pca = PCA()
#set dimension
pca.set_target_dim(i)
#compute PCA
pca.init(RealFeatures(images))
pca.apply_to_feature_vector(
RealFeatures(imageAsRow).get_feature_vector(0))
#reconstruct
projection = pca.apply_to_feature_vector(
RealFeatures(imageAsRow).get_feature_vector(0))
reconstruction = np.asmatrix( np.asarray(projection, np.float64))* \
np.asmatrix( pca.get_transformation_matrix()).T
reconstruction = reconstruction + pca.get_mean()
#normlize image
reconstruction_normalize = np.zeros((IMAGE_HEIGHT, IMAGE_WIDHT, 1),
np.uint8)
reconstruction_normalize = cv2.normalize(reconstruction,
reconstruction_normalize, 0,
255, cv2.NORM_MINMAX,
cv2.CV_8UC1)
reconstruction_normalize = reconstruction_normalize.reshape(
IMAGE_HEIGHT, IMAGE_WIDHT)
#show reconstruction
cv2.imshow("reconstruction" + str(i), reconstruction_normalize)
cv2.waitKey(0)
#Reconstruct 10 eigen vectors to 300, step 15
for i in reconstructions:
print "Reconstruct with " + str(i) + " eigenvectors"
pca = PCA()
#set dimension
pca.set_target_dim(i);
#compute PCA
pca.init(RealFeatures(images))
pca.apply_to_feature_vector(RealFeatures(imageAsRow)
.get_feature_vector(0));
#reconstruct
projection = pca.apply_to_feature_vector(RealFeatures(imageAsRow)
.get_feature_vector(0));
reconstruction = np.asmatrix( np.asarray(projection, np.float64))* \
np.asmatrix( pca.get_transformation_matrix()).T
reconstruction = reconstruction + pca.get_mean()
#prepare the data to visualize in one window
show_images_titles.append( str(i) + " eigenvectors" );
show_images.append(reconstruction.reshape(IMAGE_HEIGHT, IMAGE_WIDHT))
plot_gallery(show_images, show_images_titles, IMAGE_HEIGHT,
IMAGE_WIDHT, 4, 4);
pl.show()
