qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2026-05-13 01:13:54 +02:00
Code Issues Projects Releases Wiki Activity

Merge remote-tracking branch 'bertsky/ro-fixes-final' into prepare-release-v0.8.0

Browse source 
# Conflicts:
#	requirements-ocr.txt
This commit is contained in:
kba 2026-05-11 09:46:17 +02:00
commit 2035b07b55
3 changed files with 187 additions and 254 deletions
Download patch file Download diff file Expand all files Collapse all files

2
requirements-ocr.txt
View file

@ -1,3 +1,3 @@
torch
transformers < 5 ; python_version < '3.10'
transformers <= 4.30.2 ; python_version < '3.10'
transformers >= 5 ; python_version >= '3.10'

14
src/eynollah/utils/contour.py
View file

@ -223,18 +223,12 @@ def get_region_confidences(cnts, confidence_matrix):
confs.append(np.sum(confidence_matrix * cnt_mask) / np.sum(cnt_mask))
return confs
def return_contours_of_interested_textline(region_pre_p, label):
# pixels of images are identified by 5
if region_pre_p.ndim == 3:
cnts_images = (region_pre_p[:, :, 0] == label) * 1
else:
cnts_images = (region_pre_p[:, :] == label) * 1
_, thresh = cv2.threshold(cnts_images.astype(np.uint8), 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
def return_contours_of_interested_textline(region_pre_p, label, min_area=0.0):
cnts_images = (region_pre_p == label).astype(np.uint8)
contours_imgs, hierarchy = cv2.findContours(cnts_images, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(
thresh, contours_imgs, hierarchy, max_area=1, min_area=0.000000003)
cnts_images, contours_imgs, hierarchy, max_area=1, min_area=min_area)
return contours_imgs
def return_contours_of_image(image):

425
src/eynollah/utils/separate_lines.py
View file

@ -45,10 +45,8 @@ def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
x_cont = x_cont - np.min(x_cont)
y_cont = y_cont - np.min(y_cont)
x_min_cont = 0
x_max_cont = img_patch.shape[1]
y_min_cont = 0
y_max_cont = img_patch.shape[0]
y_min_cont, x_min_cont = 0, 0
y_max_cont, x_max_cont = img_patch.shape
xv = np.linspace(x_min_cont, x_max_cont, 1000)
textline_patch_sum_along_width = img_patch.sum(axis=axis)
@ -957,122 +955,93 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
[[int(x_min), int(point_down)]]]))
return peaks, textline_boxes_rot
def separate_lines_new_inside_tiles2(img_patch, thetha):
(h, w) = img_patch.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, -thetha, 1.0)
x_d = M[0, 2]
y_d = M[1, 2]
thetha = thetha / 180.0 * np.pi
rotation_matrix = np.array([[np.cos(thetha), -np.sin(thetha)], [np.sin(thetha), np.cos(thetha)]])
# contour_text_interest_copy = contour_text_interest.copy()
# x_cont = contour_text_interest[:, 0, 0]
# y_cont = contour_text_interest[:, 0, 1]
# x_cont = x_cont - np.min(x_cont)
# y_cont = y_cont - np.min(y_cont)
x_min_cont = 0
x_max_cont = img_patch.shape[1]
y_min_cont = 0
y_max_cont = img_patch.shape[0]
xv = np.linspace(x_min_cont, x_max_cont, 1000)
textline_patch_sum_along_width = img_patch.sum(axis=1)
first_nonzero = 0 # (next((i for i, x in enumerate(mada_n) if x), None))
y = textline_patch_sum_along_width[:] # [first_nonzero:last_nonzero]
y_padded = np.zeros(len(y) + 40)
y_padded[20 : len(y) + 20] = y
x = np.array(range(len(y)))
def separate_lines_new_inside_tiles2(img_patch, _):
y = img_patch.sum(axis=1)
y_padded = np.pad(y, (20,))
x = np.arange(len(y))
peaks_real, _ = find_peaks(gaussian_filter1d(y, 3), height=0)
if 1 > 0:
try:
y_padded_smoothed_e = gaussian_filter1d(y_padded, 2)
y_padded_up_to_down_e = -y_padded + np.max(y_padded)
y_padded_up_to_down_padded_e = np.zeros(len(y_padded_up_to_down_e) + 40)
y_padded_up_to_down_padded_e[20 : len(y_padded_up_to_down_e) + 20] = y_padded_up_to_down_e
y_padded_up_to_down_padded_e = gaussian_filter1d(y_padded_up_to_down_padded_e, 2)
try:
y_padded_smoothed_e = gaussian_filter1d(y_padded, 2)
y_padded_up_to_down_e = -y_padded + np.max(y_padded)
y_padded_up_to_down_padded_e = np.zeros(len(y_padded_up_to_down_e) + 40)
y_padded_up_to_down_padded_e[20 : len(y_padded_up_to_down_e) + 20] = y_padded_up_to_down_e
y_padded_up_to_down_padded_e = gaussian_filter1d(y_padded_up_to_down_padded_e, 2)
peaks_e, _ = find_peaks(y_padded_smoothed_e, height=0)
peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0)
neg_peaks_max = np.max(y_padded_up_to_down_padded_e[peaks_neg_e])
peaks_e, _ = find_peaks(y_padded_smoothed_e, height=0)
peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0)
neg_peaks_max = np.max(y_padded_up_to_down_padded_e[peaks_neg_e])
arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[
y_padded_up_to_down_padded_e[peaks_neg_e] / float(neg_peaks_max) < 0.3]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[
y_padded_up_to_down_padded_e[peaks_neg_e] / float(neg_peaks_max) < 0.3]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
arg_diff_cluster = arg_diff[diff_arg_neg_must_be_deleted > 1]
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
arg_diff_cluster = arg_diff[diff_arg_neg_must_be_deleted > 1]
peaks_new = peaks_e[:]
peaks_neg_new = peaks_neg_e[:]
peaks_new = peaks_e[:]
peaks_neg_new = peaks_neg_e[:]
clusters_to_be_deleted = []
if len(arg_diff_cluster) > 0:
clusters_to_be_deleted.append(arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1])
for i in range(len(arg_diff_cluster) - 1):
clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[i] + 1:
arg_diff_cluster[i + 1] + 1])
clusters_to_be_deleted = []
if len(arg_diff_cluster) > 0:
clusters_to_be_deleted.append(arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1])
for i in range(len(arg_diff_cluster) - 1):
clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :])
if len(clusters_to_be_deleted) > 0:
peaks_new_extra = []
for m in range(len(clusters_to_be_deleted)):
min_cluster = np.min(peaks_e[clusters_to_be_deleted[m]])
max_cluster = np.max(peaks_e[clusters_to_be_deleted[m]])
peaks_new_extra.append(int((min_cluster + max_cluster) / 2.0))
for m1 in range(len(clusters_to_be_deleted[m])):
peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1] - 1]]
peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1]]]
peaks_neg_new = peaks_neg_new[peaks_neg_new != peaks_neg_e[clusters_to_be_deleted[m][m1]]]
peaks_new_tot = []
for i1 in peaks_new:
peaks_new_tot.append(i1)
for i1 in peaks_new_extra:
peaks_new_tot.append(i1)
peaks_new_tot = np.sort(peaks_new_tot)
else:
peaks_new_tot = peaks_e[:]
arg_neg_must_be_deleted[arg_diff_cluster[i] + 1:
arg_diff_cluster[i + 1] + 1])
clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :])
if len(clusters_to_be_deleted) > 0:
peaks_new_extra = []
for m in range(len(clusters_to_be_deleted)):
min_cluster = np.min(peaks_e[clusters_to_be_deleted[m]])
max_cluster = np.max(peaks_e[clusters_to_be_deleted[m]])
peaks_new_extra.append(int((min_cluster + max_cluster) / 2.0))
for m1 in range(len(clusters_to_be_deleted[m])):
peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1] - 1]]
peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1]]]
peaks_neg_new = peaks_neg_new[peaks_neg_new != peaks_neg_e[clusters_to_be_deleted[m][m1]]]
peaks_new_tot = []
for i1 in peaks_new:
peaks_new_tot.append(i1)
for i1 in peaks_new_extra:
peaks_new_tot.append(i1)
peaks_new_tot = np.sort(peaks_new_tot)
else:
peaks_new_tot = peaks_e[:]
textline_con, hierarchy = return_contours_of_image(img_patch)
textline_con_fil = filter_contours_area_of_image(img_patch,
textline_con, hierarchy,
max_area=1, min_area=0.0008)
if len(np.diff(peaks_new_tot)):
y_diff_mean = np.mean(np.diff(peaks_new_tot)) # self.find_contours_mean_y_diff(textline_con_fil)
sigma_gaus = int(y_diff_mean * (7.0 / 40.0))
else:
sigma_gaus = 12
except:
textline_con, hierarchy = return_contours_of_image(img_patch)
textline_con_fil = filter_contours_area_of_image(img_patch,
textline_con, hierarchy,
max_area=1, min_area=0.0008)
if len(np.diff(peaks_new_tot)):
y_diff_mean = np.mean(np.diff(peaks_new_tot)) # self.find_contours_mean_y_diff(textline_con_fil)
sigma_gaus = int(y_diff_mean * (7.0 / 40.0))
else:
sigma_gaus = 12
if sigma_gaus < 3:
sigma_gaus = 3
except:
sigma_gaus = 12
if sigma_gaus < 3:
sigma_gaus = 3
y_padded_smoothed = gaussian_filter1d(y_padded, sigma_gaus)
y_padded_up_to_down = -y_padded + np.max(y_padded)
y_padded_up_to_down_padded = np.zeros(len(y_padded_up_to_down) + 40)
y_padded_up_to_down_padded[20 : len(y_padded_up_to_down) + 20] = y_padded_up_to_down
y_padded_up_to_down_padded = gaussian_filter1d(y_padded_up_to_down_padded, sigma_gaus)
y_padded_neg = np.pad(np.max(y_padded) - y_padded, (20,))
y_padded_neg_smoothed = gaussian_filter1d(y_padded_neg, sigma_gaus)
peaks, _ = find_peaks(y_padded_smoothed, height=0)
peaks_neg, _ = find_peaks(y_padded_up_to_down_padded, height=0)
peaks_neg, _ = find_peaks(y_padded_neg_smoothed, height=0)
peaks_new = peaks[:]
peaks_neg_new = peaks_neg[:]
try:
neg_peaks_max = np.max(y_padded_smoothed[peaks])
arg_neg_must_be_deleted = np.arange(len(peaks_neg))[
y_padded_up_to_down_padded[peaks_neg] / float(neg_peaks_max) < 0.24]
y_padded_neg_smoothed[peaks_neg] <
y_padded_smoothed[peaks].max() * 0.24]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
arg_diff = np.arange(len(diff_arg_neg_must_be_deleted))
arg_diff_cluster = arg_diff[diff_arg_neg_must_be_deleted > 1]
clusters_to_be_deleted = []
@ -1103,12 +1072,12 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
peaks_new_tot.append(i1)
peaks_new_tot = np.sort(peaks_new_tot)
# plt.plot(y_padded_up_to_down_padded)
# plt.plot(peaks_neg,y_padded_up_to_down_padded[peaks_neg],'*')
# plt.plot(y_padded_neg_smoothed)
# plt.plot(peaks_neg,y_padded_neg_smoothed[peaks_neg],'*')
# plt.show()
# plt.plot(y_padded_up_to_down_padded)
# plt.plot(peaks_neg_new,y_padded_up_to_down_padded[peaks_neg_new],'*')
# plt.plot(y_padded_neg_smoothed)
# plt.plot(peaks_neg_new,y_padded_neg_smoothed[peaks_neg_new],'*')
# plt.show()
# plt.plot(y_padded_smoothed)
@ -1128,62 +1097,48 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
peaks = peaks_new_tot[:]
peaks_neg = peaks_neg_new[:]
if len(y_padded_smoothed[peaks]) > 1:
mean_value_of_peaks = np.mean(y_padded_smoothed[peaks])
std_value_of_peaks = np.std(y_padded_smoothed[peaks])
else:
mean_value_of_peaks = np.nan
std_value_of_peaks = np.nan
# if len(y_padded_smoothed[peaks]) > 1:
# mean_value_of_peaks = np.mean(y_padded_smoothed[peaks])
# std_value_of_peaks = np.std(y_padded_smoothed[peaks])
# else:
# mean_value_of_peaks = np.nan
# std_value_of_peaks = np.nan
peaks_values = y_padded_smoothed[peaks]
# peaks_values = y_padded_smoothed[peaks]
###peaks_neg = peaks_neg - 20 - 20
###peaks = peaks - 20
peaks_neg_true = peaks_neg[:]
peaks_pos_true = peaks[:]
def clip(positions):
# prevent wrap around array bounds
return np.maximum(0, np.minimum(img_patch.shape[0] - 1, positions))
if len(peaks_neg_true) > 0:
peaks_neg_true = np.array(peaks_neg_true)
peaks_neg_true = peaks_neg_true - 20 - 20
peaks_neg_true = clip(np.array(peaks_neg) - 40)
peaks_pos_true = clip(np.array(peaks) - 20)
for i in range(len(peaks_neg_true)):
img_patch[peaks_neg_true[i] - 6 : peaks_neg_true[i] + 6, :] = 0
else:
pass
# ax1 = plt.subplot(1, 2, 1, title="textline mask slice")
# plt.imshow(img_patch, aspect="auto")
# ax2 = plt.subplot(1, 2, 2, title="projection profile", sharey=ax1)
# plt.plot(y, x)
# ax2.scatter(y[peaks_neg_true], peaks_neg_true, color='r', label="neg (0)")
# ax2.scatter(y[peaks_pos_true], peaks_pos_true, color='g', label="pos (1)")
# plt.legend()
# plt.show()
if len(peaks_pos_true) > 0:
peaks_pos_true = np.array(peaks_pos_true)
peaks_pos_true = peaks_pos_true - 20
offsets = np.arange(-6, 6)
def add_offsets(positions):
# let y range around peak positions (without slice indexing)
return (positions[np.newaxis] + offsets[:, np.newaxis]).flatten()
if peaks_neg_true.size:
img_patch[clip(add_offsets(peaks_neg_true))] = 0
if peaks_pos_true.size:
img_patch[clip(add_offsets(peaks_pos_true))] = 1
for i in range(len(peaks_pos_true)):
##img_patch[peaks_pos_true[i]-8:peaks_pos_true[i]+8,:]=1
img_patch[peaks_pos_true[i] - 6 : peaks_pos_true[i] + 6, :] = 1
else:
pass
kernel = np.ones((5, 5), np.uint8)
# img_patch = cv2.erode(img_patch,kernel,iterations = 3)
#######################img_patch = cv2.erode(img_patch,kernel,iterations = 2)
img_patch = cv2.erode(img_patch, kernel, iterations=1)
return img_patch
def separate_lines_new_inside_tiles(img_path, thetha):
(h, w) = img_path.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, -thetha, 1.0)
x_d = M[0, 2]
y_d = M[1, 2]
thetha = thetha / 180.0 * np.pi
rotation_matrix = np.array([[np.cos(thetha), -np.sin(thetha)], [np.sin(thetha), np.cos(thetha)]])
x_min_cont = 0
x_max_cont = img_path.shape[1]
y_min_cont = 0
y_max_cont = img_path.shape[0]
xv = np.linspace(x_min_cont, x_max_cont, 1000)
def separate_lines_new_inside_tiles(img_path, _):
mada_n = img_path.sum(axis=1)
##plt.plot(mada_n)
@ -1371,26 +1326,18 @@ def textline_contours_postprocessing(textline_mask, angle, contour_parent):
if len(contour) > 3]
return contours_rotated_clean
def separate_lines_new2(img_crop, thetha, num_col, slope_region, logger=None, plotter=None):
def separate_lines_new2(img_crop, _, num_col, slope_region, logger=None, plotter=None):
"""
morph textline mask to cope with warped lines by independently deskewing horizontal slices
"""
if logger is None:
logger = getLogger(__package__)
if not np.prod(img_crop.shape):
return img_crop
if num_col == 1:
num_patches = int(img_crop.shape[1] / 200.0)
else:
num_patches = int(img_crop.shape[1] / 140.0)
# num_patches=int(img_crop.shape[1]/200.)
if num_patches == 0:
num_patches = 1
img_patch_interest = img_crop[:, :] # [peaks_neg_true[14]-dis_up:peaks_neg_true[15]+dis_down ,:]
# plt.imshow(img_patch_interest)
# plt.show()
length_x = int(img_crop.shape[1] / float(num_patches))
height, width = img_crop.shape
num_patches = max(1, width // (200 if num_col == 1 else 140))
length_x = width // num_patches
# margin = int(0.04 * length_x) just recently this was changed because it break lines into 2
margin = int(0.04 * length_x)
# if margin<=4:
@ -1398,85 +1345,68 @@ def separate_lines_new2(img_crop, thetha, num_col, slope_region, logger=None, pl
# margin=0
width_mid = length_x - 2 * margin
nxf = img_crop.shape[1] / float(width_mid)
if nxf > int(nxf):
nxf = int(nxf) + 1
else:
nxf = int(nxf)
img_crop_revised = np.zeros_like(img_crop)
for index_x_d in range(0, width, width_mid):
index_x_u = index_x_d + length_x
if index_x_u > width:
if index_x_u >= width + width_mid:
break # already in last window
index_x_u = width
index_x_d = width - length_x
slopes_tile_wise = []
for i in range(nxf):
if i == 0:
index_x_d = i * width_mid
index_x_u = index_x_d + length_x
elif i > 0:
index_x_d = i * width_mid
index_x_u = index_x_d + length_x
# box = (slice(index_y_d, index_y_u), slice(index_x_d, index_x_u))
# img_patch = img_crop[box]
box = (slice(None), slice(index_x_d, index_x_u))
img_xline = img_crop[box]
if index_x_u > img_crop.shape[1]:
index_x_u = img_crop.shape[1]
index_x_d = img_crop.shape[1] - length_x
# img_patch = img[index_y_d:index_y_u, index_x_d:index_x_u, :]
img_xline = img_patch_interest[:, index_x_d:index_x_u]
try:
assert img_xline.any()
if img_xline.any():
slope_xline = return_deskew_slop(img_xline, 2, logger=logger, plotter=plotter)
except:
slope_xline = 0
else:
continue
if abs(slope_region) < 25 and abs(slope_xline) > 25:
slope_xline = [slope_region][0]
if (abs(slope_region) < 25 and
abs(slope_xline) > 25):
slope_xline = slope_region
# if abs(slope_region)>70 and abs(slope_xline)<25:
# slope_xline=[slope_region][0]
slopes_tile_wise.append(slope_xline)
img_line_rotated = rotate_image(img_xline, slope_xline)
img_line_rotated[:, :][img_line_rotated[:, :] != 0] = 1
img_patch_interest = img_crop[:, :] # [peaks_neg_true[14]-dis_up:peaks_neg_true[14]+dis_down ,:]
# slope_xline = slope_region
img_patch_interest_revised = np.zeros(img_patch_interest.shape)
for i in range(nxf):
if i == 0:
index_x_d = i * width_mid
index_x_u = index_x_d + length_x
elif i > 0:
index_x_d = i * width_mid
index_x_u = index_x_d + length_x
if index_x_u > img_crop.shape[1]:
index_x_u = img_crop.shape[1]
index_x_d = img_crop.shape[1] - length_x
img_xline = img_patch_interest[:, index_x_d:index_x_u]
img_int = np.zeros((img_xline.shape[0], img_xline.shape[1]))
img_int[:, :] = img_xline[:, :] # img_patch_org[:,:,0]
img_resized = np.zeros((int(img_int.shape[0] * (1.2)), int(img_int.shape[1] * (3))))
img_resized[int(img_int.shape[0] * (0.1)) : int(img_int.shape[0] * (0.1)) + img_int.shape[0],
int(img_int.shape[1] * (1.0)) : int(img_int.shape[1] * (1.0)) + img_int.shape[1]] = img_int[:, :]
# plt.imshow(img_xline)
pad_above = pad_below = int(img_xline.shape[0] * 0.1)
pad_left = pad_right = img_xline.shape[1]
img_xline_padded = np.pad(img_xline, ((pad_above, pad_below),
(pad_left, pad_right)))
# plt.subplot(2, 2, 1, title="xline padded")
# plt.imshow(img_xline_padded)
img_xline_rotated = rotate_image(img_xline_padded, slope_xline)
#img_xline_rotated[img_xline_rotated != 0] = 1
# plt.subplot(2, 2, 2, title="xline rotated")
# plt.imshow(img_xline_rotated)
img_xline_separated = separate_lines_new_inside_tiles2(img_xline_rotated, 0)
# plt.subplot(2, 2, 3, title="xline separated")
# plt.imshow(img_xline_separated)
img_xline_separated = rotate_image(img_xline_separated, -slope_xline)
#img_xline_separated[img_xline_separated != 0] = 1
# plt.subplot(2, 2, 4, title="xline unrotated")
# plt.imshow(img_xline_separated)
# plt.show()
img_line_rotated = rotate_image(img_resized, slopes_tile_wise[i])
img_line_rotated[:, :][img_line_rotated[:, :] != 0] = 1
img_patch_separated = separate_lines_new_inside_tiles2(img_line_rotated, 0)
# unpad
img_xline_separated = img_xline_separated[
pad_above: -pad_below,
pad_left: -pad_right]
img_patch_separated_returned = rotate_image(img_patch_separated, -slopes_tile_wise[i])
img_patch_separated_returned[:, :][img_patch_separated_returned[:, :] != 0] = 1
# window
window = (slice(None), slice(margin, -margin or None))
img_crop_revised[box][window] = img_xline_separated[window]
# plt.subplot(1, 2, 1, title="original box")
# plt.imshow(img_crop[box])
# plt.gca().add_patch(patches.Rectangle((margin, 0), length_x - 2 * margin, height, alpha=0.5, color='gray'))
# plt.subplot(1, 2, 2, title="revised box")
# plt.imshow(img_crop_revised[box])
# plt.gca().add_patch(patches.Rectangle((margin, 0), length_x - 2 * margin, height, alpha=0.5, color='gray'))
# plt.show()
img_patch_separated_returned_true_size = img_patch_separated_returned[
int(img_int.shape[0] * (0.1)) : int(img_int.shape[0] * (0.1)) + img_int.shape[0],
int(img_int.shape[1] * (1.0)) : int(img_int.shape[1] * (1.0)) + img_int.shape[1]]
img_patch_separated_returned_true_size = img_patch_separated_returned_true_size[:, margin : length_x - margin]
img_patch_interest_revised[:, index_x_d + margin : index_x_u - margin] = img_patch_separated_returned_true_size
return img_patch_interest_revised
return img_crop_revised
def do_image_rotation(angle, img=None, sigma_des=1.0, logger=None):
if logger is None:
@ -1580,19 +1510,20 @@ def do_work_of_slopes_new_curved(
if not np.any(all_text_region_raw):
return [], slope_deskew
img_int_p = np.copy(all_text_region_raw)
# correct for relative area
rel_area = 1.0 * textline_mask_tot_ea.size / img_int_p.size
# img_int_p=cv2.erode(img_int_p,KERNEL,iterations = 2)
# plt.imshow(img_int_p)
# plt.show()
if not np.prod(img_int_p.shape) or img_int_p.shape[0] / img_int_p.shape[1] < 0.1:
slope = slope_deskew
else:
slope = slope_deskew
if h >= 0.1 * w:
try:
textline_con, hierarchy = return_contours_of_image(img_int_p)
textline_con_fil = filter_contours_area_of_image(img_int_p, textline_con,
hierarchy,
max_area=1, min_area=0.0008)
min_area=0.0008 * rel_area)
if len(textline_con_fil) > 1:
cx, cy = find_center_of_contours(textline_con_fil)
y_diff_mean = np.median(np.diff(np.sort(np.array(cy))))
@ -1613,7 +1544,7 @@ def do_work_of_slopes_new_curved(
slope = -90 - slope if slope < 0 else 90 - slope
if abs(slope - slope_deskew) < 0.5:
slope = slope_deskew
else:
elif len(textline_con_fil):
if h > 3 * w:
# print(1, "transposed", h, w)
transposed = True
@ -1636,24 +1567,32 @@ def do_work_of_slopes_new_curved(
# print(slope, slope_deskew)
if abs(slope) < 45:
mask_parent = np.zeros((h, w), dtype=np.uint8)
mask_parent = cv2.fillPoly(mask_parent, pts=[contour_par - [x, y]], color=1)
mask_parent_textline = mask_parent * textline_mask_tot_ea[y : y + h, x : x + w]
mask_textlines_separated_d = separate_lines_new2(mask_parent_textline, 0,
# apply horizontal tiling, deskew each patch independently
mask_textlines_separated_d = separate_lines_new2(all_text_region_raw, 0,
num_col, slope,
logger=logger, plotter=plotter)
#mask_textlines_separated_d[mask_parent != 1] = 0
# plt.subplot(1, 2, 1, title="textline mask of region")
# plt.imshow(all_text_region_raw)
# plt.subplot(1, 2, 2, title="separated+deskewed")
# plt.imshow(mask_textlines_separated_d)
# plt.show()
textline_contours = return_contours_of_interested_textline(mask_textlines_separated_d, 1)
textline_contours = return_contours_of_interested_textline(
mask_textlines_separated_d, 1, min_area=3e-9 * rel_area)
textlines_cnt_per_region = []
for contour in textline_contours:
mask_line = np.zeros_like(mask_parent)
mask_line = cv2.fillPoly(mask_line, pts=[contour], color=1)
mask_line = cv2.dilate(mask_line, KERNEL, iterations=5 if num_col == 0 else 4)
# plt.subplot(1, 2, 1, title="parent mask")
# plt.imshow(mask_parent)
# plt.subplot(1, 2, 2, title="single textline")
# plt.imshow(mask_line)
# plt.show()
textline_contours2 = return_contours_of_interested_textline(mask_line, 1)
textline_contours2 = return_contours_of_interested_textline(
mask_line, 1, min_area=3e-9 * rel_area)
textline_areas2 = np.array(list(map(cv2.contourArea, textline_contours2)))
try:
contour2 = textline_contours2[np.argmax(textline_areas2)]