Faces recognition using PCA and SVMs

In [1]:

    

%matplotlib inline
from time import time
import logging
import matplotlib.pyplot as plt

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_lfw_people
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import PCA
from sklearn.svm import SVC
from sklearn import manifold

print(__doc__)

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')

lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)

# introspect the images arrays to find the shapes (for plotting)
n_samples, h, w = lfw_people.images.shape

# for machine learning we use the 2 data directly (as relative pixel
# positions info is ignored by this model)
X = lfw_people.data
n_features = X.shape[1]

# the label to predict is the id of the person
y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]

print("Total dataset size:")
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
print("n_classes: %d" % n_classes)

# split into a training and testing set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42)


    

    




2017-03-19 21:42:53,765 Loading LFW people faces from /home/chandu/scikit_learn_data/lfw_home






    




Automatically created module for IPython interactive environment
Total dataset size:
n_samples: 1288
n_features: 1850
n_classes: 7

In [2]:

    

n_comp_1 = np.arange(150,250,3)
accuracies = []
components = []
n_components = 153
    
pca = PCA(n_components=n_components, svd_solver='randomized',whiten=True).fit(X_train)
    
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)

param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
                  'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)
clf = clf.fit(X_train_pca, y_train)
y_pred = clf.predict(X_test_pca)

accuracies.append(float(np.sum(y_test==y_pred))/len(y_pred))
components.append(n_components)

print('For '+str(n_components)+' components, accuracy is '+str(float(np.sum(y_test==y_pred))/len(y_pred))+' confusion matrix is: ')
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))
print(classification_report(y_test, y_pred, target_names=target_names))


    

    




For 153 components, accuracy is 0.829192546584 confusion matrix is: 
[[  6   6   1   0   0   0   0]
 [  0  53   1   3   1   0   2]
 [  0   1  21   5   0   0   0]
 [  2   5   3 133   0   2   1]
 [  0   0   0   2  16   1   6]
 [  0   0   0   2   1  11   1]
 [  0   2   3   4   0   0  27]]
                   precision    recall  f1-score   support

     Ariel Sharon       0.75      0.46      0.57        13
     Colin Powell       0.79      0.88      0.83        60
  Donald Rumsfeld       0.72      0.78      0.75        27
    George W Bush       0.89      0.91      0.90       146
Gerhard Schroeder       0.89      0.64      0.74        25
      Hugo Chavez       0.79      0.73      0.76        15
       Tony Blair       0.73      0.75      0.74        36

      avg / total       0.83      0.83      0.83       322

In [3]:

    

eigenfaces = pca.components_.reshape((n_components, h, w))
def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
    """Helper function to plot a gallery of portraits"""
#     plt.figure(figsize=(1.8 * n_col, 2.4 * n_row))
    plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
    for i in range(n_row * n_col):
        plt.subplot(n_row, n_col, i + 1)
        plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray)
        plt.title(titles[i], size=12)
        plt.xticks(())
        plt.yticks(())
        
eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)
plt.show()


    

In [ ]: