def reconstruct (W , Y , mu = None ) :
if mu is None :
return np . dot (Y ,W.T)
return np . dot (Y , W .T) + mu
# read images
[X , y] = read_images ('D:\homework and assignments\computer vision\face and gender recognition\images')
# perform a full pca
[D , W , mu ] = pca ( asRowMatrix (X ) , y)
import sys
# append tinyfacerec to module search path
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.util import read_images
from tinyfacerec.model import FisherfacesModel
if __name__ == '__main__':
if len(sys.argv) != 2:
print "USAGE: example_model_fisherfaces.py </path/to/images>"
sys.exit()
# read images
[X,y] = read_images(sys.argv[1], sz=[92, 112])
# compute the eigenfaces model
model = FisherfacesModel(X[1:], y[1:])
# get a prediction for the first observation
print "expected =", y[0], "/", "predicted =", model.predict(X[0])
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
if __name__ == '__main__':
if len(sys.argv) != 2:
print "USAGE: example_eigenfaces.py </path/to/images>"
sys.exit()
# read images
[X, y] = read_images(sys.argv[1])
# perform a full pca
[D, W, mu] = pca(asRowMatrix(X), y)
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in xrange(min(len(X), 16)):
e = W[:, i].reshape(X[0].shape)
E.append(normalize(e, 0, 255))
# plot them and store the plot to "python_eigenfaces.pdf"
subplot(title="Eigenfaces AT&T Facedatabase",
images=E,
import sys
# append tinyfacerec to module search path
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.util import read_images
from tinyfacerec.model import EigenfacesModel
# read images
[X,y] = read_images("/home/philipp/facerec/data/yalefaces_recognition")
# compute the eigenfaces model
model = EigenfacesModel(X[1:], y[1:])
# get a prediction for the first observation
print "expected =", y[0], "/", "predicted =", model.predict(X[0])
s, img = cam.read() if s: # frame captured without any errors print "capture done!!" #cam.release() else: print "Not successful!!" #Convert to gray scale gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #-------------------------------------------------------- # read images [X,y] = read_images(imagePath) # Create the haar cascade faceCascade = cv2.CascadeClassifier(cascPath) #-------------------------------------------------------- # compute the eigenfaces model #model = EigenfacesModel(X, y) #makes an instance of EigenfacesModel class #-------------------------------------------------------- # For face recognition we will the the LBPH Face Recognizer recognizer = cv2.createLBPHFaceRecognizer() #Better results in different lighting conditions #recognizer = cv2.createEigenFaceRecognizer()
import sys
# append tinyfacerec to module search path
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
# read images
[X,y] = read_images('att_faces')
# perform a full pca
[D, W, mu] = pca(asRowMatrix(X[1:]), y)
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in range(min(len(X), 16)):
e = W[:,i].reshape(X[0].shape)
E.append(normalize(e,0,255))
# plot them and store the plot to "python_eigenfaces.pdf"
subplot(title="Eigenfaces AT&T Facedatabase", images=E, rows=4, cols=4, sptitle="Eigenface", colormap=cm.gray, filename="python_pca_eigenfaces.pdf")
from tinyfacerec.subspace import project, reconstruct
# reconstruction steps
steps=[i for i in range(10, min(len(X), 400), 20)]
E = []
import sys
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
# set numpy array print option
np.set_printoptions(threshold=1000000)
# read images
[X, y] = read_images('../att_faces')
# perform a full pca
[D, W, mu] = pca(asRowMatrix(X), y)
print()
print(D)
print()
print(len(W))
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in range(min(len(X), 10)):
e = W[:, i].reshape(X[0].shape)
E.append(normalize(e, 0, 255))
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
if __name__ == '__main__':
if len(sys.argv) != 2:
print "USAGE: example_eigenfaces.py </path/to/images>"
sys.exit()
# read images
[X,y] = read_images(sys.argv[1])
# perform a full pca
[D, W, mu] = pca(asRowMatrix(X), y)
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in xrange(min(len(X), 16)):
e = W[:,i].reshape(X[0].shape)
E.append(normalize(e,0,255))
# plot them and store the plot to "python_eigenfaces.pdf"
subplot(title="Eigenfaces AT&T Facedatabase", images=E, rows=4, cols=4, sptitle="Eigenface", colormap=cm.jet, filename="python_pca_eigenfaces.png")
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import fisherfaces
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
if __name__ == '__main__':
if len(sys.argv) != 2:
print "USAGE: example_fisherfaces.py </path/to/images>"
sys.exit()
# read images
[X,y] = read_images(sys.argv[1])
# perform a full pca
[D, W, mu] = fisherfaces(asRowMatrix(X), y)
#import colormaps
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in xrange(min(W.shape[1], 16)):
e = W[:,i].reshape(X[0].shape)
E.append(normalize(e,0,255))
# plot them and store the plot to "python_fisherfaces_fisherfaces.pdf"
subplot(title="Fisherfaces AT&T Facedatabase", images=E, rows=4, cols=4, sptitle="Fisherface", colormap=cm.jet, filename="python_fisherfaces_fisherfaces.png")
from tinyfacerec.subspace import project, reconstruct
import sys
import os
import numpy as np
# append tinyfacerec to module search path
sys.path.append("..")
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
[X,y] = read_images("/home/priyanka/Desktop/CV/scripts/att_faces")
[D, W, mu] = pca(asRowMatrix(X), y)
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in range(min(len(X), 16)):
e = W[:,i].reshape(X[0].shape)
E.append(normalize(e,0,255))
# plot them and store the plot to "python_eigenfaces.pdf"
subplot(title="Eigenfaces AT&T Facedatabase", images=E, rows=4, cols=4, sptitle="Eigenface", colormap=cm.jet, filename="python_pca_eigenfaces.pdf")
from tinyfacerec.subspace import project, reconstruct
# reconstruction steps
steps=[i for i in range(10, min(len(X), 320), 20)]
E = []
import sys
# append tinyfacerec to module search path
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
# read images
[X,y] = read_images("/home/philipp/facerec/data/at")
# perform a full pca
[D, W, mu] = pca(asRowMatrix(X), y)
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in xrange(min(len(X), 16)):
e = W[:,i].reshape(X[0].shape)
E.append(normalize(e,0,255))
# plot them and store the plot to "python_eigenfaces.pdf"
subplot(title="Eigenfaces AT&T Facedatabase", images=E, rows=4, cols=4, sptitle="Eigenface", colormap=cm.jet, filename="python_pca_eigenfaces.pdf")
from tinyfacerec.subspace import project, reconstruct
# reconstruction steps
steps=[i for i in xrange(10, min(len(X), 320), 20)]
E = []
from pylab import *
from PIL import Image
from io import StringIO
# append tinyfacerec to module search path
sys . path . append ("..")
# import tinyfacerec modules
from tinyfacerec . util import read_images
from tinyfacerec . model import EigenfacesModel
from scripts . data_spilt import data_spilts
# read images
data_spilts(train=5)
[X,y] = read_images ("/home/priyanka/Desktop/scripts/Test")
[A,a] = read_images ("/home/priyanka/Desktop/scripts/Train")
model = EigenfacesModel (X[0:] , y [0:])
correct=0
incorrect=0
for i in range(size(a)):
if a[i] ==model . predict (A[i]):
correct+=1
else:
incorrect+=1
print("Correct = ",correct)
print("Incorrect = ",incorrect)
Accuracy=(size(a)-incorrect)*100/size(a)
import sys
# append tinyfacerec to module search path
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.util import read_images
from tinyfacerec.model import EigenfacesModel
# read images
[X,y] = read_images('training')
[A,b] = read_images('test')
# compute the eigenfaces model
model = EigenfacesModel(X[:], y[:])
# get a prediction for the first observation
c=[]
num_correct=0
for i in range(120):
if i%3==0:
a=int(i/3)
print ("expected =", y[(a)*7])
print("/", "predicted =", model.predict(A[i]))
c.append(model.predict(A[i]))
if c[i]==b[i]:
num_correct+=1
num_test = float(len(b[:]))
accuracy = float(num_correct)/ num_test
sys.path.append("..")
# import numpy and matplotlib colormaps
import numpy as np
# import tinyfacerec modules
from tinyfacerec.subspace import pca
from tinyfacerec.util import normalize, asRowMatrix, read_images
from tinyfacerec.visual import subplot
if __name__ == '__main__':
if len(sys.argv) != 2:
print "USAGE: example_eigenfaces.py </path/to/images>"
sys.exit()
# read images
[X, y] = read_images(sys.argv[1])
# perform a full pca
[D, W, mu] = pca(asRowMatrix(X), y)
import matplotlib.cm as cm
# turn the first (at most) 16 eigenvectors into grayscale
# images (note: eigenvectors are stored by column!)
E = []
for i in xrange(min(len(X), 16)):
e = W[:, i].reshape(X[0].shape)
E.append(normalize(e, 0, 255))
# plot them and store the plot to "python_eigenfaces.pdf"
subplot(title="Eigenfaces AT&T Facedatabase",
images=E,
#Cgray = CropFace(img, eye_left=(252,364), eye_right=(420,366), offset_pct=(0.3,0.3), dest_sz=(200,200)) #gray = cv2.normalize(gray,gray,0,255) #gray = Image.fromarray(gray) #-------------------------------------------------------- # Create the haar cascade faceCascade = cv2.CascadeClassifier(cascPath) #if len(sys.argv) != 3: # print "USAGE: example_model_eigenfaces.py </path/to/images>" # sys.exit() # read images [X,y] = read_images(imagePath) #argv[1]:path to the images #-------------------------------------------------------- # compute the eigenfaces model #model = EigenfacesModel(X, y) #makes an instance of EigenfacesModel class #-------------------------------------------------------- # For face recognition we will the the LBPH Face Recognizer recognizer = cv2.createLBPHFaceRecognizer() #Better results in different lighting conditions #recognizer = cv2.createEigenFaceRecognizer() # Perform the tranining recognizer.train(X, np.array(y))
