1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
|
"""
===============================
Fisher vector feature encoding
===============================
A Fisher vector is an image feature encoding and quantization technique that
can be seen as a soft or probabilistic version of the popular
bag-of-visual-words or VLAD algorithms. Images are modelled using a visual
vocabulary which is estimated using a K-mode Gaussian mixture model trained on
low-level image features such as SIFT or ORB descriptors. The Fisher vector
itself is a concatenation of the gradients of the Gaussian mixture model (GMM)
with respect to its parameters - mixture weights, means, and covariance
matrices.
In this example, we compute Fisher vectors for the digits dataset in
scikit-learn, and train a classifier on these representations.
Please note that scikit-learn is required to run this example.
"""
from matplotlib import pyplot as plt
import numpy as np
from sklearn.datasets import load_digits
from sklearn.metrics import classification_report, ConfusionMatrixDisplay
from sklearn.model_selection import train_test_split
from sklearn.svm import LinearSVC
from skimage.transform import resize
from skimage.feature import fisher_vector, ORB, learn_gmm
data = load_digits()
images = data.images
targets = data.target
# Resize images so that ORB detects interest points for all images
images = np.array([resize(image, (80, 80)) for image in images])
# Compute ORB descriptors for each image
descriptors = []
for image in images:
detector_extractor = ORB(n_keypoints=5, harris_k=0.01)
detector_extractor.detect_and_extract(image)
descriptors.append(detector_extractor.descriptors.astype('float32'))
# Split the data into training and testing subsets
train_descriptors, test_descriptors, train_targets, test_targets = train_test_split(
descriptors, targets
)
# Train a K-mode GMM
k = 16
gmm = learn_gmm(train_descriptors, n_modes=k)
# Compute the Fisher vectors
training_fvs = np.array(
[fisher_vector(descriptor_mat, gmm) for descriptor_mat in train_descriptors]
)
testing_fvs = np.array(
[fisher_vector(descriptor_mat, gmm) for descriptor_mat in test_descriptors]
)
svm = LinearSVC().fit(training_fvs, train_targets)
predictions = svm.predict(testing_fvs)
print(classification_report(test_targets, predictions))
ConfusionMatrixDisplay.from_estimator(
svm,
testing_fvs,
test_targets,
cmap=plt.cm.Blues,
)
plt.show()
|
