def process(self):
"""
Performs the line segmentation.
"""
with PyTessBaseAPI(path=TESSDATA_PREFIX) as tessapi:
for (n, input_file) in enumerate(self.input_files):
pcgts = from_file(self.workspace.download_file(input_file))
image_url = pcgts.get_Page().imageFilename
for region in pcgts.get_Page().get_TextRegion():
log.debug("Detecting lines in %s with tesseract",
region.id)
image = self.workspace.resolve_image_as_pil(
image_url,
polygon_from_points(region.get_Coords().points))
tessapi.SetImage(image)
offset = xywh_from_points(region.get_Coords().points)
for (line_no, component) in enumerate(
tessapi.GetComponentImages(RIL.TEXTLINE, True)):
line_id = '%s_line%04d' % (region.id, line_no)
line_xywh = component[1]
line_xywh['x'] += offset['x']
line_xywh['y'] += offset['y']
line_points = points_from_xywh(line_xywh)
region.add_TextLine(
TextLineType(id=line_id,
Coords=CoordsType(line_points)))
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
basename=ID + '.xml',
mimetype=MIMETYPE_PAGE,
content=to_xml(pcgts).encode('utf-8'),
)
def test_points_from_xywh(self):
self.assertEqual(
points_from_xywh({
'x': 100,
'y': 100,
'w': 100,
'h': 100
}), '100,100 200,100 200,200 100,200')
def process(self):
"""
Performs the region segmentation.
"""
with tesserocr.PyTessBaseAPI(path=TESSDATA_PREFIX) as tessapi:
print(self.input_file_grp)
for (n, input_file) in enumerate(self.input_files):
pcgts = from_file(self.workspace.download_file(input_file))
image = self.workspace.resolve_image_as_pil(
pcgts.get_Page().imageFilename)
log.debug("Detecting regions with tesseract")
tessapi.SetImage(image)
for component in tessapi.GetComponentImages(
tesserocr.RIL.BLOCK, True):
points, index = points_from_xywh(
component[1]), component[2]
#
# the region reference in the reading order element
#
ID = "region%04d" % index
log.debug("Detected region '%s': %s", ID, points)
# <pg:ReadingOrder>
ro = pcgts.get_Page().get_ReadingOrder()
if ro is None:
ro = ReadingOrderType()
pcgts.get_Page().set_ReadingOrder(ro)
# <pg:OrderedGroup>
og = ro.get_OrderedGroup()
if og is None:
og = OrderedGroupType(id="reading-order")
ro.set_OrderedGroup(og)
# <pg:RegionRefIndexed>
og.add_RegionRefIndexed(
RegionRefIndexedType(regionRef=ID, index=index))
#
# text region
#
pcgts.get_Page().add_TextRegion(
TextRegionType(id=ID,
Coords=CoordsType(points=points)))
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
basename=ID + '.xml',
mimetype=MIMETYPE_PAGE,
content=to_xml(pcgts).encode('utf-8'),
)
def process(self):
"""
Performs the line segmentation.
"""
with PyTessBaseAPI(
psm=PSM.SINGLE_LINE,
path=TESSDATA_PREFIX,
) as tessapi:
for (n, input_file) in enumerate(self.input_files):
pcgts = from_file(self.workspace.download_file(input_file))
image_url = pcgts.get_Page().imageFilename
for region in pcgts.get_Page().get_TextRegion():
for line in region.get_TextLine():
log.debug("Detecting words in line '%s'", line.id)
image = self.workspace.resolve_image_as_pil(
image_url,
polygon_from_points(line.get_Coords().points))
tessapi.SetImage(image)
offset = xywh_from_points(line.get_Coords().points)
for (word_no, component) in enumerate(
tessapi.GetComponentImages(RIL.WORD, True)):
word_id = '%s_word%04d' % (line.id, word_no)
word_xywh = component[1]
word_xywh['x'] += offset['x']
word_xywh['y'] += offset['y']
line.add_Word(
WordType(id=word_id,
Coords=CoordsType(
points_from_xywh(word_xywh))))
ID = concat_padded(self.output_file_grp, n)
self.add_output_file(
ID=ID,
file_grp=self.output_file_grp,
basename=ID + '.xml',
mimetype=MIMETYPE_PAGE,
content=to_xml(pcgts).encode('utf-8'),
)