def compute_segmentation(binary, scale, blackseps, maxseps, maxcolseps,
csminheight, sepwiden, usegauss, vscale, hscale,
threshold, quiet):
"""Given a binary image, compute a complete segmentation into
lines, computing both columns and text lines."""
binary = np.array(binary, 'B')
# start by removing horizontal black lines, which only
# interfere with the rest of the page segmentation
binary = remove_hlines(binary, scale)
# do the column finding
if not quiet: print_info("computing column separators")
colseps, binary = compute_colseps(binary, scale, blackseps, maxseps,
maxcolseps, csminheight, sepwiden)
# now compute the text line seeds
if not quiet: print_info("computing lines")
bottom, top, boxmap = compute_gradmaps(binary, scale, usegauss, vscale,
hscale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale, threshold,
vscale)
DSAVE("seeds", [bottom, top, boxmap])
# spread the text line seeds to all the remaining
# components
if not quiet: print_info("propagating labels")
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
if not quiet: print_info("spreading labels")
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
return segmentation
def compute_segmentation(binary, scale):
"""Given a binary image, compute a complete segmentation into lines, computing both columns and
text lines.
"""
print("$$ compute_segmentation: %s %g" % (desc(binary), scale))
binary = np.array(binary, 'B')
# start by removing horizontal black lines, which only interfere with the rest of the page
# segmentation
binary = remove_hlines(binary, scale)
# do the column finding
print("computing column separators")
colseps, binary = compute_colseps(binary, scale)
# now compute the text line seeds
print("computing lines")
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
print("seeds=%s" % desc(seeds))
DSAVE("seeds", [bottom, top, boxmap])
# spread the text line seeds to all the remaining components
print("propagating labels")
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
print("spreading labels: llabels=%s" % desc(llabels))
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
print("$$ llabels: %s" % desc(llabels))
print("$$ segmentation: %s" % desc(segmentation))
return segmentation
def text_line_segmentation(binary, scale=None, gray=None, num_col = 1):
"""Given a binary image, compute a complete segmentation into
lines, computing both columns and text lines."""
binary = array(binary, 'B')
if scale is None:
scale = psegutils.estimate_scale(binary)
# do the column finding
if num_col > 1:
colseps, binary = compute_colseps(binary, scale)
else:
colseps = np.zeros(binary.shape)
# now compute the text line seeds
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
# spread the text line seeds to all the remaining components
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
lines = psegutils.compute_lines(segmentation, scale, 0.8)
line_ims = []
for l in lines:
if gray is None:
binline = psegutils.extract_masked(1-binary, l, pad=0)
else:
binline = psegutils.extract_masked(gray, l, pad=0)
binline = pad_by(binline, 10, invert=False)
line_ims.append(binline)
return line_ims, lines
def compute_segmentation(binary, scale):
"""Given a binary image, compute a complete segmentation into
lines, computing both columns and text lines."""
binary = array(binary, 'B')
# start by removing horizontal black lines, which only
# interfere with the rest of the page segmentation
binary = remove_hlines(binary, scale)
# do the column finding
if not args.quiet:
print("computing column separators")
colseps, binary = compute_colseps(binary, scale)
# now compute the text line seeds
if not args.quiet:
print("computing lines")
bottom, top, boxmap = compute_gradmaps(binary, scale)
seeds = compute_line_seeds(binary, bottom, top, colseps, scale)
####imsave('/home/gupta/Documents/combinedseeds.png', [bottom,top,boxmap])
# DSAVE("seeds",[bottom,top,boxmap])
# spread the text line seeds to all the remaining
# components
if not args.quiet:
print("propagating labels")
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
if not args.quiet:
print("spreading labels")
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
return segmentation
def compute_segmentation(self, binary, scale):
"""Given a binary image, compute a complete segmentation into
lines, computing both columns and text lines."""
binary = np.array(binary, 'B')
# start by removing horizontal black lines, which only
# interfere with the rest of the page segmentation
binary = self.remove_hlines(binary, scale)
# do the column finding
log.debug("computing column separators")
colseps, binary = self.compute_colseps(binary, scale)
# now compute the text line seeds
log.debug("computing lines")
bottom, top, boxmap = self.compute_gradmaps(binary, scale)
log.debug("bottom=%s top=%s boxmap=%s", bottom, top, boxmap)
seeds = self.compute_line_seeds(binary, bottom, top, colseps, scale)
# spread the text line seeds to all the remaining
# components
log.debug("propagating labels")
llabels = morph.propagate_labels(boxmap, seeds, conflict=0)
log.debug("spreading labels")
spread = morph.spread_labels(seeds, maxdist=scale)
llabels = np.where(llabels > 0, llabels, spread * binary)
segmentation = llabels * binary
return segmentation
def compute_segmentation(binary,scale):
"""Given a binary image, compute a complete segmentation into
lines, computing both columns and text lines."""
binary = array(binary,'B')
# start by removing horizontal black lines, which only
# interfere with the rest of the page segmentation
binary = remove_hlines(binary,scale)
# do the column finding
colseps,binary = compute_colseps(binary,scale)
# now compute the text line seeds
bottom,top,boxmap = compute_gradmaps(binary,scale)
seeds = compute_line_seeds(binary,bottom,top,colseps,scale)
#DSAVE("seeds",[bottom,top,boxmap])
# spread the text line seeds to all the remaining
# components
llabels = morph.propagate_labels(boxmap,seeds,conflict=0)
spread = morph.spread_labels(seeds,maxdist=scale)
llabels = where(llabels>0,llabels,spread*binary)
segmentation = llabels*binary
return segmentation
