def lu2010(im):
im_h, im_w = im.shape
# im_bg_row = polynomial_background_easy(im) # TODO: implement full
# im_bg = polynomial_background_easy(im_bg_row.T).T
# im_bg = im_bg.clip(0.1, 255)
IM = cv2.erode(niblack(im, window_size=61, k=0.2), rect33)
inpainted, modified = inpaint.inpaint_ng14(im, -IM)
im_bg = (inpainted & ~IM) | (modified & IM)
im_bg = im_bg.astype(np.float32).clip(0.1, 255)
debug_imwrite('bg.png', im_bg)
C = np.percentile(im, 30)
I_bar = clip_u8(C / im_bg * im)
debug_imwrite('ibar.png', I_bar)
I_bar_padded = np.pad(I_bar, (1, 1), 'edge')
V_h = cv2.absdiff(I_bar_padded[2:, 1:-1], I_bar_padded[:-2, 1:-1])
V_v = cv2.absdiff(I_bar_padded[1:-1, 2:], I_bar_padded[1:-1, :-2])
V = V_h + V_v
V[V < V_h] = 255 # clip overflow
_, stroke_edges = cv2.threshold(V, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# 1 if high contrast, 0 otherwise.
E_inv = stroke_edges & 1
E_inv_255 = E_inv * 255
debug_imwrite('e_inv.png', E_inv_255)
im_high = im & E_inv_255
debug_imwrite('im_high.png', im_high)
# calculate stroke width
H, _ = np.histogram(nonzero_distances_row(E_inv), np.arange(im_h / 100))
H[1] = 0 # don't use adjacent pix
W = H.argmax()
print('stroke width:', W)
size = 2 * W
N_min = W
if size >= 16:
E_inv = E_inv.astype(np.uint16)
window = (size | 1, size | 1)
N_e = cv2.boxFilter(E_inv, -1, window, normalize=False)
debug_imwrite('n_e.png', bool_to_u8(N_e >= N_min))
E_mean = cv2.boxFilter(im_high, cv2.CV_32S, window,
normalize=False) / (N_e.astype(np.float64) + 0.1)
debug_imwrite('i_bar_e_mean.png', bool_to_u8(I_bar <= E_mean))
out = ~bool_to_u8((N_e >= N_min) & (I_bar <= E_mean))
debug_imwrite('lu2010.png', out)
return out
def gradient2(im):
im_inv = ~im
mins = erode_square(im_inv, 15)
maxes = dilate_square(im_inv, 15)
diff = maxes - mins
return bool_to_u8(diff < 50)
def remove_stroke_outliers(im, lines, k=1.0):
stroke_widths = fast_stroke_width(im)
if lib.debug:
lib.debug_imwrite('strokes.png',
lib.normalize_u8(stroke_widths.clip(0, 10)))
mask = np.zeros(im.shape, dtype=np.uint8)
for line in lines:
for letter in line:
sliced = letter.crop().apply(mask)
sliced |= letter.raster()
lib.debug_imwrite('letter_mask.png', -mask)
masked_strokes = stroke_widths.copy()
masked_strokes &= -mask
strokes_mean, strokes_std = masked_mean_std(masked_strokes, mask)
if lib.debug:
print('overall: mean:', strokes_mean, 'std:', strokes_std)
debug = cv2.cvtColor(im, cv2.COLOR_GRAY2RGB)
new_lines = []
for line in lines:
if len(line) <= 1: continue
good_letters = []
for letter in line:
crop = letter.crop()
if not crop.nonempty(): continue
raster = letter.raster()
sliced_strokes = crop.apply(stroke_widths).copy()
sliced_strokes &= lib.bool_to_u8(raster)
mean, std = masked_mean_std(sliced_strokes, raster)
if mean < strokes_mean - k * strokes_std:
if lib.debug:
print('skipping {:4d} {:4d} {:.03f} {:.03f}'.format(
letter.x,
letter.y,
mean,
std,
))
letter.box(debug, color=lib.RED)
else:
if lib.debug: letter.box(debug, color=lib.GREEN)
good_letters.append(letter)
if good_letters:
new_lines.append(TextLine(good_letters,
underlines=line.underlines))
lib.debug_imwrite("stroke_filter.png", debug)
return new_lines
def retinex(im, mu_1=0.9, mu_2=25, sigma=5):
G = cv2.GaussianBlur(im, (0, 0), sigma)
debug_imwrite('G.png', G)
bools = (im < mu_1 * G) & (cv2.absdiff(im, G) > mu_2)
return bool_to_u8(bools)
def roth(im, s=51, t=0.8):
im_h, im_w = im.shape
means = cv2.blur(im, (s, s))
ints = cv2.bitwise_not(bool_to_u8(im > means * t))
debug_imwrite('roth.png', ints)
return ints
def sauvola(im, window_size=61, k=0.2):
assert im.dtype == np.uint8
means, stds = mean_std(im, window_size)
thresh = means * (1 + k * ((stds / 127) - 1))
return bool_to_u8(im > thresh)
def niblack(im, window_size=61, k=0.2):
means, stds = mean_std(im, window_size)
thresh = means + k * stds
return bool_to_u8(im > thresh)
