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 textimageseg(self, imf):
# I: binarized-input-image; imftext: output-text-portion.png; imfimage: output-image-portion.png
I = ocrolib.read_image_binary(imf)
I = 1 - I / I.max()
rows, cols = I.shape
# Generate Mask and Seed Images
Imask, Iseed = self.pixMorphSequence_mask_seed_fill_holes(I)
# Iseedfill: Union of Mask and Seed Images
Iseedfill = self.pixSeedfillBinary(Imask, Iseed)
# Dilation of Iseedfill
mask = ones((3, 3))
Iseedfill = ndimage.binary_dilation(Iseedfill, mask)
# Expansion of Iseedfill to become equal in size of I
Iseedfill = self.expansion(Iseedfill, (rows, cols))
# Write Text and Non-Text images
image_part = array((1 - I * Iseedfill), dtype=int)
image_part[0, 0] = 0 # only for visualisation purpose
text_part = array((1 - I * (1 - Iseedfill)), dtype=int)
text_part[0, 0] = 0 # only for visualisation purpose
base, _ = ocrolib.allsplitext(imf)
ocrolib.write_image_binary(base + ".ts.png", text_part)
#imf_image = imf[0:-3] + "nts.png"
ocrolib.write_image_binary(base + ".nts.png", image_part)
return [base + ".ts.png", base + ".nts.png"]
def deskew(fpath, job):
base,_ = ocrolib.allsplitext(fpath)
basefile = ocrolib.allsplitext(os.path.basename(fpath))[0]
if args.parallel<2: print_info("=== %s %-3d" % (fpath, job))
raw = ocrolib.read_image_gray(fpath)
flat = raw
# estimate skew angle and rotate
if args.maxskew>0:
if args.parallel<2: print_info("estimating skew angle")
d0,d1 = flat.shape
o0,o1 = int(args.bignore*d0),int(args.bignore*d1)
flat = amax(flat)-flat
flat -= amin(flat)
est = flat[o0:d0-o0,o1:d1-o1]
ma = args.maxskew
ms = int(2*args.maxskew*args.skewsteps)
angle = estimate_skew_angle(est,linspace(-ma,ma,ms+1))
flat = interpolation.rotate(flat,angle,mode='constant',reshape=0)
flat = amax(flat)-flat
else:
angle = 0
# estimate low and high thresholds
if args.parallel<2: print_info("estimating thresholds")
d0,d1 = flat.shape
o0,o1 = int(args.bignore*d0),int(args.bignore*d1)
est = flat[o0:d0-o0,o1:d1-o1]
if args.escale>0:
# by default, we use only regions that contain
# significant variance; this makes the percentile
# based low and high estimates more reliable
e = args.escale
v = est-filters.gaussian_filter(est,e*20.0)
v = filters.gaussian_filter(v**2,e*20.0)**0.5
v = (v>0.3*amax(v))
v = morphology.binary_dilation(v,structure=ones((int(e*50),1)))
v = morphology.binary_dilation(v,structure=ones((1,int(e*50))))
if args.debug>0: imshow(v); ginput(1,args.debug)
est = est[v]
lo = stats.scoreatpercentile(est.ravel(),args.lo)
hi = stats.scoreatpercentile(est.ravel(),args.hi)
# rescale the image to get the gray scale image
if args.parallel<2: print_info("rescaling")
flat -= lo
flat /= (hi-lo)
flat = clip(flat,0,1)
if args.debug>0: imshow(flat,vmin=0,vmax=1); ginput(1,args.debug)
bin = 1*(flat>args.threshold)
# output the normalized grayscale and the thresholded images
print_info("%s lo-hi (%.2f %.2f) angle %4.1f" % (basefile, lo, hi, angle))
if args.parallel<2: print_info("writing")
ocrolib.write_image_binary(base+".ds.png",bin)
return base+".ds.png"
def binarize(image_filepath):
raw = ocrolib.read_image_gray(image_filepath)
# Perform image normalization.
image = normalize_raw_image(raw)
threshold = 0.5 # Threshold, determines lightness.
zoom = 0.5 # Zoom for page background estimation, smaller=faster.
escale = 1.0 # Scale for estimating a mask over the text region.
bignore = 0.1 # Ignore this much of the border for threshold estimation.
perc = 80 # Percentage for filters.
range = 20 # Range for filters.
maxskew = 2 # Skew angle estimation parameters (degrees).
lo = 5 # Percentile for black estimation.
hi = 90 # Percentile for white estimation.
skewsteps = 8 # Steps for skew angle estimation (per degree).
debug = 0 # Display intermediate results.
# Flatten it by estimating the local whitelevel.
flat = estimate_local_whitelevel(image, zoom, perc, range, debug)
# Estimate skew angle and rotate.
flat, angle = estimate_skew(flat, bignore, maxskew, skewsteps, debug)
# Estimate low and high thresholds.
lo, hi = estimate_thresholds(flat, bignore, escale, lo, hi, debug)
# Rescale the image to get the gray scale image.
flat -= lo
flat /= (hi - lo)
flat = np.clip(flat, 0, 1)
bin = 1 * (flat > threshold)
if False:
# Output the normalized grayscale and the thresholded images.
ocrolib.write_image_binary('./ocropy_test.bin.png', bin)
ocrolib.write_image_gray('./ocropy_test.nrm.png', flat)
return bin, flat
def process1(job):
fname, i = job
print_info("# %s" % (fname))
if args.parallel < 2: print_info("=== %s %-3d" % (fname, i))
raw = ocrolib.read_image_gray(fname)
dshow(raw, "input")
# perform image normalization
image = raw - amin(raw)
if amax(image) == amin(image):
print_info("# image is empty: %s" % (fname))
return
image /= amax(image)
if not args.nocheck:
check = check_page(amax(image) - image)
if check is not None:
print_error(fname + " SKIPPED. " + check +
" (use -n to disable this check)")
return
# check whether the image is already effectively binarized
if args.gray:
extreme = 0
else:
extreme = (sum(image < 0.05) + sum(image > 0.95)) * 1.0 / prod(
image.shape)
if extreme > 0.95:
comment = "no-normalization"
flat = image
else:
comment = ""
# if not, we need to flatten it by estimating the local whitelevel
if args.parallel < 2: print_info("flattening")
m = interpolation.zoom(image, args.zoom)
m = filters.percentile_filter(m, args.perc, size=(args.range, 2))
m = filters.percentile_filter(m, args.perc, size=(2, args.range))
m = interpolation.zoom(m, 1.0 / args.zoom)
if args.debug > 0:
clf()
imshow(m, vmin=0, vmax=1)
ginput(1, args.debug)
w, h = minimum(array(image.shape), array(m.shape))
flat = clip(image[:w, :h] - m[:w, :h] + 1, 0, 1)
if args.debug > 0:
clf()
imshow(flat, vmin=0, vmax=1)
ginput(1, args.debug)
# estimate low and high thresholds
if args.parallel < 2: print_info("estimating thresholds")
d0, d1 = flat.shape
o0, o1 = int(args.bignore * d0), int(args.bignore * d1)
est = flat[o0:d0 - o0, o1:d1 - o1]
if args.escale > 0:
# by default, we use only regions that contain
# significant variance; this makes the percentile
# based low and high estimates more reliable
e = args.escale
v = est - filters.gaussian_filter(est, e * 20.0)
v = filters.gaussian_filter(v**2, e * 20.0)**0.5
v = (v > 0.3 * amax(v))
v = morphology.binary_dilation(v, structure=ones((int(e * 50), 1)))
v = morphology.binary_dilation(v, structure=ones((1, int(e * 50))))
if args.debug > 0:
imshow(v)
ginput(1, args.debug)
est = est[v]
lo = stats.scoreatpercentile(est.ravel(), args.lo)
hi = stats.scoreatpercentile(est.ravel(), args.hi)
# rescale the image to get the gray scale image
if args.parallel < 2: print_info("rescaling")
flat -= lo
flat /= (hi - lo)
flat = clip(flat, 0, 1)
if args.debug > 0:
imshow(flat, vmin=0, vmax=1)
ginput(1, args.debug)
bin = 1 * (flat > args.threshold)
# output the normalized grayscale and the thresholded images
#print_info("%s lo-hi (%.2f %.2f) angle %4.1f %s" % (fname, lo, hi, angle, comment))
print_info("%s lo-hi (%.2f %.2f) %s" % (fname, lo, hi, comment))
if args.parallel < 2: print_info("writing")
if args.debug > 0 or args.show:
clf()
gray()
imshow(bin)
ginput(1, max(0.1, args.debug))
base, _ = ocrolib.allsplitext(fname)
ocrolib.write_image_binary(base + ".bin.png", bin)
ocrolib.write_image_gray(base + ".nrm.png", flat)
#print("########### File path : ", base+".nrm.png")
#write_to_xml(base+".bin.png")
return base + ".bin.png"
def process(job):
fname, i = job
print_info("# %s" % (fname))
if args['parallel'] < 2: print_info("=== %s %-3d" % (fname, i))
raw = ocrolib.read_image_gray(fname)
# perform image normalization
image = raw - amin(raw)
if amax(image) == amin(image):
print_info("# image is empty: %s" % (fname))
return
image /= amax(image)
if not args['nocheck']:
check = check_page(amax(image) - image)
if check is not None:
print_error(fname + "SKIPPED" + check +
"(use -n to disable this check)")
return
# flatten the image by estimating the local whitelevel
comment = ""
# if not, we need to flatten it by estimating the local whitelevel
if args['parallel'] < 2: print_info("flattening")
m = interpolation.zoom(image, args['zoom'])
m = filters.percentile_filter(m, args['perc'], size=(args['range'], 2))
m = filters.percentile_filter(m, args['perc'], size=(2, args['range']))
m = interpolation.zoom(m, 1.0 / args['zoom'])
w, h = minimum(array(image.shape), array(m.shape))
flat = clip(image[:w, :h] - m[:w, :h] + 1, 0, 1)
# estimate skew angle and rotate
if args['maxskew'] > 0:
if args['parallel'] < 2: print_info("estimating skew angle")
d0, d1 = flat.shape
o0, o1 = int(args['bignore'] * d0), int(args['bignore'] * d1)
flat = amax(flat) - flat
flat -= amin(flat)
est = flat[o0:d0 - o0, o1:d1 - o1]
ma = args['maxskew']
ms = int(2 * args['maxskew'] * args['skewsteps'])
angle = estimate_skew_angle(est, linspace(-ma, ma, ms + 1))
flat = interpolation.rotate(flat, angle, mode='constant', reshape=0)
flat = amax(flat) - flat
else:
angle = 0
# estimate low and high thresholds
if args['parallel'] < 2: print_info("estimating thresholds")
d0, d1 = flat.shape
o0, o1 = int(args['bignore'] * d0), int(args['bignore'] * d1)
est = flat[o0:d0 - o0, o1:d1 - o1]
if args['escale'] > 0:
# by default, we use only regions that contain
# significant variance; this makes the percentile
# based low and high estimates more reliable
e = args['escale']
v = est - filters.gaussian_filter(est, e * 20.0)
v = filters.gaussian_filter(v**2, e * 20.0)**0.5
v = (v > 0.3 * amax(v))
v = morphology.binary_dilation(v, structure=ones((int(e * 50), 1)))
v = morphology.binary_dilation(v, structure=ones((1, int(e * 50))))
est = est[v]
lo = stats.scoreatpercentile(est.ravel(), args['lo'])
hi = stats.scoreatpercentile(est.ravel(), args['hi'])
# rescale the image to get the gray scale image
if args['parallel'] < 2: print_info("rescaling")
flat -= lo
flat /= (hi - lo)
flat = clip(flat, 0, 1)
bin = 1 * (flat > args['threshold'])
# output the normalized grayscale and the thresholded images
print_info("%s lo-hi (%.2f %.2f) angle %4.1f %s" %
(fname, lo, hi, angle, comment))
if args['parallel'] < 2: print_info("writing")
base, _ = ocrolib.allsplitext(fname)
outputfile_bin = base + ".bin.png"
#outputfile_nrm = base+".nrm.png"
#output_files = [outputfile_bin, outputfile_nrm]
ocrolib.write_image_binary(outputfile_bin, bin)
#ocrolib.write_image_gray(outputfile_nrm, flat)
#return output_files
return outputfile_bin
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 binarize(inFile, binFile, grayFile):
print("binarize: inFile=%s binFile=%s grayFile=%s" %
(inFile, binFile, grayFile))
fname = inFile
raw = ocrolib.read_image_gray(inFile)
# perform image normalization
image = normalize_raw_image(raw)
if image is None:
print("!! # image is empty: %s" % (inFile))
assert False
return False
check = check_page(np.amax(image) - image)
if check is not None:
print(inFile + " SKIPPED " + check + "(use -n to disable this check)")
# assert False
return False
# check whether the image is already effectively binarized
extreme = (np.sum(image < 0.05) + np.sum(image > 0.95)) / np.prod(
image.shape)
if extreme > 0.95:
comment = "no-normalization"
flat = image
else:
comment = ""
# if not, we need to flatten it by estimating the local whitelevel
print("flattening")
flat = estimate_local_whitelevel(image, zoom, perc, size)
print("comment=%r extreme=%s" % (comment, extreme))
print("image=%s" % desc(image))
print(" flat=%s" % desc(flat))
# assert False
# estimate skew angle and rotate
# print("estimating skew angle")
# flat, angle = estimate_skew(flat, args.bignore, args.maxskew, args.skewsteps)
angle = 0.0
# estimate low and high thresholds
print("estimating thresholds")
lo, hi, ok = estimate_thresholds(flat, bignore, escale, defLo, defHi)
if not ok:
return False
print("lo=%5.3f (%g)" % (lo, defLo))
print("hi=%5.3f (%g)" % (hi, defHi))
# rescale the image to get the gray scale image
print("rescaling")
flat -= lo
flat /= (hi - lo)
flat = np.clip(flat, 0, 1)
bin = flat > threshold
# output the normalized grayscale and the thresholded images
print("%s lo-hi (%.2f %.2f) angle %4.1f %s" %
(fname, lo, hi, angle, comment))
print("##1 flat=%s" % desc(flat))
print("##2 bin=%s" % desc(bin))
print("writing %s" % binFile)
ocrolib.write_image_binary(binFile, bin)
ocrolib.write_image_gray(grayFile, flat)
return True
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(self):
for (n, input_file) in enumerate(self.input_files):
pcgts = page_from_file(self.workspace.download_file(input_file))
page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID
page = pcgts.get_Page()
LOG.info("INPUT FILE %s", input_file.pageId or input_file.ID)
page_image, page_xywh, _ = self.workspace.image_from_page(
page, page_id)
print("----------", type(page_image))
raw = ocrolib.read_image_gray(page_image.filename)
self.dshow(raw, "input")
# perform image normalization
image = raw - amin(raw)
if amax(image) == amin(image):
LOG.info("# image is empty: %s" %
(input_file.pageId or input_file.ID))
return
image /= amax(image)
if not self.parameter['nocheck']:
check = self.check_page(amax(image) - image)
if check is not None:
LOG.error(input_file.pageId
or input_file.ID + " SKIPPED. " + check +
" (use -n to disable this check)")
return
# check whether the image is already effectively binarized
if self.parameter['gray']:
extreme = 0
else:
extreme = (np.sum(image < 0.05) +
np.sum(image > 0.95)) * 1.0 / np.prod(image.shape)
if extreme > 0.95:
comment = "no-normalization"
flat = image
else:
comment = ""
# if not, we need to flatten it by estimating the local whitelevel
LOG.info("Flattening")
m = interpolation.zoom(image, self.parameter['zoom'])
m = filters.percentile_filter(m,
self.parameter['perc'],
size=(self.parameter['range'],
2))
m = filters.percentile_filter(m,
self.parameter['perc'],
size=(2,
self.parameter['range']))
m = interpolation.zoom(m, 1.0 / self.parameter['zoom'])
if self.parameter['debug'] > 0:
clf()
imshow(m, vmin=0, vmax=1)
ginput(1, self.parameter['debug'])
w, h = minimum(array(image.shape), array(m.shape))
flat = clip(image[:w, :h] - m[:w, :h] + 1, 0, 1)
if self.parameter['debug'] > 0:
clf()
imshow(flat, vmin=0, vmax=1)
ginput(1, self.parameter['debug'])
# estimate low and high thresholds
LOG.info("Estimating Thresholds")
d0, d1 = flat.shape
o0, o1 = int(self.parameter['bignore'] * d0), int(
self.parameter['bignore'] * d1)
est = flat[o0:d0 - o0, o1:d1 - o1]
if self.parameter['escale'] > 0:
# by default, we use only regions that contain
# significant variance; this makes the percentile
# based low and high estimates more reliable
e = self.parameter['escale']
v = est - filters.gaussian_filter(est, e * 20.0)
v = filters.gaussian_filter(v**2, e * 20.0)**0.5
v = (v > 0.3 * amax(v))
v = morphology.binary_dilation(v,
structure=ones(
(int(e * 50), 1)))
v = morphology.binary_dilation(v,
structure=ones(
(1, int(e * 50))))
if self.parameter['debug'] > 0:
imshow(v)
ginput(1, self.parameter['debug'])
est = est[v]
lo = stats.scoreatpercentile(est.ravel(), self.parameter['lo'])
hi = stats.scoreatpercentile(est.ravel(), self.parameter['hi'])
# rescale the image to get the gray scale image
LOG.info("Rescaling")
flat -= lo
flat /= (hi - lo)
flat = clip(flat, 0, 1)
if self.parameter['debug'] > 0:
imshow(flat, vmin=0, vmax=1)
ginput(1, self.parameter['debug'])
binarized = 1 * (flat > self.parameter['threshold'])
# output the normalized grayscale and the thresholded images
# print_info("%s lo-hi (%.2f %.2f) angle %4.1f %s" % (fname, lo, hi, angle, comment))
LOG.info("%s lo-hi (%.2f %.2f) %s" %
(input_file.pageId or input_file.ID, lo, hi, comment))
LOG.info("writing")
if self.parameter['debug'] > 0 or self.parameter['show']:
clf()
gray()
imshow(binarized)
ginput(1, max(0.1, self.parameter['debug']))
base, _ = ocrolib.allsplitext(page_image.filename)
ocrolib.write_image_binary(base + ".bin.png", binarized)
# ocrolib.write_image_gray(base +".nrm.png", flat)
# print("########### File path : ", base+".nrm.png")
# write_to_xml(base+".bin.png")
# return base+".bin.png"
# bin_array = array(255*(binarized>ocrolib.midrange(binarized)),'B')
# bin_image = ocrolib.array2pil(bin_array)
'''
file_path = self.workspace.save_image_file(bin_image,
file_id + ".bin",
page_id=page_id,
file_grp=self.output_file_grp
)
'''
file_id = input_file.ID.replace(self.input_file_grp,
self.output_file_grp)
if file_id == input_file.ID:
file_id = concat_padded(self.output_file_grp, n)
page.add_AlternativeImage(
AlternativeImageType(filename=base + ".bin.png",
comment="binarized"))
self.workspace.add_file(ID=file_id,
file_grp=self.output_file_grp,
pageId=input_file.pageId,
mimetype="image/png",
url=base + ".bin.png",
local_filename=os.path.join(
self.output_file_grp,
file_id + '.xml'),
content=to_xml(pcgts).encode('utf-8'))
def process(self):
for (n, input_file) in enumerate(self.input_files):
pcgts = page_from_file(self.workspace.download_file(input_file))
fname = pcgts.get_Page().imageFilename
img = self.workspace.resolve_image_as_pil(fname)
param = self.parameter
base, _ = ocrolib.allsplitext(fname)
#basefile = ocrolib.allsplitext(os.path.basename(fpath))[0]
if param['parallel'] < 2:
print_info("=== %s " % (fname))
raw = ocrolib.read_image_gray(img.filename)
flat = raw
#flat = np.array(binImg)
# estimate skew angle and rotate
if param['maxskew'] > 0:
if param['parallel'] < 2:
print_info("estimating skew angle")
d0, d1 = flat.shape
o0, o1 = int(param['bignore'] * d0), int(param['bignore'] * d1)
flat = amax(flat) - flat
flat -= amin(flat)
est = flat[o0:d0 - o0, o1:d1 - o1]
ma = param['maxskew']
ms = int(2 * param['maxskew'] * param['skewsteps'])
angle = self.estimate_skew_angle(est,
linspace(-ma, ma, ms + 1))
flat = interpolation.rotate(flat,
angle,
mode='constant',
reshape=0)
flat = amax(flat) - flat
else:
angle = 0
# self.write_angles_to_pageXML(base,angle)
# estimate low and high thresholds
if param['parallel'] < 2:
print_info("estimating thresholds")
d0, d1 = flat.shape
o0, o1 = int(param['bignore'] * d0), int(param['bignore'] * d1)
est = flat[o0:d0 - o0, o1:d1 - o1]
if param['escale'] > 0:
# by default, we use only regions that contain
# significant variance; this makes the percentile
# based low and high estimates more reliable
e = param['escale']
v = est - filters.gaussian_filter(est, e * 20.0)
v = filters.gaussian_filter(v**2, e * 20.0)**0.5
v = (v > 0.3 * amax(v))
v = morphology.binary_dilation(v,
structure=ones(
(int(e * 50), 1)))
v = morphology.binary_dilation(v,
structure=ones(
(1, int(e * 50))))
if param['debug'] > 0:
imshow(v)
ginput(1, param['debug'])
est = est[v]
lo = stats.scoreatpercentile(est.ravel(), param['lo'])
hi = stats.scoreatpercentile(est.ravel(), param['hi'])
# rescale the image to get the gray scale image
if param['parallel'] < 2:
print_info("rescaling")
flat -= lo
flat /= (hi - lo)
flat = clip(flat, 0, 1)
if param['debug'] > 0:
imshow(flat, vmin=0, vmax=1)
ginput(1, param['debug'])
deskewed = 1 * (flat > param['threshold'])
# output the normalized grayscale and the thresholded images
print_info("%s lo-hi (%.2f %.2f) angle %4.1f" %
(pcgts.get_Page().imageFilename, lo, hi, angle))
if param['parallel'] < 2:
print_info("writing")
ocrolib.write_image_binary(base + ".ds.png", deskewed)
orientation = -angle
orientation = 180 - (180 - orientation) % 360
pcgts.get_Page().set_orientation(orientation)
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(ID=ID,
file_grp=self.output_file_grp,
pageId=input_file.pageId,
mimetype="image/png",
url=base + ".ds.png",
local_filename='%s/%s' %
(self.output_file_grp, ID),
content=to_xml(pcgts).encode('utf-8'))
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)
