def extract(image):
try:
binary = ocrolib.read_image_binary(image)
binary = 1-binary
scale = psegutils.estimate_scale(binary)
segmentation = compute_segmentation(binary,scale)
# ...lines = compute_lines(segmentation,scale)
# compute the reading order
lines = psegutils.compute_lines(segmentation,scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
# renumber the labels so that they conform to the specs
nlabels = amax(compute_segmentation)+1
renumber = zeros(nlabels,'i')
for i,v in enumerate(lsort): renumber[lines[v].label] = 0x010000+(i+1)
segmentation = renumber[segmentation]
outputdir = "http://127.0.0.1:5000/uploads/"
lines = [lines[i] for i in lsort]
ocrolib.write_page_segmentation("%s.pseg.png"%outputdir,segmentation)
cleaned = ocrolib.remove_noise(binary,args.noise)
for i,l in enumerate(lines):
binline = psegutils.extract_masked(1-cleaned,l,pad=args.pad,expand=args.expand)
ocrolib.write_image_binary("%s/01%04x.bin.png"%(outputdir,i+1),binline)
#print "%6d"%i,fname,"%4.1f"%scale,len(lines)
except:
print ('error')
def _process_segment(self, page_image, page, textregion, region_xywh,
page_id, input_file, n):
LOG = getLogger('OcrdAnybaseocrTextline')
#check for existing text lines and whether to overwrite them
if textregion.get_TextLine():
if self.parameter['overwrite']:
LOG.info('removing existing TextLines in region "%s"', page_id)
textregion.set_TextLine([])
else:
LOG.warning('keeping existing TextLines in region "%s"',
page_id)
return
binary = ocrolib.pil2array(page_image)
if len(binary.shape) > 2:
binary = np.mean(binary, 2)
binary = np.array(1 - binary / np.amax(binary), 'B')
if self.parameter['scale'] == 0:
scale = psegutils.estimate_scale(binary)
else:
scale = self.parameter['scale']
if np.isnan(
scale) or scale > 1000.0 or scale < self.parameter['minscale']:
LOG.warning(str(scale) + ": bad scale; skipping!\n")
return
segmentation = self.compute_segmentation(binary, scale)
if np.amax(segmentation) > self.parameter['maxlines']:
LOG.warning("too many lines %i; skipping!\n",
(np.amax(segmentation)))
return
lines = psegutils.compute_lines(segmentation, scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
# renumber the labels so that they conform to the specs
nlabels = np.amax(segmentation) + 1
renumber = np.zeros(nlabels, 'i')
for i, v in enumerate(lsort):
renumber[lines[v].label] = 0x010000 + (i + 1)
segmentation = renumber[segmentation]
lines = [lines[i] for i in lsort]
cleaned = ocrolib.remove_noise(binary, self.parameter['noise'])
for i, l in enumerate(lines):
#LOG.info('check this: ')
#LOG.info(type(l.bounds))
#LOG.info(l.bounds)
#line_points = np.where(l.mask==1)
#hull = MultiPoint([x for x in zip(line_points[0],line_points[1])]).convex_hull
#x,y = hull.exterior.coords.xy
#LOG.info('hull coords x: ',x)
#LOG.info('hull coords y: ',y)
min_x, max_x = (l.bounds[0].start, l.bounds[0].stop)
min_y, max_y = (l.bounds[1].start, l.bounds[1].stop)
line_polygon = [[min_x, min_y], [max_x, min_y], [max_x, max_y],
[min_x, max_y]]
#line_polygon = [x for x in zip(y, x)]
line_polygon = coordinates_for_segment(line_polygon, page_image,
region_xywh)
line_points = points_from_polygon(line_polygon)
img = cleaned[l.bounds[0], l.bounds[1]]
img = np.array(255 * (img > ocrolib.midrange(img)), 'B')
img = 255 - img
img = ocrolib.array2pil(img)
file_id = make_file_id(input_file, self.output_file_grp)
file_path = self.workspace.save_image_file(
img,
file_id + "_" + str(n) + "_" + str(i),
page_id=page_id,
file_grp=self.output_file_grp)
ai = AlternativeImageType(filename=file_path,
comments=region_xywh['features'])
line_id = '%s_line%04d' % (page_id, i)
line = TextLineType(custom='readingOrder {index:' + str(i) + ';}',
id=line_id,
Coords=CoordsType(line_points))
line.add_AlternativeImage(ai)
textregion.add_TextLine(line)
def analyze_page_layout(binary, gray, rgb=None):
hscale = 1.0 # Non-standard scaling of horizontal parameters.
vscale = 1.0 # Non-standard scaling of vertical parameters.
threshold = 0.2 # baseline threshold.
usegauss = True # Use gaussian instead of uniform.
maxseps = 0 # Maximum black column separators.
sepwiden = 10 # Widen black separators (to account for warping).
blackseps = True
maxcolseps = 3 # Maximum # whitespace column separators.
csminheight = 10 # Minimum column height (units=scale).
noise = 8 # Noise threshold for removing small components from lines.
gray_output = True # Output grayscale lines as well, which are extracted from the grayscale version of the pages.
pad = 3 # Padding for extracted lines.
expand = 3 # Expand mask for grayscale extraction.
if False:
bin_image_filepath = './ocropy_test.bin.png'
gray_image_filepath = './ocropy_test.nrm.png'
binary = ocrolib.read_image_binary(bin_image_filepath)
gray = ocrolib.read_image_gray(gray_image_filepath)
binary = 1 - binary # Invert.
scale = psegutils.estimate_scale(binary)
segmentation = compute_segmentation(binary,
scale,
blackseps,
maxseps,
maxcolseps,
csminheight,
sepwiden,
usegauss,
vscale,
hscale,
threshold,
quiet=True)
lines = psegutils.compute_lines(segmentation, scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
# Renumber the labels so that they conform to the specs.
nlabels = np.amax(segmentation) + 1
renumber = np.zeros(nlabels, 'i')
for i, v in enumerate(lsort):
renumber[lines[v].label] = 0x010000 + (i + 1)
segmentation = renumber[segmentation] # Image.
lines = [lines[i] for i in lsort]
# Visualize bounding boxes.
if False:
if rgb is not None:
# REF [function] >> extract_masked() in ${OCROPY_HOME}/ocrolib/psegutils.py.
for l in lines:
y0, x0, y1, x1 = [
int(x) for x in [
l.bounds[0].start, l.bounds[1].start, l.bounds[0].stop,
l.bounds[1].stop
]
]
cv2.rectangle(rgb, (x0, y0), (x1, y1), (0, 0, 255), 1,
cv2.LINE_AA)
cv2.imshow('Image', rgb)
cv2.waitKey(0)
# Output everything.
if False:
if not os.path.exists(outputdir):
os.mkdir(outputdir)
ocrolib.write_page_segmentation("%s.pseg.png" % outputdir,
segmentation)
cleaned = ocrolib.remove_noise(binary, noise)
for i, l in enumerate(lines):
binline = psegutils.extract_masked(1 - cleaned,
l,
pad=pad,
expand=expand) # Image.
ocrolib.write_image_binary(
"%s/01%04x.bin.png" % (outputdir, i + 1), binline)
if gray_output:
grayline = psegutils.extract_masked(gray,
l,
pad=pad,
expand=expand) # Image.
ocrolib.write_image_gray(
"%s/01%04x.nrm.png" % (outputdir, i + 1), grayline)
def processPngFile(outRoot, origFile, fileNum):
baseName = os.path.basename(origFile)
baseBase, _ = os.path.splitext(baseName)
outDir = os.path.join(outRoot, "%s.%03d" % (baseBase, fileNum))
inFile = os.path.join(outDir, baseName)
os.makedirs(outDir, exist_ok=True)
shutil.copy(origFile, inFile)
inBase, _ = ocrolib.allsplitext(inFile)
print("** inBase=%s" % inBase)
# print("** binBase=%s" % binBase)
fname = inFile
outputdir = inBase
binFile = inBase + ".bin.png"
outFile = inBase + ".out.png"
outRoot2, outDir2 = os.path.split(outRoot)
outFile2 = os.path.join(outRoot2, "%s.out" % outDir2, baseName)
print("outFile2=%s" % outFile2)
# assert False
grayFile = inBase + ".nrm.png"
psegFile = inBase + ".pseg.png"
print(" inFile=%s" % inFile)
print(" binFile=%s" % binFile)
print("grayFile=%s" % grayFile)
print(" outFile=%s" % outFile)
assert inFile and binFile
assert outFile != inFile
assert outFile != binFile
if not binarize(inFile, binFile, grayFile):
binExists = os.path.exists(binFile)
print("Couldn't binarize inFile=%s binFile=%s exists=%s" %
(inFile, binFile, binExists))
return False
binary = ocrolib.read_image_binary(binFile)
print("$$ %s=%s" % (binFile, desc(binary)))
height, width = binary.shape
checktype(binary, ABINARY2)
check = check_page(np.amax(binary) - binary)
if check is not None:
print("%s SKIPPED %s (use -n to disable this check)" % (inFile, check))
return False
# if args.gray:
# if os.path.exists(base+".nrm.png"):
# gray = ocrolib.read_image_gray(base+".nrm.png")
# checktype(gray, GRAYSCALE)
# else:
# print_error("Grayscale version %s.nrm.png not found. Use ocropus-nlbin for creating " +
# "normalized grayscale version of the pages as well." % base)
# return
binary = 1 - binary # invert
scale = psegutils.estimate_scale(binary)
print("scale %f" % scale)
if np.isnan(scale) or scale > 1000.0:
print("%s: bad scale (%g); skipping\n" % (fname, scale))
return False
# find columns and text lines
print("computing segmentation")
segmentation = compute_segmentation(binary, scale)
if np.amax(segmentation) > maxlines:
print("%s: too many lines %g" % (fname, np.amax(segmentation)))
return False
print("segmentation=%s" % desc(segmentation))
print("number of lines %g" % np.amax(segmentation))
# compute the reading order
print("finding reading order")
lines = psegutils.compute_lines(segmentation, scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
print("$$ lsort = %d = %s...%s" % (len(lsort), lsort[:10], lsort[-10:]))
# renumber the labels so that they conform to the specs
nlabels = np.amax(segmentation) + 1
renumber = np.zeros(nlabels, 'i')
for i, v in enumerate(lsort):
renumber[lines[v].label] = 0x010000 + (i + 1)
segmentation = renumber[segmentation]
# finally, output everything
print("writing lines")
if not os.path.exists(outputdir):
os.mkdir(outputdir)
lines = [lines[i] for i in lsort]
ocrolib.write_page_segmentation("%s.pseg.png" % outputdir, segmentation)
cleaned = ocrolib.remove_noise(binary, noise)
for i, l in enumerate(lines):
binline = psegutils.extract_masked(1 - cleaned,
l,
pad=pad,
expand=expand)
ocrolib.write_image_binary("%s/01%04x.bin.png" % (outputdir, i + 1),
binline)
# if args.gray:
# grayline = psegutils.extract_masked(
# gray, l, pad=args.pad, expand=args.expand)
# ocrolib.write_image_gray("%s/01%04x.nrm.png" % (outputdir, i+1), grayline)
print("%6d %s %4.1f %d" % (i, fname, scale, len(lines)))
# to proceed, we need a pseg file and a subdirectory containing text lines
assert os.path.exists(psegFile), "%s: no such file" % psegFile
assert os.path.isdir(inBase), "%s: no such directory" % inBase
# iterate through the text lines in reading order, based on the page segmentation file
pseg = ocrolib.read_page_segmentation(psegFile)
print("$$ %s=%s" % (psegFile, desc(pseg)))
regions = ocrolib.RegionExtractor()
print("$$ regions=%s" % regions)
regions.setPageLines(pseg)
im = Image.open(inFile)
print("~~%s %s" % (inFile, im.size))
print("$$ regions=%s=%s" % (regions, sorted(regions.__dict__)))
print("$$ regions.length=%s" % regions.length())
n = regions.length()
for i in range(1, n):
id = regions.id(i)
y0, x0, y1, x1 = regions.bbox(i)
# print("%5d: 0x%05X %s %d x %d" %
# (i, id, [y0, x0, y1, x1], y1 - y0, x1 - x0))
draw = ImageDraw.Draw(im)
draw.rectangle((x0, y0, x1, y1), outline=(255, 0, 0), width=3)
draw.rectangle((x0, y0, x1, y1), outline=(0, 0, 255), width=0)
# draw.rectangle((x0, y0, x1, y1), outline=255, width=5)
# draw.rectangle((x0, y0, x1, y1), outline=10, width=1)
del draw
# write output files
print("outFile=%s" % outFile)
im.save(outFile, "PNG")
print("outFile2=%s" % outFile2)
outDir2 = os.path.dirname(outFile2)
os.makedirs(outDir2, exist_ok=True)
im.save(outFile2, "PNG")
assert os.path.exists(outFile2)
# outFile3, _ = os.path.splitext(outFile)
# outFile3 = "%s.jpg" % outFile3
# print("outFile3=%s" % outFile3)
# im.save(outFile3, "JPEG")
# assert os.path.exists(outFile3)
return True
def process(job):
imagepath, i = job
global base
base, _ = ocrolib.allsplitext(imagepath)
outputdir = base
imagename_base = os.path.basename(os.path.normpath(base))
try:
binary = ocrolib.read_image_binary(imagepath)
except IOError:
if ocrolib.trace: traceback.print_exc()
print_error("cannot open either %s.bin.png or %s" % (base, imagepath))
return
checktype(binary, ABINARY2)
if not args['nocheck']:
check = check_page(amax(binary) - binary)
if check is not None:
print_error("%s SKIPPED %s (use -n to disable this check)" %
(imagepath, check))
return
binary = 1 - binary # invert
if args['scale'] == 0:
scale = psegutils.estimate_scale(binary)
else:
scale = args['scale']
print_info("scale %f" % (scale))
if isnan(scale) or scale > 1000.0:
print_error("%s: bad scale (%g); skipping\n" % (imagepath, scale))
return
if scale < args['minscale']:
print_error("%s: scale (%g) less than --minscale; skipping\n" %
(imagepath, scale))
return
# find columns and text lines
if not args['quiet']: print_info("computing segmentation")
segmentation = compute_segmentation(binary, scale)
if amax(segmentation) > args['maxlines']:
print_error("%s: too many lines %g" % (imagepath, amax(segmentation)))
return
if not args['quiet']: print_info("number of lines %g" % amax(segmentation))
# compute the reading order
if not args['quiet']: print_info("finding reading order")
lines = psegutils.compute_lines(segmentation, scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
# renumber the labels so that they conform to the specs
nlabels = amax(segmentation) + 1
renumber = zeros(nlabels, 'i')
for i, v in enumerate(lsort):
renumber[lines[v].label] = 0x010000 + (i + 1)
segmentation = renumber[segmentation]
# finally, output everything
if not args['quiet']: print_info("writing lines")
if not os.path.exists(outputdir):
os.mkdir(outputdir)
lines = [lines[i] for i in lsort]
ocrolib.write_page_segmentation("%s.pseg.png" % outputdir, segmentation)
cleaned = ocrolib.remove_noise(binary, args['noise'])
for i, l in enumerate(lines):
binline = psegutils.extract_masked(1 - cleaned,
l,
pad=args['pad'],
expand=args['expand'])
ocrolib.write_image_binary(
"%s/%s_01%04x.bin.png" % (outputdir, imagename_base, i + 1),
binline)
print_info("%6d %s %4.1f %d" % (i, imagepath, scale, len(lines)))
return outputdir
def process1(job):
fname, i = job
global base
base, _ = ocrolib.allsplitext(fname)
outputdir = base
try:
binary = ocrolib.read_image_binary(base + ".bin.png")
except IOError:
try:
binary = ocrolib.read_image_binary(fname)
except IOError:
if ocrolib.trace:
traceback.print_exc()
print("cannot open either", base + ".bin.png", "or", fname)
return
checktype(binary, ABINARY2)
if not args.nocheck:
check = check_page(amax(binary) - binary)
if check is not None:
print(fname, "SKIPPED", check, "(use -n to disable this check)")
return
if args.gray:
if os.path.exists(base + ".nrm.png"):
gray = ocrolib.read_image_gray(base + ".nrm.png")
checktype(gray, GRAYSCALE)
binary = 1 - binary # invert
if args.scale == 0:
scale = psegutils.estimate_scale(binary)
else:
scale = args.scale
print("scale", scale)
if isnan(scale) or scale > 1000.0:
sys.stderr.write("%s: bad scale (%g); skipping\n" % (fname, scale))
return
if scale < args.minscale:
sys.stderr.write("%s: scale (%g) less than --minscale; skipping\n" %
(fname, scale))
return
# find columns and text lines
if not args.quiet:
print("computing segmentation")
segmentation = compute_segmentation(binary, scale)
if amax(segmentation) > args.maxlines:
print(fname, ": too many lines", amax(segmentation))
return
if not args.quiet:
print("number of lines", amax(segmentation))
# compute the reading order
if not args.quiet:
print("finding reading order")
lines = psegutils.compute_lines(segmentation, scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
# renumber the labels so that they conform to the specs
nlabels = amax(segmentation) + 1
renumber = zeros(nlabels, 'i')
for i, v in enumerate(lsort):
renumber[lines[v].label] = 0x010000 + (i + 1)
segmentation = renumber[segmentation]
# finally, output everything
if not args.quiet:
print("writing lines")
if not os.path.exists(outputdir):
os.mkdir(outputdir)
lines = [lines[i] for i in lsort]
ocrolib.write_page_segmentation("%s.pseg.png" % outputdir, segmentation)
cleaned = ocrolib.remove_noise(binary, args.noise)
for i, l in enumerate(lines):
binline = psegutils.extract_masked(1 - cleaned,
l,
pad=args.pad,
expand=args.expand)
ocrolib.write_image_binary("%s/01%04x.bin.png" % (outputdir, i + 1),
binline)
if args.gray:
grayline = psegutils.extract_masked(gray,
l,
pad=args.pad,
expand=args.expand)
ocrolib.write_image_gray("%s/01%04x.nrm.png" % (outputdir, i + 1),
grayline)
print("%6d" % i, fname, "%4.1f" % scale, len(lines))
def _process_segment(self, page_image, page, region_xywh, page_id,
input_file, n):
binary = ocrolib.pil2array(page_image)
binary = np.array(1 - binary / np.amax(binary), 'B')
if page.get_TextRegion() is None or len(page.get_TextRegion()) < 1:
min_x, max_x = (0, binary.shape[0])
min_y, max_y = (0, binary.shape[1])
textregion = TextRegionType(
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)))
page.add_TextRegion(textregion)
else:
textregion = page.get_TextRegion()[-1]
ocrolib.write_image_binary("test.bin.png", binary)
if self.parameter['scale'] == 0:
scale = psegutils.estimate_scale(binary)
else:
scale = self.parameter['scale']
if np.isnan(
scale) or scale > 1000.0 or scale < self.parameter['minscale']:
LOG.warning("%s: bad scale (%g); skipping\n" % (fname, scale))
return
segmentation = self.compute_segmentation(binary, scale)
if np.amax(segmentation) > self.parameter['maxlines']:
LOG.warning("%s: too many lines %i",
(fname, np.amax(segmentation)))
return
lines = psegutils.compute_lines(segmentation, scale)
order = psegutils.reading_order([l.bounds for l in lines])
lsort = psegutils.topsort(order)
# renumber the labels so that they conform to the specs
nlabels = np.amax(segmentation) + 1
renumber = np.zeros(nlabels, 'i')
for i, v in enumerate(lsort):
renumber[lines[v].label] = 0x010000 + (i + 1)
segmentation = renumber[segmentation]
lines = [lines[i] for i in lsort]
cleaned = ocrolib.remove_noise(binary, self.parameter['noise'])
region_xywh['features'] += ",textline"
for i, l in enumerate(lines):
ocrolib.write_image_binary("test.bin.png", binary[l.bounds[0],
l.bounds[1]])
min_x, max_x = (l.bounds[0].start, l.bounds[0].stop)
min_y, max_y = (l.bounds[1].start, l.bounds[1].stop)
img = binary[l.bounds[0], l.bounds[1]]
img = np.array(255 * (img > ocrolib.midrange(img)), 'B')
img = ocrolib.array2pil(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(img,
file_id + "_" + str(i),
page_id=page_id,
file_grp=self.image_grp)
ai = AlternativeImageType(filename=file_path,
comments=region_xywh['features'])
line = TextLineType(
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)))
line.add_AlternativeImage(ai)
textregion.add_TextLine(line)