Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

split functions from nlbin #244

Closed
wants to merge 3 commits into from
Closed

split functions from nlbin #244

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f4b84bf
split functions from nlbin
ZhangXinNan Sep 21, 2017
79a17b7
fix normalze
ZhangXinNan Sep 21, 2017
84a23be
binary-->estimate_thresholds
ZhangXinNan Sep 22, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
131 changes: 84 additions & 47 deletions ocropus-nlbin
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,18 +83,94 @@ def dshow(image,info):
if args.debug<=0: return
ion(); gray(); imshow(image); title(info); ginput(1,args.debug)


def normalize(raw):
''' perform image normalization '''
image = raw-amin(raw)
if amax(image)==amin(image):
print_info("# image is empty: %s" % (fname))
return None
image /= amax(image)
return image


def estimate_local_whitelevel(image, zoom=0.5, perc=80, range=20, debug=0):
'''flatten it by estimating the local whitelevel
zoom for page background estimation, smaller=faster, default: %(default)s
percentage for filters, default: %(default)s
range for filters, default: %(default)s
'''
m = interpolation.zoom(image,zoom)
m = filters.percentile_filter(m,perc,size=(range,2))
m = filters.percentile_filter(m,perc,size=(2,range))
m = interpolation.zoom(m,1.0/zoom)
if debug>0: clf(); imshow(m,vmin=0,vmax=1); ginput(1,debug)
w,h = minimum(array(image.shape),array(m.shape))
flat = clip(image[:w,:h]-m[:w,:h]+1,0,1)
if debug>0: clf(); imshow(flat,vmin=0,vmax=1); ginput(1,debug)
return flat


def estimate_skew(flat, bignore=0.1, maxskew=2, skewsteps=8):
''' estimate skew angle and rotate'''
d0,d1 = flat.shape
o0,o1 = int(bignore*d0),int(bignore*d1) # border ignore
flat = amax(flat)-flat
flat -= amin(flat)
est = flat[o0:d0-o0,o1:d1-o1]
ma = maxskew
ms = int(2*maxskew*skewsteps)
# print(linspace(-ma,ma,ms+1))
angle = estimate_skew_angle(est,linspace(-ma,ma,ms+1))
flat = interpolation.rotate(flat,angle,mode='constant',reshape=0)
flat = amax(flat)-flat
return flat, angle



def binary(flat, bignore=0.1, escale=1.0, lo=5, hi=90, threshold=0.5, debug=0):
'''# estimate low and high thresholds
ignore this much of the border for threshold estimation, default: %(default)s
scale for estimating a mask over the text region, default: %(default)s
lo percentile for black estimation, default: %(default)s
hi percentile for white estimation, default: %(default)s
threshold, determines lightness, default: %(default)s
'''
d0,d1 = flat.shape
o0,o1 = int(bignore*d0),int(bignore*d1)
est = flat[o0:d0-o0,o1:d1-o1]
if escale>0:
# by default, we use only regions that contain
# significant variance; this makes the percentile
# based low and high estimates more reliable
e = 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 debug>0: imshow(v); ginput(1,debug)
est = est[v]
lo = stats.scoreatpercentile(est.ravel(),lo)
hi = stats.scoreatpercentile(est.ravel(),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 debug>0: imshow(flat,vmin=0,vmax=1); ginput(1,debug)
bin = 1*(flat>threshold)
return bin


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)
image = normalze(raw)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Typo?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you !


if not args.nocheck:
check = check_page(amax(image)-image)
Expand All @@ -114,57 +190,18 @@ def process1(job):
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)
flat = estimate_local_whitelevel(image, args.zoom, args.perc, args.range, args.debug)

# 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
flat, angle = estimate_skew(flat, args.bignore, args.maxskew, args.skewsteps)
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)
bin = binary(flat, args.bignore, args.escale, args.lo, args.hi, args.threshold, args.debug)

# output the normalized grayscale and the thresholded images
print_info("%s lo-hi (%.2f %.2f) angle %4.1f %s" % (fname, lo, hi, angle, comment))
Expand Down