def splitimage(image):
dpmm = min(image.shape[0:2]) / DOCSIZE[0]
sizethresh = SIZE_THRESH_MM * dpmm
uprightimg = makeupright(image)
grayimg = getgrayimage(uprightimg)
# top line
top = grayimg[0, :]
sepx = [
0,
]
ret, binimg = cv2.threshold(top, 0, 255,
cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(
binimg)
for i in range(1, nlabels):
if stats[i, cv2.CC_STAT_AREA] >= sizethresh:
sepx.append(centroids[i][1])
# left line
left = grayimg[:, 0]
sepy = [
0,
]
ret, binimg = cv2.threshold(left, 0, 255,
cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(
binimg)
for i in range(1, nlabels):
if stats[i, cv2.CC_STAT_AREA] >= sizethresh:
sepy.append(centroids[i][1])
# divide into images
imgs = []
for iy in range(len(sepy)):
for ix in range(len(sepx)):
if iy == len(sepy) - 1:
if ix == len(sepx) - 1:
#right-bottom corner
imgs.append(uprightimg[int(sepy[iy]):, int(sepx[ix]):])
else:
#bottom end
imgs.append(uprightimg[int(sepy[iy]):,
int(sepx[ix]):int(sepx[ix + 1])])
else:
if ix == len(sepx) - 1:
#right end
imgs.append(uprightimg[int(sepy[iy]):int(sepy[iy + 1]),
int(sepx[ix]):])
else:
#others
imgs.append(uprightimg[int(sepy[iy]):int(sepy[iy + 1]),
int(sepx[ix]):int(sepx[ix + 1])])
return imgs
def scanchars(img, outdir, verbose=True):
wholeimage = slantcorrection.correctslant(img)
markersize = getapproxmarkersize(wholeimage)
#dpmm = min(img.shape[0:2]) / DOCSIZE[0]
imgs = splitimage(wholeimage)
resol = detectresol(imgs.pop())
if resol == None:
if verbose:
print(
'QR Code for the page cannot be detected. skipping the image')
return
for im in imgs:
name, croppedimg = getcroppedarea(im, markersize)
if name == None:
continue
grayimg = getgrayimage(croppedimg)
ret, binimg = cv2.threshold(grayimg, 0, 255,
cv2.THRESH_BINARY + cv2.THRESH_OTSU)
if verbose:
print(name, end=" ")
sys.stdout.flush()
#cv2.imwrite("chr/"+name+".jpg", croppedimg)
imgheight = 1000
margintop = int(imgheight * resol[1][0] /
resol[1][1]) #-h[px] * (margint[mm]/h[mm])
marginbottom = int(imgheight * resol[1][2] /
resol[1][1]) #-h[px] * (marginb[mm]/h[mm])
imgwidth = int(imgheight * resol[0][1] /
resol[1][1]) #h[px] * (w[mm]/h[mm])
marginleft = int(imgheight * resol[0][0] /
resol[1][1]) #-h[px] * (marginl[mm]/h[mm])
marginright = int(imgheight * resol[0][2] /
resol[1][1]) #-h[px] * (marginr[mm]/h[mm])
# potrace cannot set size in px when converting to SVG.
# set size in pt and convert to SVG, after that, replace pt with px
optargs = [
"-W%dpt" % (imgwidth + marginleft + marginright),
"-H%dpt" % (imgheight + margintop + marginbottom),
"-L%dpt" % (-marginleft),
"-R%dpt" % (-marginright),
"-T%dpt" % (-margintop),
"-B%dpt" % (-marginbottom)
]
bsvg = passpotrace.passpotrace(binimg, optargs)
bsvg = bsvg.replace(b"pt", b"px") # any exceptions?
#save function
if outdir != '' and not os.path.isdir(outdir):
os.makedirs(outdir)
saveasfile(outdir, name, bsvg)
#break
if verbose:
print("")
def makeupright(image):
#binarize image
grayimg = getgrayimage(image)
ret, binimg = cv2.threshold(grayimg,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# markers which are placed for dividing make
# the top line darker than the bottom line
nwhitefirst = np.count_nonzero(binimg[0,:]) #first line
nwhitelast = np.count_nonzero(binimg[-1,:]) #last line
if nwhitefirst <= nwhitelast: # upright
return image
else:
return np.rot90(image, k=2)
def makeupright(image):
#binarize image
grayimg = getgrayimage(image)
ret, binimg = cv2.threshold(grayimg, 0, 255,
cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# markers which are placed for dividing make
# the top line darker than the bottom line
nwhitefirst = np.count_nonzero(binimg[0, :]) #first line
nwhitelast = np.count_nonzero(binimg[-1, :]) #last line
if nwhitefirst <= nwhitelast: # upright
return image
else:
return np.rot90(image, k=2)
def detectmarker(image):
grayscale = getgrayimage(image)
mkradius = getapproxmarkerradius(grayscale) # approximate marker radius
marker = cv2.resize(MARKER, (mkradius*2, mkradius*2)) # resize the marker
#template matching
matched = cv2.matchTemplate(grayscale, marker, cv2.TM_CCORR_NORMED) #returns float32
#detect 4 greatest values
markerposarray = []
for i in range(4):
(minval, maxval, minloc, maxloc) = cv2.minMaxLoc(matched)
markerposarray.append(tuple(map(lambda x: x+mkradius, maxloc)))
cv2.circle(matched, maxloc, mkradius, (0.0), -1) #ignore near the current minloc
return markerposarray
def splitimage(image):
dpmm = min(image.shape[0:2]) / DOCSIZE[0]
sizethresh = SIZE_THRESH_MM * dpmm
uprightimg = makeupright(image)
grayimg = getgrayimage(uprightimg)
# top line
top = grayimg[0,:]
sepx = [0,]
ret, binimg = cv2.threshold(top,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binimg)
for i in range(1,nlabels):
if stats[i,cv2.CC_STAT_AREA] >= sizethresh:
sepx.append(centroids[i][1])
# left line
left = grayimg[:,0]
sepy = [0,]
ret, binimg = cv2.threshold(left,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binimg)
for i in range(1,nlabels):
if stats[i,cv2.CC_STAT_AREA] >= sizethresh:
sepy.append(centroids[i][1])
# divide into images
imgs = []
for iy in range(len(sepy)):
for ix in range(len(sepx)):
if iy == len(sepy) - 1:
if ix == len(sepx) - 1:
#right-bottom corner
imgs.append(uprightimg[int(sepy[iy]):,int(sepx[ix]):])
else:
#bottom end
imgs.append(uprightimg[int(sepy[iy]):,int(sepx[ix]):int(sepx[ix+1])])
else:
if ix == len(sepx) - 1:
#right end
imgs.append(uprightimg[int(sepy[iy]):int(sepy[iy+1]),int(sepx[ix]):])
else:
#others
imgs.append(uprightimg[int(sepy[iy]):int(sepy[iy+1]),int(sepx[ix]):int(sepx[ix+1])])
return imgs
def scanchars(img, outdir, verbose=True):
wholeimage = slantcorrection.correctslant(img)
markersize = getapproxmarkersize(wholeimage)
#dpmm = min(img.shape[0:2]) / DOCSIZE[0]
imgs = splitimage(wholeimage)
resol = detectresol(imgs.pop())
if resol == None:
if verbose:
print('QR Code for the page cannot be detected. skipping the image')
return
for im in imgs:
name, croppedimg = getcroppedarea(im, markersize)
if name == None:
continue
grayimg = getgrayimage(croppedimg)
ret, binimg = cv2.threshold(grayimg,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
if verbose:
print(name, end=" ")
sys.stdout.flush()
#cv2.imwrite("chr/"+name+".jpg", croppedimg)
imgheight = 1000
margintop = int(imgheight * resol[1][0] / resol[1][1]) #-h[px] * (margint[mm]/h[mm])
marginbottom= int(imgheight * resol[1][2] / resol[1][1]) #-h[px] * (marginb[mm]/h[mm])
imgwidth = int(imgheight * resol[0][1] / resol[1][1]) #h[px] * (w[mm]/h[mm])
marginleft = int(imgheight * resol[0][0] / resol[1][1]) #-h[px] * (marginl[mm]/h[mm])
marginright = int(imgheight * resol[0][2] / resol[1][1]) #-h[px] * (marginr[mm]/h[mm])
# potrace cannot set size in px when converting to SVG.
# set size in pt and convert to SVG, after that, replace pt with px
optargs = [ "-W%dpt"%(imgwidth + marginleft + marginright),
"-H%dpt"%(imgheight + margintop + marginbottom),
"-L%dpt"%(- marginleft), "-R%dpt"%(- marginright),
"-T%dpt"%(- margintop), "-B%dpt"%(- marginbottom)]
bsvg = passpotrace.passpotrace(binimg, optargs)
bsvg = bsvg.replace(b"pt", b"px") # any exceptions?
#save function
if outdir != '' and not os.path.isdir(outdir):
os.makedirs(outdir)
saveasfile(outdir, name, bsvg)
#break
if verbose:
print("")
def getmarkercenter(image, pos):
mkradius = getapproxmarkerradius(image)
buffer = int(mkradius * 0.15)
roisize = mkradius + buffer # half of the height or width
x = pos[0] - roisize
y = pos[1] - roisize
w = 2 * roisize
h = 2 * roisize
roi = image[y:y+h, x:x+w]
grayroi = getgrayimage(roi)
ret, binimage = cv2.threshold(grayroi,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binimage)
# stats[0], centroids[0] are for the background label. ignore
lblareas = stats[1:,cv2.CC_STAT_AREA]
ave = np.average(centroids[1:], axis=0, weights=lblareas)
return tuple(np.array([x, y]) + ave) # weighted average pos of centroids
def detectmarker(image):
grayscale = getgrayimage(image)
mkradius = getapproxmarkerradius(grayscale) # approximate marker radius
marker = cv2.resize(MARKER,
(mkradius * 2, mkradius * 2)) # resize the marker
#template matching
matched = cv2.matchTemplate(grayscale, marker,
cv2.TM_CCORR_NORMED) #returns float32
#detect 4 greatest values
markerposarray = []
for i in range(4):
(minval, maxval, minloc, maxloc) = cv2.minMaxLoc(matched)
markerposarray.append(tuple(map(lambda x: x + mkradius, maxloc)))
cv2.circle(matched, maxloc, mkradius, (0.0),
-1) #ignore near the current minloc
return markerposarray
def getmarkerboundingrect(img, mkpos, mksize):
buffer = int(mksize * 0.15)
x = mkpos[0] - buffer
y = mkpos[1] - buffer
w = mksize + buffer*2
h = mksize + buffer*2
roi = img[y:y+h, x:x+w]
grayroi = getgrayimage(roi)
ret, binimage = cv2.threshold(grayroi,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(binimage)
# stats[0], centroids[0] are for the background label. ignore
# cv2.CC_STAT_LEFT, cv2.CC_STAT_TOP, cv2.CC_STAT_WIDTH, cv2.CC_STAT_HEIGHT
lblareas = stats[1:,cv2.CC_STAT_AREA]
imax = max(enumerate(lblareas), key=(lambda x: x[1]))[0] + 1
boundingrect = Rect(stats[imax, cv2.CC_STAT_LEFT],
stats[imax, cv2.CC_STAT_TOP],
stats[imax, cv2.CC_STAT_WIDTH],
stats[imax, cv2.CC_STAT_HEIGHT])
return boundingrect.addoffset((x,y))
def getmarkercenter(image, pos):
mkradius = getapproxmarkerradius(image)
buffer = int(mkradius * 0.15)
roisize = mkradius + buffer # half of the height or width
x = pos[0] - roisize
y = pos[1] - roisize
w = 2 * roisize
h = 2 * roisize
roi = image[y:y + h, x:x + w]
grayroi = getgrayimage(roi)
ret, binimage = cv2.threshold(grayroi, 0, 255,
cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(
binimage)
# stats[0], centroids[0] are for the background label. ignore
lblareas = stats[1:, cv2.CC_STAT_AREA]
ave = np.average(centroids[1:], axis=0, weights=lblareas)
return tuple(np.array([x, y]) + ave) # weighted average pos of centroids
def getcroppedarea(img, markersize):
#use template matching to detect area to be cropped
grayimg = getgrayimage(img)
# detect top-left marker using template matching
marker_tl = cv2.resize(MARKER_TL, (markersize, markersize))
matched = cv2.matchTemplate(grayimg, marker_tl,
cv2.TM_CCORR_NORMED) #returns float32
(minval, maxval, minloc, maxloc) = cv2.minMaxLoc(matched)
mkrect = getmarkerboundingrect(grayimg, maxloc, markersize)
pos_tl = (mkrect.x + mkrect.w, mkrect.y + mkrect.h)
#pos_tl = (maxloc[0]+markersize, maxloc[1]+markersize)
# detect bottom-right marker using template matching
marker_br = cv2.resize(MARKER_BR, (markersize, markersize))
matched = cv2.matchTemplate(grayimg, marker_br,
cv2.TM_CCORR_NORMED) #returns float32
(minval, maxval, minloc, maxloc) = cv2.minMaxLoc(matched)
mkrect = getmarkerboundingrect(grayimg, maxloc, markersize)
pos_br = (mkrect.x, mkrect.y)
#pos_br = maxloc
#detect QR code
qrarea = img[pos_br[1]:, :img.shape[0] - pos_br[1]]
typ, val = passzbar.passzbar(qrarea)
if not typ:
return None, None
strval = val.decode('ascii').strip()
#print(strval)
#cv2.circle(img, pos_tl, 5, (255, 0, 0), -1)
#cv2.circle(img, pos_br, 5, (0, 255, 0), -1)
#print(pos_tl, pos_br
#cv2.imshow("hoge", img)
#cv2.imshow("hoge", img[pos_tl[1]:pos_br[1], pos_tl[0]:pos_br[0]])
# crop and return detected area
return strval, img[pos_tl[1]:pos_br[1], pos_tl[0]:pos_br[0]]
def getmarkerboundingrect(img, mkpos, mksize):
buffer = int(mksize * 0.15)
x = mkpos[0] - buffer
y = mkpos[1] - buffer
w = mksize + buffer * 2
h = mksize + buffer * 2
roi = img[y:y + h, x:x + w]
grayroi = getgrayimage(roi)
ret, binimage = cv2.threshold(grayroi, 0, 255,
cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(
binimage)
# stats[0], centroids[0] are for the background label. ignore
# cv2.CC_STAT_LEFT, cv2.CC_STAT_TOP, cv2.CC_STAT_WIDTH, cv2.CC_STAT_HEIGHT
lblareas = stats[1:, cv2.CC_STAT_AREA]
imax = max(enumerate(lblareas), key=(lambda x: x[1]))[0] + 1
boundingrect = Rect(stats[imax, cv2.CC_STAT_LEFT],
stats[imax, cv2.CC_STAT_TOP], stats[imax,
cv2.CC_STAT_WIDTH],
stats[imax, cv2.CC_STAT_HEIGHT])
return boundingrect.addoffset((x, y))
def getcroppedarea(img, markersize):
#use template matching to detect area to be cropped
grayimg = getgrayimage(img)
# detect top-left marker using template matching
marker_tl = cv2.resize(MARKER_TL, (markersize, markersize))
matched = cv2.matchTemplate(grayimg, marker_tl, cv2.TM_CCORR_NORMED) #returns float32
(minval, maxval, minloc, maxloc) = cv2.minMaxLoc(matched)
mkrect = getmarkerboundingrect(grayimg, maxloc, markersize)
pos_tl = (mkrect.x+mkrect.w, mkrect.y+mkrect.h)
#pos_tl = (maxloc[0]+markersize, maxloc[1]+markersize)
# detect bottom-right marker using template matching
marker_br = cv2.resize(MARKER_BR, (markersize, markersize))
matched = cv2.matchTemplate(grayimg, marker_br, cv2.TM_CCORR_NORMED) #returns float32
(minval, maxval, minloc, maxloc) = cv2.minMaxLoc(matched)
mkrect = getmarkerboundingrect(grayimg, maxloc, markersize)
pos_br = (mkrect.x, mkrect.y)
#pos_br = maxloc
#detect QR code
qrarea = img[pos_br[1]:,:img.shape[0]-pos_br[1]]
typ, val = passzbar.passzbar(qrarea)
if not typ:
return None, None
strval = val.decode('ascii').strip()
#print(strval)
#cv2.circle(img, pos_tl, 5, (255, 0, 0), -1)
#cv2.circle(img, pos_br, 5, (0, 255, 0), -1)
#print(pos_tl, pos_br
#cv2.imshow("hoge", img)
#cv2.imshow("hoge", img[pos_tl[1]:pos_br[1], pos_tl[0]:pos_br[0]])
# crop and return detected area
return strval, img[pos_tl[1]:pos_br[1], pos_tl[0]:pos_br[0]]