def test_decompose_and_resize():
words = [("abcd", 4), ("ijkl", 6), ("şğuf", 5), ("ibadullah", 10)]
for w, expected in words:
w_img = aui.get_gray_word_image(w,
fontname="Amiri",
dpi=600,
background=0,
foreground=255)
component_imgs = aui.decompose_and_resize(w_img, size_x=64, size_y=64)
LOG.debug("=== component_imgs.shape ===")
LOG.debug(component_imgs.shape)
res_n, res_rows, res_cols = component_imgs.shape
assert (res_rows, res_cols) == (64, 64)
assert res_n == expected, "w: {}, res_n: {}, expected: {}".format(
w, res_n, expected)
for j in range(res_n):
c_img = component_imgs[j]
bb = aui.img_bounding_box(c_img)
LOG.debug("=== bb ===")
LOG.debug(bb)
if np.any(bb > 0):
assert (bb[0, 0], bb[0, 1]) == (0, 64)
assert (bb[1, 0], bb[1, 1]) == (0, 64)
def random_img():
num_words_in_text = nr.randint(num_words_min, num_words_max)
text = " ".join(
[w.strip() for w in list(nr.choice(words, num_words_in_text))])
fg = nr.randint(fg_min, fg_max)
bg = nr.randint(bg_min, bg_max)
font = nr.choice(fonts)
dpi = nr.randint(dpi_min, dpi_max)
return aui.get_gray_word_image(text, font, dpi, bg, fg)
def create_letter_group_image(lg, font, dpi, output_dir):
otm = aua.visenc_to_arabic(lg)
word_image = aui.get_gray_word_image(otm,
fontname=font,
dpi=dpi,
background=0,
foreground=255)
components, stats = aui.text_image_segmentation(word_image)
LOG.debug("=== lg ===")
LOG.debug(lg)
LOG.debug("=== components.shape ===")
LOG.debug(components.shape)
LOG.debug("=== stats.shape ===")
LOG.debug(stats.shape)
# aui.write_image_array(components, lg)
stats_sorted_area = np.argsort(stats['area'])
stem_label = aua.delete_visenc_diacritics(lg)
li = stats_sorted_area[-1]
largest = components[li]
largest_dir = os.path.join(output_dir, stem_label)
largest_file = os.path.join(
largest_dir, "cc-{}-font-{}-dpi-{}-w-{}-h-{}-area-{}.png".format(
stem_label,
font.replace(" ", "").lower(), dpi, stats[li]["w"], stats[li]["h"],
stats[li]["area"]))
LOG.debug("=== stem_label ===")
LOG.debug(stem_label)
if not os.path.isdir(largest_dir):
os.makedirs(largest_dir)
cv2.imwrite(largest_file, largest)
if len(stats) == 2: # if there is a single diacritic
di = stats_sorted_area[0]
diacritic = components[di]
diacritic_label = aua.delete_visenc_stems(lg)
n_diacritics = (diacritic_label.count('o') +
diacritic_label.count('u') +
diacritic_label.count('i'))
if n_diacritics == 1:
diacritic_label = re.sub(r'^[oui]?(.*)', r'\1', diacritic_label)
LOG.debug("=== diacritic_label ===")
LOG.debug(diacritic_label)
diacritic_dir = os.path.join(output_dir, diacritic_label)
diacritic_file = os.path.join(
diacritic_dir,
"cc-{}-font-{}-dpi-{}-w-{}-h-{}-area-{}.png".format(
diacritic_label,
font.replace(" ", "").lower(), dpi, stats[di]["w"],
stats[di]["h"], stats[di]["area"]))
if not os.path.isdir(diacritic_dir):
os.makedirs(diacritic_dir)
cv2.imwrite(diacritic_file, diacritic)
def create_word_images(word, fonts=['Amiri', 'Droid Sans Arabic'], dpis=[1200]):
res_list = []
for font in fonts:
for dpi in dpis:
word_img = aui.get_gray_word_image(word,
fontname=font,
dpi=dpi,
background=0,
foreground=255)
res_list.append(word_img)
return res_list
def test_generate_component_map():
words = [("abcd", 4), ("ijkl", 6), ("şğuf", 5), ("ibadullah", 10)]
for w, expected in words:
w_img = aui.get_gray_word_image(w,
fontname="Amiri",
dpi=600,
background=0,
foreground=255)
LOG.debug("=== w_img.shape ===")
LOG.debug(w_img.shape)
imgs, stats = aui.text_image_segmentation(w_img)
component_map_1 = aui.generate_component_map(stats, PROXIMITY_BOUND=1)
component_map_2 = aui.generate_component_map(stats, PROXIMITY_BOUND=2)
assert component_map_1.shape[0] < component_map_2.shape[0]
def test_text_image_segmentation():
words = [("abcd", 4), ("ijkl", 6), ("şğuf", 5), ("ibadullah", 10)]
for w, expected in words:
w_img = aui.get_gray_word_image(w,
fontname="Amiri",
dpi=600,
background=0,
foreground=255)
LOG.debug("=== w_img.shape ===")
LOG.debug(w_img.shape)
imgs, stats = aui.text_image_segmentation(w_img)
res_n, res_rows, res_cols = imgs.shape
assert (res_rows, res_cols) == w_img.shape
assert res_n == expected, "w: {}, res_n: {}, expected: {}".format(
w, res_n, expected)
def test_generate_component_graph():
import matplotlib.pyplot as plt
import networkx as nx
words = [("abcd", 4), ("ijkl", 6), ("şğuf", 5), ("ibadullah", 10)]
for w, expected in words:
w_img = aui.get_gray_word_image(w,
fontname="Amiri",
dpi=600,
background=0,
foreground=255)
LOG.debug("=== w_img.shape ===")
LOG.debug(w_img.shape)
imgs, stats = aui.text_image_segmentation(w_img)
component_map = aui.generate_component_map(stats, PROXIMITY_BOUND=0.5)
graph = aui.component_map_to_nx(stats, component_map)
pos = nx.spring_layout(graph)
nx.draw_networkx_nodes(graph, pos)
nx.draw_networkx_edges(graph, pos)
plt.savefig('/tmp/{}-graph.png'.format(w))
plt.clf()
assert nx.number_of_nodes(graph) == expected