def test_gmm_best_segment(self):
"""
Calculate the best segment
generated by the GMM and
compare the subsequent likelihood
of a reference segmentation.
Note: this test will take a while
to run.
returns:
best_seg = np.ndarray[np.ndarray[float]]
"""
image_file = 'images/party_spock.png'
image_matrix = image_to_matrix(image_file)
image_matrix_flat = flatten_image_matrix(image_matrix)
num_components = 3
gmm = GaussianMixtureModel(image_matrix, num_components)
gmm.initialize_training()
iters = 10
# generate best segment from 10 iterations
# and extract its likelihood
best_seg = gmm.best_segment(iters)
matrix_to_image(best_seg, 'images/best_segment_spock.png')
best_likelihood = gmm.likelihood()
# extract likelihood from reference image
ref_image_file = 'images/party_spock%d_baseline.png' % num_components
ref_image = image_to_matrix(ref_image_file, grays=True)
gmm_ref = GaussianMixtureModel(ref_image, num_components)
ref_vals = ref_image.flatten()
ref_means = list(set(ref_vals))
ref_variances = np.zeros(num_components)
ref_mixing = np.zeros(num_components)
for i in range(num_components):
relevant_vals = ref_vals[ref_vals == ref_means[i]]
ref_mixing[i] = float(len(relevant_vals)) / float(len(ref_vals))
ref_mask = ref_vals == ref_means[i]
ref_variances[i] = np.mean(
(image_matrix_flat[ref_mask] - ref_means[i])**2)
gmm_ref.means = ref_means
gmm_ref.variances = ref_variances
gmm_ref.mixing_coefficients = ref_mixing
ref_likelihood = gmm_ref.likelihood()
# compare best likelihood and reference likelihood
likelihood_diff = best_likelihood - ref_likelihood
print "Reference"
print gmm_ref.means
print gmm_ref.variances
print gmm_ref.mixing_coefficients
print best_likelihood
print ref_likelihood
print likelihood_diff
likelihood_thresh = 8e4
self.assertTrue(likelihood_diff >= likelihood_thresh,
msg=("Image segmentation failed to improve baseline "
"by at least %.2f" % likelihood_thresh))
def test_k_means(self):
"""
Testing your implementation
of k-means on the segmented
bird_color_24 reference images.
"""
k_min = 2
k_max = 6
image_dir = 'images/'
image_name = 'bird_color_24.png'
image_values = image_to_matrix(image_dir + image_name)
# initial mean for each k value
initial_means = [
np.array([[0.90980393, 0.8392157, 0.65098041],
[0.83137256, 0.80784315, 0.69411767]]),
np.array([[0.90980393, 0.8392157, 0.65098041],
[0.83137256, 0.80784315, 0.69411767],
[0.67450982, 0.52941179, 0.25490198]]),
np.array([[0.90980393, 0.8392157, 0.65098041],
[0.83137256, 0.80784315, 0.69411767],
[0.67450982, 0.52941179, 0.25490198],
[0.86666667, 0.8392157, 0.70588237]]),
np.array([[0.90980393, 0.8392157, 0.65098041],
[0.83137256, 0.80784315, 0.69411767],
[0.67450982, 0.52941179, 0.25490198],
[0.86666667, 0.8392157, 0.70588237], [0, 0, 0]]),
np.array([[0.90980393, 0.8392157, 0.65098041],
[0.83137256, 0.80784315, 0.69411767],
[0.67450982, 0.52941179, 0.25490198],
[0.86666667, 0.8392157, 0.70588237], [0, 0, 0],
[0.8392157, 0.80392158, 0.63921571]]),
]
# test different k values to find best
for k in range(k_min, k_max + 1):
updated_values = k_means_cluster(image_values, k, initial_means[k - k_min])
ref_image = image_dir + 'k%d_%s' % (k, image_name)
ref_values = image_to_matrix(ref_image)
matrix_to_image(updated_values,"./testImage-%d.png" % k)
dist = image_difference(updated_values, ref_values)
self.assertEqual(int(dist), 0, msg=("Clustering for %d clusters"
+ "produced unrealistic image segmentation.") % k)
prev_cluster_allocation = np.zeros((1, row * col))
while (1):
for cluster_number in range(k):
distance[cluster_number] = np.linalg.norm(image_values_flat -
means[cluster_number],
axis=1)
cluster_allocation = np.argmin(distance, axis=0)
if (np.array_equal(prev_cluster_allocation, cluster_allocation)):
break
else:
prev_cluster_allocation = cluster_allocation
for cluster_number in range(k):
indices = np.where(cluster_allocation == cluster_number)
means[cluster_number] = np.mean(image_values_flat[[indices]][0],
axis=0)
for cluster_number in range(k):
indices = np.where(cluster_allocation == cluster_number)
image_values_flat[[indices]] = means[cluster_number]
updated_image_values = unflatten_image_matrix(image_values_flat, col)
return updated_image_values
updated_values = k_means_cluster(image_values, 10, initial_means=None)
matrix_to_image(updated_values, 'images/kmeans.png')
