def compute_geomaps(fnames,shapedict,old_model,use_gt=1,size=32,debug=0,old_order=1):
"""Given a shape dictionary and an existing line geometry
estimator, compute updated geometric maps for each entry
in the shape dictionary."""
if debug>0: gray(); ion()
shape = (shapedict.k,size,size)
bls = zeros(shape)
xls = zeros(shape)
count = 0
for fno,fname in enumerate(fnames):
if fno%20==0: print fno,fname,count
if use_gt:
# don't use lines with many capital letters for training because
# they result in bad models
gt = ocrolib.read_text(ocrolib.fvariant(fname,"txt","gt"))
if len(re.sub(r'[^A-Z]','',gt))>=0.3*len(re.sub(r'[^a-z]','',gt)): continue
if len(re.sub(r'[^0-9]','',gt))>=0.3*len(re.sub(r'[^a-z]','',gt)): continue
image = 1-ocrolib.read_image_gray(fname)
if debug>0 and fno%debug==0: clf(); subplot(411); imshow(image)
try:
blp,xlp = old_model.lineFit(image,order=old_order)
except:
traceback.print_exc()
continue
blimage = zeros(image.shape)
h,w = image.shape
for x in range(w): blimage[clip(int(polyval(blp,x)),0,h-1),x] = 1
xlimage = zeros(image.shape)
for x in range(w): xlimage[clip(int(polyval(xlp,x)),0,h-1),x] = 1
if debug>0 and fno%debug==0:
subplot(413); imshow(xlimage+0.3*image)
subplot(414); imshow(blimage+0.3*image)
try:
seg = lineseg.ccslineseg(image)
except:
continue
if debug>0 and fno%debug==0: subplot(412); morph.showlabels(seg)
shape = None
for sub,transform,itransform_add in extract_chars(seg):
if shape is None: shape = sub.shape
assert sub.shape==shape
count += 1
best = shapedict.predict1(sub)
bls[best] += transform(blimage)
xls[best] += transform(xlimage)
if debug==1: ginput(1,100)
elif debug>1: ginput(1,0.01)
for i in range(len(bls)): bls[i] *= bls[i].shape[1]*1.0/max(1e-6,sum(bls[i]))
for i in range(len(xls)): xls[i] *= xls[i].shape[1]*1.0/max(1e-6,sum(xls[i]))
return bls,xls
def allchars():
count = 0
for fno,fname in enumerate(fnames):
if fno%20==0: print fno,fname,count
image = 1-ocrolib.read_image_gray(fname)
try:
seg = lineseg.ccslineseg(image)
except:
traceback.print_exc()
continue
seg = morph.renumber_by_xcenter(seg)
for e in extract_chars(seg):
count += 1
yield e
def allchars():
count = 0
for fno, fname in enumerate(fnames):
if fno % 20 == 0: print fno, fname, count
image = 1 - ocrolib.read_image_gray(fname)
try:
seg = lineseg.ccslineseg(image)
except:
traceback.print_exc()
continue
seg = morph.renumber_by_xcenter(seg)
for e in extract_chars(seg):
count += 1
yield e
def blxlimages(image,shapedict,bls,xls):
image = (image>ocrolib.midrange(image))
if amax(image)==0: raise RecognitionError("empty line")
seg = lineseg.ccslineseg(image)
# ion(); subplot(311); imshow(image); subplot(312); morph.showlabels(seg); ginput(1,0.1); raw_input()
seg = morph.renumber_by_xcenter(seg)
blimage = zeros(image.shape)
xlimage = zeros(image.shape)
for sub,transform,itransform_add in extract_chars(seg):
best = shapedict.predict1(sub)
bli = bls[best].reshape(32,32)
xli = xls[best].reshape(32,32)
itransform_add(blimage,bli)
itransform_add(xlimage,xli)
return blimage,xlimage
def blxlimages(image, shapedict, bls, xls):
image = (image > ocrolib.midrange(image))
if amax(image) == 0: raise RecognitionError("empty line")
seg = lineseg.ccslineseg(image)
# ion(); subplot(311); imshow(image); subplot(312); morph.showlabels(seg); ginput(1,0.1); raw_input()
seg = morph.renumber_by_xcenter(seg)
blimage = zeros(image.shape)
xlimage = zeros(image.shape)
for sub, transform, itransform_add in extract_chars(seg):
best = shapedict.predict1(sub)
bli = bls[best].reshape(32, 32)
xli = xls[best].reshape(32, 32)
itransform_add(blimage, bli)
itransform_add(xlimage, xli)
return blimage, xlimage
def compute_geomaps(fnames,
shapedict,
old_model,
use_gt=1,
size=32,
debug=0,
old_order=1):
"""Given a shape dictionary and an existing line geometry
estimator, compute updated geometric maps for each entry
in the shape dictionary."""
if debug > 0:
gray()
ion()
shape = (shapedict.k, size, size)
bls = zeros(shape)
xls = zeros(shape)
count = 0
for fno, fname in enumerate(fnames):
if fno % 20 == 0: print fno, fname, count
if use_gt:
# don't use lines with many capital letters for training because
# they result in bad models
gt = ocrolib.read_text(ocrolib.fvariant(fname, "txt", "gt"))
if len(re.sub(r'[^A-Z]', '',
gt)) >= 0.3 * len(re.sub(r'[^a-z]', '', gt)):
continue
if len(re.sub(r'[^0-9]', '',
gt)) >= 0.3 * len(re.sub(r'[^a-z]', '', gt)):
continue
image = 1 - ocrolib.read_image_gray(fname)
if debug > 0 and fno % debug == 0:
clf()
subplot(411)
imshow(image)
try:
blp, xlp = old_model.lineFit(image, order=old_order)
except:
traceback.print_exc()
continue
blimage = zeros(image.shape)
h, w = image.shape
for x in range(w):
blimage[clip(int(polyval(blp, x)), 0, h - 1), x] = 1
xlimage = zeros(image.shape)
for x in range(w):
xlimage[clip(int(polyval(xlp, x)), 0, h - 1), x] = 1
if debug > 0 and fno % debug == 0:
subplot(413)
imshow(xlimage + 0.3 * image)
subplot(414)
imshow(blimage + 0.3 * image)
try:
seg = lineseg.ccslineseg(image)
except:
continue
if debug > 0 and fno % debug == 0:
subplot(412)
morph.showlabels(seg)
shape = None
for sub, transform, itransform_add in extract_chars(seg):
if shape is None: shape = sub.shape
assert sub.shape == shape
count += 1
best = shapedict.predict1(sub)
bls[best] += transform(blimage)
xls[best] += transform(xlimage)
if debug == 1: ginput(1, 100)
elif debug > 1: ginput(1, 0.01)
for i in range(len(bls)):
bls[i] *= bls[i].shape[1] * 1.0 / max(1e-6, sum(bls[i]))
for i in range(len(xls)):
xls[i] *= xls[i].shape[1] * 1.0 / max(1e-6, sum(xls[i]))
return bls, xls