def compute_texture(im):
'''Compute features for an image
Parameters
----------
im : str
filepath for image to process
Returns
-------
fs : ndarray
1-D array of features
'''
from features import texture
imc = mh.imread(im)
return texture(mh.colors.rgb2grey(imc))
def compute_texture(im):
'''Compute features for an image
Parameters
----------
im : str
filepath for image to process
Returns
-------
fs : ndarray
1-D array of features
'''
from features import texture
imc = mh.imread(im)
return texture(mh.colors.rgb2grey(imc))
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
basedir = 'SimpleImageDataset/'
haralick, labels, chistogram = [], [], []
print(
'This script will test (with cross-validation) classification of the simple 3 class dataset'
)
print('Computing features...')
# Use glob to get all the images
images = glob('{}/*.jpg'.format(basedir))
for fname in sorted(images):
imc = mh.imread(fname)
haralick.append(texture(mh.colors.rgb2gray(imc)))
chistogram.append(chist(imc))
labels.append(fname[:-len('xx.jpg')])
print('Finished computing features.')
haralick = np.array(haralick)
chistogram = np.array(chistogram)
labels = np.array(labels)
haralick_plus_chist = np.hstack([chistogram, haralick])
clf = Pipeline([('preproc', StandardScaler()),
('classifier', LogisticRegression())])
from sklearn import cross_validation
haralicks = []
sobels = []
labels = []
print('This script will test (with cross-validation) classification of the simple 3 class dataset')
print('Computing features...')
# Use glob to get all the images
images = glob('{}/*.jpg'.format(basedir))
# We sort the images to ensure that they are always processed in the same order
# Otherwise, this would introduce some variation just based on the random
# ordering that the filesystem uses
for fname in sorted(images):
im = mh.imread(fname, as_grey=True)
haralicks.append(texture(im))
sobels.append(edginess_sobel(im))
# Files are named like building00.jpg, scene23.jpg...
labels.append(fname[:-len('xx.jpg')])
print('Finished computing features.')
haralicks = np.array(haralicks)
sobels = np.array(sobels)
labels = np.array(labels)
# We use logistic regression because it is very fast.
# Feel free to experiment with other classifiers
scores = cross_validation.cross_val_score(
LogisticRegression(), haralicks, labels, cv=5)
sobels = []
labels = []
print(
'This script will test (with cross-validation) classification of the simple 3 class dataset'
)
print('Computing features...')
# Use glob to get all the images
images = glob('{}/*.jpg'.format(basedir))
# We sort the images to ensure that they are always processed in the same order
# Otherwise, this would introduce some variation just based on the random
# ordering that the filesystem uses
for fname in sorted(images):
im = mh.imread(fname, as_grey=True)
haralicks.append(texture(im))
sobels.append(edginess_sobel(im))
# Files are named like building00.jpg, scene23.jpg...
labels.append(fname[:-len('xx.jpg')])
print('Finished computing features.')
haralicks = np.array(haralicks)
sobels = np.array(sobels)
labels = np.array(labels)
# We use logistic regression because it is very fast.
# Feel free to experiment with other classifiers
scores = cross_validation.cross_val_score(LogisticRegression(),
haralicks,
def compute_texture(im):
from features import texture
imc = mh.imread(im)
return texture(mh.colors.rgb2gray(imc))
labels = []
chists = []
print(
'This script will test (with cross-validation) classification of the simple 3 class dataset'
)
print('Computing features...')
# Use glob to get all the images
images = glob('{}/*.jpg'.format(basedir))
# We sort the images to ensure that they are always processed in the same order
# Otherwise, this would introduce some variation just based on the random
# ordering that the filesystem uses
for fname in sorted(images):
imc = mh.imread(fname)
haralicks.append(texture(mh.colors.rgb2grey(imc)))
chists.append(color_histogram(imc))
# Files are named like building00.jpg, scene23.jpg...
labels.append(fname[:-len('xx.jpg')])
print('Finished computing features.')
haralicks = np.array(haralicks)
labels = np.array(labels)
chists = np.array(chists)
haralick_plus_chists = np.hstack([chists, haralicks])
# We use Logistic Regression because it achieves high accuracy on small(ish) datasets
# Feel free to experiment with other classifiers
def compute_texture(im):
from features import texture
imc = mh.imread(im)
return texture(mh.colors.rgb2gray(imc))
haralicks = []
labels = []
chists = []
print('This script will test (with cross-validation) classification of the simple 3 class dataset')
print('Computing features...')
# Use glob to get all the images
images = glob('{}/*.jpg'.format(basedir))
# We sort the images to ensure that they are always processed in the same order
# Otherwise, this would introduce some variation just based on the random
# ordering that the filesystem uses
for fname in sorted(images):
imc = mh.imread(fname)
haralicks.append(texture(mh.colors.rgb2grey(imc)))
chists.append(color_histogram(imc))
# Files are named like building00.jpg, scene23.jpg...
labels.append(fname[:-len('xx.jpg')])
print('Finished computing features.')
haralicks = np.array(haralicks)
labels = np.array(labels)
chists = np.array(chists)
haralick_plus_chists = np.hstack([chists, haralicks])
# We use Logistic Regression because it achieves high accuracy on small(ish) datasets