       delay(50);
   }
   closegraph();
}

VISIKOM S1

materi di sini

Pesawat

 #include
 void Pesawat(float x,float y,float s)
 {    line(0*s+x,0*s+y,1*s+x,1*s+y);
       line(1*s+x,1*s+y,0.5*s+x,4*s+y);
       line(0*s+x,4*s+y,0.5*s+x,4*s+y);
       line(0*s+x,4*s+y,1*s+x,4*s+y);
       line(1*s+x,4*s+y,0*s+x,4.5*s+y);
      line(-0*s+x,0*s+y,-1*s+x,1*s+y);
       line(-1*s+x,1*s+y,-0.5*s+x,4*s+y);
       line(-0*s+x,4*s+y,-0.5*s+x,4*s+y);
       line(-0*s+x,4*s+y,-1*s+x,4*s+y);
       line(-1*s+x,4*s+y,-0*s+x,4.5*s+y);
 }
 main()
 {  float  x1,y1,x2,y2,x,y;
     float s;
     s=20; x1=100;  y1=100; x2=200;  y2=100;
  initwindow(300,300);//Inisialisasi Layar Grafik
   while (!kbhit())
   {   cleardevice();
   x=mousex();
   y=mousey();
   Pesawat(x,y,30);
       y1=y1-1;
       y2=y2-2;
       if (y1<0 y1="300;}</p">       if (y2<0 nbsp="" p="" y2="300;">       Pesawat(x1,y1,10);
       Pesawat(x2,y2,20);
       delay(50);
   }
   closegraph();//Menutup Grafik
 }

Buku Visi Komputer

Download Di SINI

Read Data Keras

from keras.models import Sequential
from keras.layers import Dense
import numpy as np

import pandas as pd
def ReadData(sf):
  print("Baca file :",sf)
  df = np.array(pd.read_csv(sf,header=None))
  df1 = pd.DataFrame(df)
  return df1.values

def ReadData2(sf,lw):
    print("Baca file :",sf)
    df = np.array(pd.read_csv(sf,header=None))
    y=df[lw:,3:4]
    x=[];
    for i in range(len(df)-lw):
        dm=np.concatenate((df[i:i+lw,0],df[i:i+lw,1],df[i:i+lw,2]))
        x.append(dm)
    x=np.array(x)
 
    return x,y


sf='Data.csv'
X,Y=ReadData2(sf,20)




model = Sequential()
model.add(Dense(1000, input_dim=60, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(X, Y, epochs=500, batch_size=1)


https://www.pyimagesearch.com/2019/02/04/keras-multiple-inputs-and-mixed-data/

https://drive.google.com/open?id=13R-SxdZVdNG_2CAACgGnTJxX1Tz8f8zF

Grafika

#include
#include
#include
#include
#include
#include
#include
#include
#include
using namespace std;
struct TPoint
{ float x;
  float y;};
struct TMatrix
{
    float m[3][3];
};

void DrawLine(TPoint P1,TPoint P2)
{
    float x1,y1,x2,y2;
    x1 = 250+P1.x ;
    y1 =250-P1.y;
    x2 = 250+P2.x ;
    y2 =250-P2.y;
    line(x1,y1,x2,y2);
}
TPoint SetPoint(float x,float y)
{
    TPoint p;
    p.x = x;
    p.y= y;
    return p;
}


float d2r(float sd )
{
    return sd/180*3.1415926535897932384626433832795;
}
TMatrix MatRotasi(float sd)
{
    TMatrix M;
    M.m[0][0]=cos(sd);M.m[0][1]=-sin(sd);M.m[0][2]=0;
    M.m[1][0]=sin(sd);M.m[1][1]=cos(sd);M.m[1][2]=0;
    M.m[2][0]=0;M.m[2][1]=0;M.m[2][2]=1;
    return M;
}


TMatrix MatSkala(float Sx,float Sy)
{
    TMatrix M;
    M.m[0][0]=Sx;M.m[0][1]=0;M.m[0][2]=0;
    M.m[1][0]=0;M.m[1][1]=Sy;M.m[1][2]=0;
    M.m[2][0]=0;M.m[2][1]=0;M.m[2][2]=1;
    return M;
}

TMatrix MatTranslasi(float Dx,float Dy)
{
    TMatrix M;
    M.m[0][0]=1;M.m[0][1]=0;M.m[0][2]=Dx;
    M.m[1][0]=0;M.m[1][1]=1;M.m[1][2]=Dy;
    M.m[2][0]=0;M.m[2][1]=0;M.m[2][2]=1;
    return M;
}

TMatrix MatKali(TMatrix A, TMatrix B)
{
    TMatrix C;
    int i,j,k;
    for (i=0;i<=2;i++)
    {
        for (j=0;j<=2;j++)
        {
            C.m[i][j]=0;
            for (k=0;k<=2;k++)
            {
                C.m[i][j]=C.m[i][j]+A.m[i][k]*B.m[k][j];
            }
        }
    }

    return C;
}

TPoint Transformasi(TMatrix  M, TPoint Pi)
{
    TPoint Po;
    Po.x=M.m[0][0]*Pi.x+M.m[0][1]*Pi.y+M.m[0][2];
    Po.y=M.m[1][0]*Pi.x+M.m[1][1]*Pi.y+M.m[1][2];
    return Po;

}



void Kotak(TMatrix m)
{
    int i;
    TPoint p[5],p1,p2;
    p[0]=SetPoint(-100,-100);
    p[1]=SetPoint(100,-100);
    p[2]=SetPoint(100,100);
    p[3]=SetPoint(-100,100);
    p[4]=SetPoint(-100,-100);
    for (i = 0;i<4 i="" p="">    {
        p1 = Transformasi(m,p[i]);
        p2 = Transformasi(m,p[i+1]);
        DrawLine(p1,p2);

    }

}

float sd;
int main()
{
    TMatrix m;

     initwindow(500,500);
    do
    {
        cleardevice();
         m=MatSkala(1,1);
    m=MatKali(MatRotasi(d2r(sd)),MatSkala(1,1));
sd =sd+2;
       Kotak(m);

        delay(100);

    }while(!kbhit());
    return 0;
}

opencv filter

import cv2
import numpy as np
from matplotlib import pyplot as plt

img = cv2.imread('opencv_logo.png')

kernel = np.ones((5,5),np.float32)/25
dst = cv2.filter2D(img,-1,kernel)

plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(dst),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.show()

Resources S3

dowload di sini

Contoh ReadData pada Google

from keras.models import Sequential

from keras.layers import Dense

import numpy

from scipy.spatial import Delaunay

import pandas as pd

def ReadData(sf):

sdir="drive/My Drive/Colab Notebooks"

sff="%s/%s"%(sdir ,sf)

print("Baca file :",sff)

df = array(pd.read_csv(sff,header=None))

df1 = pd.DataFrame(df)

return df1.values

def SaveData(sf,m):

sdir="drive/My Drive/Colab Notebooks"

sff="%s/%s"%(sdir ,sf)

print("Simpan File :",sff)

savetxt(sff, m, delimiter=',',newline='\r\n')

# load and prepare the dataset

#dataset = numpy.loadtxt("cb.csv", delimiter=",")

#X = dataset[:,0:8]

#Y = dataset[:,8]

X=numpy.array([[0,0],[0,1],[1,0],[1,1]]);

Y=numpy.array([[0],[1],[1],[0]]);

# 1. define the network

model = Sequential()

model.add(Dense(1000, input_dim=2, activation='sigmoid'))

model.add(Dense(1, activation='sigmoid'))

# 2. compile the network

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# 3. fit the network

history = model.fit(X, Y, epochs=10000, batch_size=1)

#history = model.fit(X, Y, epochs=2000)

# 4. evaluate the network

loss, accuracy = model.evaluate(X, Y)

print("\nLoss: %.2f, Accuracy: %.2f%%" % (loss, accuracy*100))

# 5. make predictions

probabilities = model.predict(X)

predictions = [float(numpy.round(x)) for x in probabilities]

accuracy = numpy.mean(predictions == Y)

print("Prediction Accuracy: %.2f%%" % (accuracy*100))

Cloack

https://www.learnopencv.com/invisibility-cloak-using-color-detection-and-segmentation-with-opencv/

Keras Squential Model

# example of training a final classification model
import matplotlib.pyplot as plt

from keras.models import Sequential
from keras.layers import Dense
import numpy as np
X=np.array([[0,0],[0,1],[1,0],[1,1]])
T=np.array([[0],[1],[1],[0]])
# define and fit the final model





model = Sequential()
model.add(Dense(1000, input_dim=2, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam')
model.fit(X, T, epochs=2000)
model.save_weights("model.h5")

history =model.history
plt.plot(history.history['loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

Xp=np.array([[1,1]])
model.predict(Xp)

Materi Kuliah Pemodelan 3D

Download Materi Di SINI

PCD VB6 Point Opration

program bisa didownload di sini

Visi Komputer

Bahan Kuliah Download di sini