patch = normalise(patch)
descs[i] = patch.flatten()
# OK, these are the labels of our observation !
labels = euclidean_distances(descs, voc).argmin(axis=1)
# Now, we can compute the emission probability matrices
emission_obs = emission[:, labels].T
alphas = vdhmms.alpha(transition,
emission_obs,
occurances,
p_init=first_letter.reshape((len(first_letter), )))
betas = vdhmms.beta(transition,
emission_obs,
occurances,
p_init=last_letter.reshape((len(first_letter), )))
show_segments(im, segments)
g = alphas * betas
chain = g.argmax(axis=1)
prob = g.max(axis=1)
# careful ! Some labels of the chain "just" correspond to null probabilities
letters = 'abcdefghijklmnopqrstuvwxyz'
labels = []
for p, l in zip(prob, chain):
if p == 0:
labels.append('_')
else:
labels.append(letters[l])
d = [len(l) for l in letters_list[letter]]
ave_letter.append([
sum(m) / len(letters_list[letter]),
sum(d) / len(letters_list[letter])
])
# OK, now we have all the letters initialized
num = 0
texts = load_text_images()
for image, text in texts:
words = text.split()
segments = find_words(image)
bits = split_on(image, segments, clean=True)
# Just to check if we have segmented properly !
show_segments(image,
segments,
title=('./text_seg/%s' % text.replace(' ', '_')),
save=True)
if len(bits) != len(words):
print "problem with image %s" % text
continue
for im, word in zip(bits, words):
h, w = im.shape
seg = find_letters(im)
el = split_on(im, seg)
database.append([word, el])
show_segments(im,
seg,
title=('./word_seg/' + str(num) + '_' + word),
save=True)
labels = []
for i, patch in enumerate(patches):
patch = imresize(patch, (h, w))
patch = normalise(patch)
descs[i] = patch.flatten()
# OK, these are the labels of our observation !
labels = euclidean_distances(descs, voc).argmin(axis=1)
# Now, we can compute the emission probability matrices
emission_obs = emission[:, labels].T
alphas = vdhmms.alpha(transition, emission_obs, occurances,
p_init=first_letter.reshape((len(first_letter), )))
betas = vdhmms.beta(transition, emission_obs, occurances,
p_init=last_letter.reshape((len(first_letter), )))
show_segments(im, segments)
g = alphas * betas
chain = g.argmax(axis=1)
prob = g.max(axis=1)
# careful ! Some labels of the chain "just" correspond to null probabilities
letters = 'abcdefghijklmnopqrstuvwxyz'
labels = []
for p, l in zip(prob, chain):
if p == 0:
labels.append('_')
else:
labels.append(letters[l])
d = [len(l) for l in letters_list[letter]]
ave_letter.append(
[sum(m) / len(letters_list[letter]),
sum(d) / len(letters_list[letter])])
# OK, now we have all the letters initialized
num = 0
texts = load_text_images()
for image, text in texts:
words = text.split()
segments = find_words(image)
bits = split_on(image, segments, clean=True)
# Just to check if we have segmented properly !
show_segments(image, segments,
title=('./text_seg/%s' % text.replace(' ', '_')),
save=True)
if len(bits) != len(words):
print "problem with image %s" % text
continue
for im, word in zip(bits, words):
h, w = im.shape
seg = find_letters(im)
el = split_on(im, seg)
database.append([word, el])
show_segments(im, seg,
title=('./word_seg/' + str(num) + '_' + word),
save=True)
labels = []
print ("computing word '%s' of length %d splitted in %d"
