def test_alternative_image_additions():
pcgts = PcGtsType(pcGtsId="foo")
assert pcgts.pcGtsId == 'foo'
# act
# Page/AlternativeImage
page = PageType()
pcgts.set_Page(page)
page.add_AlternativeImage(AlternativeImageType())
# TextRegion/AlternativeImage
region = TextRegionType()
page.add_TextRegion(region)
region.add_AlternativeImage(AlternativeImageType())
# TextLine/AlternativeImage
line = TextLineType()
region.add_TextLine(line)
line.add_AlternativeImage(AlternativeImageType())
# Word/AlternativeImage
word = WordType()
line.add_Word(word)
word.add_AlternativeImage(AlternativeImageType())
# Glyph/AlternativeImage
glyph = GlyphType()
word.add_Glyph(glyph)
glyph.add_AlternativeImage(AlternativeImageType())
def _process_segment(self, page_image, page, page_xywh, page_id,
input_file, n, mrcnn_model, class_names):
img_array = ocrolib.pil2array(page_image)
results = mrcnn_model.detect([img_array], verbose=1)
r = results[0]
page_xywh['features'] += ',blksegmented'
for i in range(len(r['rois'])):
width, height, _ = img_array.shape
min_x = r['rois'][i][0]
min_y = r['rois'][i][1]
max_x = r['rois'][i][2]
max_y = r['rois'][i][3]
#small post-processing incase of paragrapgh to not cut last alphabets
if (min_x - 5) > width and r['class_ids'][i] == 2:
min_x -= 5
if (max_x + 10) < width and r['class_ids'][i] == 2:
min_x += 10
# this can be tested, provided whether we need previous comments or not?
region_img = img_array[min_x:max_x, min_y:
max_y] #extract from points and img_array
region_img = ocrolib.array2pil(region_img)
file_id = input_file.ID.replace(self.input_file_grp,
self.image_grp)
if file_id == input_file.ID:
file_id = concat_padded(self.image_grp, n)
file_path = self.workspace.save_image_file(region_img,
file_id + "_" + str(i),
page_id=page_id,
file_grp=self.image_grp)
ai = AlternativeImageType(filename=file_path,
comments=page_xywh['features'])
coords = CoordsType(
"%i,%i %i,%i %i,%i %i,%i" %
(min_x, min_y, max_x, min_y, max_x, max_y, min_x, max_y))
textregion = TextRegionType(Coords=coords,
type_=class_names[r['class_ids'][i]])
textregion.add_AlternativeImage(ai)
page.add_TextRegion(textregion)
def test_alternativeImage(self):
pcgts = PcGtsType(pcGtsId="foo")
self.assertEqual(pcgts.pcGtsId, 'foo')
# Page/AlternativeImage
page = PageType()
pcgts.set_Page(page)
page.add_AlternativeImage(AlternativeImageType())
# TextRegion/AlternativeImage
region = TextRegionType()
page.add_TextRegion(region)
region.add_AlternativeImage(AlternativeImageType())
# TextLine/AlternativeImage
line = TextLineType()
region.add_TextLine(line)
line.add_AlternativeImage(AlternativeImageType())
# Word/AlternativeImage
word = WordType()
line.add_Word(word)
word.add_AlternativeImage(AlternativeImageType())
# Glyph/AlternativeImage
glyph = GlyphType()
word.add_Glyph(glyph)
glyph.add_AlternativeImage(AlternativeImageType())
def test_deskewing(plain_workspace):
#from ocrd_utils import initLogging, setOverrideLogLevel
#setOverrideLogLevel('DEBUG')
size = (3000, 4000)
poly = [[1403, 2573], [1560, 2573], [1560, 2598], [2311,
2598], [2311, 2757],
[2220, 2757], [2220, 2798], [2311, 2798], [2311, 2908],
[1403, 2908]]
xywh = xywh_from_polygon(poly)
bbox = bbox_from_polygon(poly)
skew = 4.625
image = Image.new('L', size)
image = polygon_mask(image, poly)
#image.show(title='image')
pixels = np.count_nonzero(np.array(image) > 0)
name = 'foo0'
assert plain_workspace.save_image_file(image, name, 'IMG')
pcgts = page_from_file(next(plain_workspace.mets.find_files(ID=name)))
page = pcgts.get_Page()
region = TextRegionType(
id='nonrect',
Coords=CoordsType(points=points_from_polygon(poly)),
orientation=-skew)
page.add_TextRegion(region)
page_image, page_coords, _ = plain_workspace.image_from_page(page, '')
#page_image.show(title='page_image')
assert list(image.getdata()) == list(page_image.getdata())
assert np.all(page_coords['transform'] == np.eye(3))
reg_image, reg_coords = plain_workspace.image_from_segment(
region, page_image, page_coords, feature_filter='deskewed', fill=0)
assert list(image.crop(bbox).getdata()) == list(reg_image.getdata())
assert reg_image.width == xywh['w'] == 908
assert reg_image.height == xywh['h'] == 335
assert reg_coords['transform'][0, 2] == -xywh['x']
assert reg_coords['transform'][1, 2] == -xywh['y']
# same fg after cropping to minimal bbox
reg_pixels = np.count_nonzero(np.array(reg_image) > 0)
assert pixels == reg_pixels
# now with deskewing (test for size after recropping)
reg_image, reg_coords = plain_workspace.image_from_segment(region,
page_image,
page_coords,
fill=0)
#reg_image.show(title='reg_image')
assert reg_image.width == 932 > xywh['w']
assert reg_image.height == 382 > xywh['h']
assert reg_coords['transform'][0, 1] != 0
assert reg_coords['transform'][1, 0] != 0
assert 'deskewed' in reg_coords['features']
# same fg after cropping to minimal bbox (roughly - due to aliasing)
reg_pixels = np.count_nonzero(np.array(reg_image) > 0)
assert np.abs(pixels - reg_pixels) / pixels < 0.005
reg_array = np.array(reg_image) > 0
# now via AlternativeImage
path = plain_workspace.save_image_file(reg_image, region.id + '_img',
'IMG')
region.add_AlternativeImage(
AlternativeImageType(filename=path, comments=reg_coords['features']))
logger_capture = FIFOIO(256)
logger_handler = logging.StreamHandler(logger_capture)
#logger_handler.setFormatter(logging.Formatter(fmt=LOG_FORMAT, datefmt=LOG_TIMEFMT))
logger = logging.getLogger('ocrd_utils.crop_image')
logger.addHandler(logger_handler)
reg_image2, reg_coords2 = plain_workspace.image_from_segment(region,
page_image,
page_coords,
fill=0)
#reg_image2.show(title='reg_image2')
logger_output = logger_capture.getvalue()
logger_capture.close()
assert logger_output == ''
assert reg_image2.width == reg_image.width
assert reg_image2.height == reg_image.height
assert np.allclose(reg_coords2['transform'], reg_coords['transform'])
assert reg_coords2['features'] == reg_coords['features']
# same fg after cropping to minimal bbox (roughly - due to aliasing)
reg_pixels2 = np.count_nonzero(np.array(reg_image) > 0)
assert reg_pixels2 == reg_pixels
reg_array2 = np.array(reg_image2) > 0
assert 0.98 < np.sum(reg_array == reg_array2) / reg_array.size <= 1.0
