def processOneLineImage(gray_img, iTag):
(_, img) = cv2.threshold(gray_img, 110, 255, cv2.THRESH_BINARY_INV)
img = img[:, 2 : img.shape[1] - 2]
scale = psegutils.estimate_scale(img)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 1))
closed = cv2.dilate(img, kernel, iterations=1)
edges = cv2.Canny(closed, 60, 300)
contours, hierarchy = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(edges, contours, -1, (255, 255, 255), 1)
# cv2.imwrite('edges%s.png' % iTag,edges)
boxmap = psegutils.compute_boxmap(img, scale, threshold=(0.4, 10), dtype="B")
# combineBoxmap(boxmap)
cv2.imwrite("box%s.png" % iTag, boxmap * 255)
h_projection = hprojection(boxmap * 255)
top, bottom = cropProjection(h_projection)
regions = splitProjection(h_projection, top, bottom, 30, 2)
# print iTag, top,bottom
# print regions
# print v_projection[1270:1450]
if len(iTag) == 0:
return regions, top, bottom
for region in regions:
topStart, TopEnd = region
cr_img = cv2.getRectSubPix(
gray_img, (gray_img.shape[1] - 4, TopEnd - topStart + 8), (gray_img.shape[1] / 2, (TopEnd + topStart) / 2)
)
cv2.imwrite("%sx%d.png" % (iTag, topStart), cr_img)
return regions, top, bottom
def processOneLineImage(gray_img, iTag):
(_, img) = cv2.threshold(gray_img, 110, 255, cv2.THRESH_BINARY_INV)
img = img[:, 2:img.shape[1]-2]
scale = psegutils.estimate_scale(img)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 1))
closed = cv2.dilate(img, kernel, iterations = 1)
edges = cv2.Canny(closed,60,300)
contours, hierarchy = cv2.findContours(edges, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(edges,contours,-1,(255,255,255),1)
#cv2.imwrite('edges%s.png' % iTag,edges)
boxmap = psegutils.compute_boxmap(img,scale,threshold=(.4,10),dtype='B')
#combineBoxmap(boxmap)
cv2.imwrite('box%s.png' % iTag, boxmap*255)
h_projection = hprojection(boxmap*255)
top, bottom = cropProjection(h_projection)
regions = splitProjection(h_projection, top, bottom,30,2)
#print iTag, top,bottom
#print regions
#print v_projection[1270:1450]
if len(iTag) == 0:
return regions,top,bottom
for region in regions:
topStart, TopEnd = region
cr_img =cv2.getRectSubPix(gray_img, (gray_img.shape[1]-4, TopEnd-topStart+8), (gray_img.shape[1]/2, (TopEnd+topStart)/2))
cv2.imwrite('%sx%d.png' % (iTag, topStart), cr_img)
return regions,top,bottom
def compute_gradmaps(binary, scale):
# use gradient filtering to find baselines
boxmap = psegutils.compute_boxmap(binary, scale, (0.4, 5))
cleaned = boxmap * binary
####imsave('/home/gupta/Documents/cleaned.png', cleaned)
####imsave('/home/gupta/Documents/boxmap.png', boxmap)
# DSAVE("cleaned",cleaned)
if args.usegauss:
# this uses Gaussians
grad = gaussian_filter(
1.0 * cleaned,
(args.vscale * 0.3 * scale, args.hscale * 6 * scale),
order=(1, 0))
else:
# this uses non-Gaussian oriented filters
grad = gaussian_filter(
1.0 * cleaned,
(max(4, args.vscale * 0.3 * scale), args.hscale * scale),
order=(1, 0))
grad = uniform_filter(grad, (args.vscale, args.hscale * 6 * scale))
bottom = ocrolib.norm_max((grad < 0) * (-grad))
top = ocrolib.norm_max((grad > 0) * grad)
testseeds = zeros(binary.shape, 'i')
####imsave('/home/gupta/Documents/grad.png', grad)
####imsave('/home/gupta/Documents/top.png', [testseeds,1.0*top,binary])
####imsave('/home/gupta/Documents/bottom.png', [testseeds,1.0*bottom,binary])
return bottom, top, boxmap
def compute_gradmaps(binary, scale):
# use gradient filtering to find baselines
boxmap = psegutils.compute_boxmap(binary, scale)
cleaned = boxmap * binary
grad = gaussian_filter(1.0 * cleaned, (max(4, 0.3 * scale),
scale), order=(1, 0))
grad = uniform_filter(grad, (1.0, 1.0 * 6 * scale))
bottom = norm_max((grad < 0) * (-grad))
top = norm_max((grad > 0) * grad)
return bottom, top, boxmap
def compute_colseps_morph(binary, scale, maxseps=3, minheight=20, maxwidth=5):
"""Finds extended vertical whitespace corresponding to column separators
using morphological operations."""
boxmap = psegutils.compute_boxmap(binary, scale, (0.4, 5), dtype='B')
bounds = morph.rb_closing(B(boxmap), (int(5 * scale), int(5 * scale)))
bounds = maximum(B(1 - bounds), B(boxmap))
cols = 1 - morph.rb_closing(boxmap, (int(20 * scale), int(scale)))
cols = morph.select_regions(cols, sl.aspect, min=args.csminaspect)
cols = morph.select_regions(cols,
sl.dim0,
min=args.csminheight * scale,
nbest=args.maxcolseps)
cols = morph.r_erosion(cols, (int(0.5 + scale), 0))
cols = morph.r_dilation(cols, (int(0.5 + scale), 0),
origin=(int(scale / 2) - 1, 0))
return cols
def compute_gradmaps(binary,scale,vscale=1.0,hscale=1.0,usegauss=False):
# use gradient filtering to find baselines
boxmap = psegutils.compute_boxmap(binary,scale)
cleaned = boxmap*binary
#DSAVE("cleaned",cleaned)
if usegauss:
# this uses Gaussians
grad = gaussian_filter(1.0*cleaned,(vscale*0.3*scale,
hscale*6*scale),order=(1,0))
else:
# this uses non-Gaussian oriented filters
grad = gaussian_filter(1.0*cleaned,(max(4,vscale*0.3*scale),
hscale*scale),order=(1,0))
grad = uniform_filter(grad,(vscale,hscale*6*scale))
bottom = ocrolib.norm_max((grad<0)*(-grad))
top = ocrolib.norm_max((grad>0)*grad)
return bottom,top,boxmap
def compute_colseps_morph(self, binary, scale):
"""Finds extended vertical whitespace corresponding to column separators
using morphological operations."""
boxmap = psegutils.compute_boxmap(binary, scale, dtype='B')
bounds = morph.rb_closing(B(boxmap), (int(5 * scale), int(5 * scale)))
bounds = np.maximum(B(1 - bounds), B(boxmap))
cols = 1 - morph.rb_closing(boxmap, (int(20 * scale), int(scale)))
cols = morph.select_regions(cols,
sl.aspect,
min=self.parameter['csminaspect'])
cols = morph.select_regions(cols,
sl.dim0,
min=self.parameter['csminheight'] * scale,
nbest=self.parameter['maxcolseps'])
cols = morph.r_erosion(cols, (int(0.5 + scale), 0))
cols = morph.r_dilation(cols, (int(0.5 + scale), 0),
origin=(int(scale / 2) - 1, 0))
return cols
def compute_gradmaps(binary, scale, usegauss, vscale, hscale):
# use gradient filtering to find baselines
boxmap = psegutils.compute_boxmap(binary, scale)
cleaned = boxmap * binary
DSAVE("cleaned", cleaned)
if usegauss:
# this uses Gaussians
grad = gaussian_filter(1.0 * cleaned,
(vscale * 0.3 * scale, hscale * 6 * scale),
order=(1, 0))
else:
# this uses non-Gaussian oriented filters
grad = gaussian_filter(1.0 * cleaned,
(max(4, vscale * 0.3 * scale), hscale * scale),
order=(1, 0))
grad = uniform_filter(grad, (vscale, hscale * 6 * scale))
bottom = ocrolib.norm_max((grad < 0) * (-grad))
top = ocrolib.norm_max((grad > 0) * grad)
return bottom, top, boxmap
def compute_gradmaps(self, binary, scale):
# use gradient filtering to find baselines
boxmap = psegutils.compute_boxmap(binary, scale)
cleaned = boxmap * binary
if self.parameter['usegauss']:
# this uses Gaussians
grad = gaussian_filter(1.0 * cleaned,
(self.parameter['vscale'] * 0.3 * scale,
self.parameter['hscale'] * 6 * scale),
order=(1, 0))
else:
# this uses non-Gaussian oriented filters
grad = gaussian_filter(
1.0 * cleaned, (max(4, self.parameter['vscale'] * 0.3 * scale),
self.parameter['hscale'] * scale),
order=(1, 0))
grad = uniform_filter(grad, (self.parameter['vscale'],
self.parameter['hscale'] * 6 * scale))
bottom = ocrolib.norm_max((grad < 0) * (-1 * grad))
top = ocrolib.norm_max((grad > 0) * grad)
return bottom, top, boxmap
