def process_image(imagename, resultname='temp.sift', dense=False):
""" process an image and save the results in a .key ascii file"""
print "working on ", imagename
if dense == False:
if imagename[-3:] != 'pgm':
#create a pgm file, image is resized, if it is too big.
# sift returns an error if more than 8000 features are found
size = (MAXSIZE, MAXSIZE)
im = Image.open(imagename).convert('L')
im.thumbnail(size, Image.ANTIALIAS)
im.save('tmp.pgm')
imagename = 'tmp.pgm'
#check if linux or windows
if os.name == "posix":
cmmd = "./sift <" + imagename + ">" + resultname
print cmmd
else:
cmmd = "siftWin32 <" + imagename + ">" + resultname
os.system(cmmd)
if os.path.getsize(resultname) == 0:
raise IOError("extracting SIFT features failed " + resultname)
else:
import vlfeat
# defines how dense the grid is
size = (150, 150)
step = 10
im = Image.open(imagename).resize(size, Image.ANTIALIAS)
im_array = numpy.asarray(im)
if im_array.ndim == 3:
im_gray = vlfeat.vl_rgb2gray(im_array)
elif im_array.ndim == 2:
im_gray = im_array
else:
raise IOError("Not enough dims found in image " + resultname)
locs, int_descriptors = vlfeat.vl_dsift(im_gray, step=step, verbose=VERBOSE)
nfeatures = int_descriptors.shape[1]
padding = numpy.zeros((2, nfeatures))
locs = numpy.vstack((locs, padding))
header = ' '.join([str(nfeatures), str(128)])
temp = int_descriptors.astype('float') # convert descriptors to float
descriptors = temp[:]
with open(resultname, 'wb') as f:
cPickle.dump([locs.T, descriptors.T], f, protocol=cPickle.HIGHEST_PROTOCOL)
print "features saved in", resultname
if WRITE_VERBOSE:
with open(resultname, 'w') as f:
f.write(header)
f.write("\n")
for i in range(nfeatures):
f.write(' '.join(map(str, locs[:, i])))
f.write("\n")
f.write(' '.join(map(str, descriptors[:, i])))
f.write("\n")
def extract_feature_vector(self):
img = imread(self.image.get_path()) if self.memory == False else self.image
imgResized = resize(img, (300,250))
grayScaleImg = vl_rgb2gray(imgResized).astype('uint8')
histEqualizedImage = equalizeHist(grayScaleImg)
sizeOfSpatialBins = 8
step = 10
fast = False #if set to True it uses a flat window rather than a Gaussian window
verbose = False
norm = False
bounds = -1
frames ,descriptors = vl_dsift(histEqualizedImage,step,bounds,sizeOfSpatialBins,fast,verbose,norm)
return descriptors.transpose().astype('float32')
def vl_phow(im,
verbose=True,
fast=True,
sizes=[4, 6, 8, 10],
step=2,
color='rgb',
floatdescriptors=False,
magnif=6,
windowsize=1.5,
contrastthreshold=0.005):
opts = Options(verbose, fast, sizes, step, color, floatdescriptors, magnif,
windowsize, contrastthreshold)
dsiftOpts = DSiftOptions(opts)
# make sure image is float, otherwise segfault
im = array(im, 'float32')
# Extract the features
imageSize = shape(im)
if im.ndim == 3:
if imageSize[2] != 3:
# "IndexError: tuple index out of range" if both if's are checked at the same time
raise ValueError("Image data in unknown format/shape")
if opts.color == 'gray':
numChannels = 1
if (im.ndim == 2):
im = vl_rgb2gray(im)
else:
numChannels = 3
if (im.ndim == 2):
im = dstack([im, im, im])
if opts.color == 'rgb':
pass
elif opts.color == 'opponent':
# from https://github.com/vlfeat/vlfeat/blob/master/toolbox/sift/vl_phow.m
# Note that the mean differs from the standard definition of opponent
# space and is the regular intesity (for compatibility with
# the contrast thresholding).
# Note also that the mean is added pack to the other two
# components with a small multipliers for monochromatic
# regions.
mu = 0.3 * im[:, :, 0] + 0.59 * im[:, :, 1] + 0.11 * im[:, :, 2]
alpha = 0.01
im = dstack([
mu, (im[:, :, 0] - im[:, :, 1]) / sqrt(2) + alpha * mu,
(im[:, :, 0] + im[:, :, 1] - 2 * im[:, :, 2]) / sqrt(6) +
alpha * mu
])
else:
raise ValueError('Color option ' + str(opts.color) +
' not recognized')
if opts.verbose:
print('{0}: color space: {1}'.format('vl_phow', opts.color))
print('{0}: image size: {1} x {2}'.format('vl_phow', imageSize[0],
imageSize[1]))
print('{0}: sizes: [{1}]'.format('vl_phow', opts.sizes))
frames_all = []
descrs_all = []
for size_of_spatial_bins in opts.sizes:
# from https://github.com/vlfeat/vlfeat/blob/master/toolbox/sift/vl_phow.m
# Recall from VL_DSIFT() that the first descriptor for scale SIZE has
# center located at XC = XMIN + 3/2 SIZE (the Y coordinate is
# similar). It is convenient to align the descriptors at different
# scales so that they have the same geometric centers. For the
# maximum size we pick XMIN = 1 and we get centers starting from
# XC = 1 + 3/2 MAX(OPTS.SIZES). For any other scale we pick XMIN so
# that XMIN + 3/2 SIZE = 1 + 3/2 MAX(OPTS.SIZES).
# In pracrice, the offset must be integer ('bounds'), so the
# alignment works properly only if all OPTS.SZES are even or odd.
off = floor(3.0 / 2 * (max(opts.sizes) - size_of_spatial_bins)) + 1
# smooth the image to the appropriate scale based on the size
# of the SIFT bins
sigma = size_of_spatial_bins / float(opts.magnif)
ims = vl_imsmooth(im, sigma)
# extract dense SIFT features from all channels
frames = []
descrs = []
for k in range(numChannels):
size_of_spatial_bins = int(size_of_spatial_bins)
# vl_dsift does not accept numpy.int64 or similar
f_temp, d_temp = vl_dsift(data=ims[:, :, k],
step=dsiftOpts.step,
size=size_of_spatial_bins,
fast=dsiftOpts.fast,
verbose=dsiftOpts.verbose,
norm=dsiftOpts.norm,
bounds=[off, off, maxint, maxint])
frames.append(f_temp)
descrs.append(d_temp)
frames = array(frames)
descrs = array(descrs)
d_new_shape = [descrs.shape[0] * descrs.shape[1], descrs.shape[2]]
descrs = descrs.reshape(d_new_shape)
# remove low contrast descriptors
# note that for color descriptors the V component is
# thresholded
if (opts.color == 'gray') | (opts.color == 'opponent'):
contrast = frames[0][2, :]
elif opts.color == 'rgb':
contrast = mean(
[frames[0][2, :], frames[1][2, :], frames[2][2, :]], 0)
else:
raise ValueError('Color option ' + str(opts.color) +
' not recognized')
descrs[:, contrast < opts.contrastthreshold] = 0
# save only x,y, and the scale
frames_temp = array(frames[0][0:3, :])
padding = array(size_of_spatial_bins * ones(frames[0][0].shape))
frames_all.append(vstack([frames_temp, padding]))
descrs_all.append(array(descrs))
frames_all = hstack(frames_all)
descrs_all = hstack(descrs_all)
return frames_all, descrs_all
def process_image(imagename, resultname='temp.sift', dense=False):
""" process an image and save the results in a .key ascii file"""
print "working on ", imagename
if dense == False:
if imagename[-3:] != 'pgm':
#create a pgm file, image is resized, if it is too big.
# sift returns an error if more than 8000 features are found
size = (MAXSIZE, MAXSIZE)
im = Image.open(imagename).convert('L')
im.thumbnail(size, Image.ANTIALIAS)
im.save('tmp.pgm')
imagename = 'tmp.pgm'
#check if linux or windows
if os.name == "posix":
cmmd = "./sift <" + imagename + ">" + resultname
print cmmd
else:
cmmd = "siftWin32 <" + imagename + ">" + resultname
os.system(cmmd)
if os.path.getsize(resultname) == 0:
raise IOError("extracting SIFT features failed " + resultname)
#print 'processed', imagename
else:
import vlfeat
# like in pinto2008 why is vision hard
size = (150, 150)
window_size = 8
step = 10
im = Image.open(imagename).resize(size, Image.ANTIALIAS)
im_array = numpy.asarray(im)
if im_array.ndim == 3:
im_gray = vlfeat.vl_rgb2gray(im_array)
elif im_array.ndim == 2:
im_gray = im_array
else:
raise IOError("Not enough dims found in image " + resultname)
#locs,int_descriptors = vlfeat.vl_dsift(im_gray,size=window_size,verbose=VERBOSE)
locs, int_descriptors = vlfeat.vl_dsift(im_gray,
step=step,
verbose=VERBOSE)
nfeatures = int_descriptors.shape[1]
padding = numpy.zeros((2, nfeatures))
locs = numpy.vstack((locs, padding))
header = ' '.join([str(nfeatures), str(128)])
temp = int_descriptors.astype('float') # convert descriptors to float
descriptors = temp[:]
with open(resultname, 'wb') as f:
cPickle.dump([locs.T, descriptors.T],
f,
protocol=cPickle.HIGHEST_PROTOCOL)
print "features saved in", resultname
if WRITE_VERBOSE:
with open(resultname, 'w') as f:
f.write(header)
f.write("\n")
for i in range(nfeatures):
f.write(' '.join(map(str, locs[:, i])))
f.write("\n")
f.write(' '.join(map(str, descriptors[:, i])))
f.write("\n")
def dsift(im,
verbose=True,
fast=True,
sizes=[4, 6, 8, 10],
step=2,
color='rgb',
floatdescriptors=False,
magnif=6,
windowsize=1.5,
contrastthreshold=0.005):
opts = Options(verbose, fast, sizes, step, color, floatdescriptors,
magnif, windowsize, contrastthreshold)
dsiftOpts = DSiftOptions(opts)
# make sure image is float, otherwise segfault
im = array(im, 'float32')
# Extract the features
imageSize = shape(im)
if im.ndim == 3:
if imageSize[2] != 3:
# "IndexError: tuple index out of range" if both if's are checked at the same time
raise ValueError("Image data in unknown format/shape")
if opts.color == 'gray':
numChannels = 1
if (im.ndim == 2):
im = vl_rgb2gray(im)
else:
numChannels = 3
if (im.ndim == 2):
im = dstack([im, im, im])
if opts.color == 'rgb':
pass
elif opts.color == 'opponent':
# from https://github.com/vlfeat/vlfeat/blob/master/toolbox/sift/vl_phow.m
# Note that the mean differs from the standard definition of opponent
# space and is the regular intesity (for compatibility with
# the contrast thresholding).
# Note also that the mean is added pack to the other two
# components with a small multipliers for monochromatic
# regions.
mu = 0.3 * im[:, :, 0] + 0.59 * im[:, :, 1] + 0.11 * im[:, :, 2]
alpha = 0.01
im = dstack([mu,
(im[:, :, 0] - im[:, :, 1]) / sqrt(2) + alpha * mu,
(im[:, :, 0] + im[:, :, 1] - 2 * im[:, :, 2]) / sqrt(6) + alpha * mu])
else:
raise ValueError('Color option ' + str(opts.color) + ' not recognized')
if opts.verbose:
great='great'
#print('{0}: color space: {1}'.format('vl_phow', opts.color))
#print('{0}: image size: {1} x {2}'.format('vl_phow', imageSize[0], imageSize[1]))
#print('{0}: sizes: [{1}]'.format('vl_phow', opts.sizes))
frames_all = []
descrs_all = []
for size_of_spatial_bins in opts.sizes:
# from https://github.com/vlfeat/vlfeat/blob/master/toolbox/sift/vl_phow.m
# Recall from VL_DSIFT() that the first descriptor for scale SIZE has
# center located at XC = XMIN + 3/2 SIZE (the Y coordinate is
# similar). It is convenient to align the descriptors at different
# scales so that they have the same geometric centers. For the
# maximum size we pick XMIN = 1 and we get centers starting from
# XC = 1 + 3/2 MAX(OPTS.SIZES). For any other scale we pick XMIN so
# that XMIN + 3/2 SIZE = 1 + 3/2 MAX(OPTS.SIZES).
# In pracrice, the offset must be integer ('bounds'), so the
# alignment works properly only if all OPTS.SZES are even or odd.
off = floor(3.0 / 2 * (max(opts.sizes) - size_of_spatial_bins)) + 1
# smooth the image to the appropriate scale based on the size
# of the SIFT bins
sigma = size_of_spatial_bins / float(opts.magnif)
ims = vl_imsmooth(im, sigma)
# extract dense SIFT features from all channels
frames = []
descrs = []
for k in range(numChannels):
size_of_spatial_bins = int(size_of_spatial_bins)
# vl_dsift does not accept numpy.int64 or similar
f_temp, d_temp = vl_dsift(data=ims[:, :, k],
step=dsiftOpts.step,
size=size_of_spatial_bins,
fast=dsiftOpts.fast,
verbose=dsiftOpts.verbose,
norm=dsiftOpts.norm,
bounds=[off, off, maxint, maxint])
frames.append(f_temp)
descrs.append(d_temp)
frames = array(frames)
descrs = array(descrs)
d_new_shape = [descrs.shape[0] * descrs.shape[1], descrs.shape[2]]
descrs = descrs.reshape(d_new_shape)
# remove low contrast descriptors
# note that for color descriptors the V component is
# thresholded
if (opts.color == 'gray') | (opts.color == 'opponent'):
contrast = frames[0][2, :]
elif opts.color == 'rgb':
contrast = mean([frames[0][2, :], frames[1][2, :], frames[2][2, :]], 0)
else:
raise ValueError('Color option ' + str(opts.color) + ' not recognized')
descrs[:, contrast < opts.contrastthreshold] = 0
# save only x,y, and the scale
frames_temp = array(frames[0][0:3, :])
padding = array(size_of_spatial_bins * ones(frames[0][0].shape))
frames_all.append(vstack([frames_temp, padding]))
descrs_all.append(array(descrs))
frames_all = hstack(frames_all)
descrs_all = hstack(descrs_all)
return frames_all, descrs_all
import Image
import numpy
import pylab
import vlfeat
from vlfeat.plotop.vl_plotframe import vl_plotframe
from numpy.random import shuffle
if __name__ == '__main__':
# VL_DEMO_SIFT_BASIC Demo: SIFT: basic functionality
# --------------------------------------------------------------------
# Load a figure and convert the to required format
# --------------------------------------------------------------------
I = Image.open('../../../data/a.jpg')
I = vlfeat.vl_rgb2gray(numpy.array(I))
I = numpy.array(I, 'f', order='F') # 'F' = column-major order!
pylab.gray()
pylab.imshow(I)
print 'sift_basic_1'
# --------------------------------------------------------------------
# Run SIFT
# --------------------------------------------------------------------
f, d = vlfeat.vl_sift(I)
sel = numpy.arange(f.shape[1])
shuffle(sel)
vl_plotframe(f[:, sel[:50]], color='k', linewidth=3)
vl_plotframe(f[:, sel[:50]], color='y')
def process_image(imagename, resultname='temp.sift', dense=False):
""" process an image and save the results in a .key ascii file"""
#print "working on ", imagename
if dense == False:
if imagename[-3:] != 'pgm':
#create a pgm file, image is resized, if it is too big.
# sift returns an error if more than 8000 features are found
size = (MAXSIZE, MAXSIZE)
im = Image.open(imagename).convert('L')
im.thumbnail(size, Image.ANTIALIAS)
im.save('tmp.pgm')
imagename = 'tmp.pgm'
#check if linux or windows
if os.name == "posix":
cmmd = "./sift < " + imagename + " > " + resultname
else:
cmmd = "siftWin32 < " + imagename + " > " + resultname
# run extraction command
returnvalue = subprocess.call(cmmd, shell=True)
if returnvalue == 127:
os.remove(resultname) # removing empty resultfile created by output redirection
raise IOError("SIFT executable not found")
if returnvalue == 2:
os.remove(resultname) # removing empty resultfile created by output redirection
raise IOError("image " + imagename + " not found")
if os.path.getsize(resultname) == 0:
raise IOError("extracting SIFT features failed " + resultname)
else:
import vlfeat
# defines how dense the grid is
size = (150, 150)
step = 10
im = Image.open(imagename).resize(size, Image.ANTIALIAS)
im_array = numpy.asarray(im)
if im_array.ndim == 3:
im_gray = vlfeat.vl_rgb2gray(im_array)
elif im_array.ndim == 2:
im_gray = im_array
else:
raise IOError("Not enough dims found in image " + resultname)
locs, int_descriptors = vlfeat.vl_dsift(im_gray, step=step, verbose=VERBOSE)
nfeatures = int_descriptors.shape[1]
padding = numpy.zeros((2, nfeatures))
locs = numpy.vstack((locs, padding))
header = ' '.join([str(nfeatures), str(128)])
temp = int_descriptors.astype('float') # convert descriptors to float
descriptors = temp[:]
with open(resultname, 'wb') as f:
cPickle.dump([locs.T, descriptors.T], f, protocol=cPickle.HIGHEST_PROTOCOL)
print "features saved in", resultname
if WRITE_VERBOSE:
with open(resultname, 'w') as f:
f.write(header)
f.write("\n")
for i in range(nfeatures):
f.write(' '.join(map(str, locs[:, i])))
f.write("\n")
f.write(' '.join(map(str, descriptors[:, i])))
f.write("\n")
def process_image(imagename, resultname="temp.sift", dense=False):
""" process an image and save the results in a .key ascii file"""
print "working on ", imagename
if dense == False:
if imagename[-3:] != "pgm":
# create a pgm file, image is resized, if it is too big.
# sift returns an error if more than 8000 features are found
size = (MAXSIZE, MAXSIZE)
im = Image.open(imagename).convert("L")
im.thumbnail(size, Image.ANTIALIAS)
im.save("tmp.pgm")
imagename = "tmp.pgm"
# check if linux or windows
if os.name == "posix":
cmmd = "./sift < " + imagename + " > " + resultname
else:
cmmd = "siftWin32 < " + imagename + " > " + resultname
# run extraction command
returnvalue = subprocess.call(cmmd, shell=True)
if returnvalue == 127:
os.remove(resultname) # removing empty resultfile created by output redirection
raise IOError("SIFT executable not found")
if returnvalue == 2:
os.remove(resultname) # removing empty resultfile created by output redirection
raise IOError("image " + imagename + " not found")
if os.path.getsize(resultname) == 0:
raise IOError("extracting SIFT features failed " + resultname)
else:
import vlfeat
# defines how dense the grid is
size = (150, 150)
step = 10
im = Image.open(imagename).resize(size, Image.ANTIALIAS)
im_array = numpy.asarray(im)
if im_array.ndim == 3:
im_gray = vlfeat.vl_rgb2gray(im_array)
elif im_array.ndim == 2:
im_gray = im_array
else:
raise IOError("Not enough dims found in image " + resultname)
locs, int_descriptors = vlfeat.vl_dsift(im_gray, step=step, verbose=VERBOSE)
nfeatures = int_descriptors.shape[1]
padding = numpy.zeros((2, nfeatures))
locs = numpy.vstack((locs, padding))
header = " ".join([str(nfeatures), str(128)])
temp = int_descriptors.astype("float") # convert descriptors to float
descriptors = temp[:]
with open(resultname, "wb") as f:
cPickle.dump([locs.T, descriptors.T], f, protocol=cPickle.HIGHEST_PROTOCOL)
print "features saved in", resultname
if WRITE_VERBOSE:
with open(resultname, "w") as f:
f.write(header)
f.write("\n")
for i in range(nfeatures):
f.write(" ".join(map(str, locs[:, i])))
f.write("\n")
f.write(" ".join(map(str, descriptors[:, i])))
f.write("\n")