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

separate_lines_new2: fix coord overflow by clipping, simplify…

Browse source 
- found positive and negative peaks, and even more so their
  relative offsets, may overflow in the cropped image,
  causing fake textlines; avoid that by clipping to the valid
  y coordinates
- calculation for number of tiles: sometimes one less
  tile is needed by making the previous last tile
  half-full on the right side
- add some (commented) plotting
- simplify (a lot, but only partially)
This commit is contained in:
Robert Sachunsky 2026-05-11 03:09:02 +02:00
parent 130f0aee42
commit e183937c5d
1 changed files with 160 additions and 230 deletions
Download patch file Download diff file Expand all files Collapse all files

390
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) x_cont = x_cont - np.min(x_cont)
y_cont = y_cont - np.min(y_cont) y_cont = y_cont - np.min(y_cont)
x_min_cont = 0 y_min_cont, x_min_cont = 0, 0
x_max_cont = img_patch.shape[1] y_max_cont, x_max_cont = img_patch.shape
y_min_cont = 0
y_max_cont = img_patch.shape[0]
xv = np.linspace(x_min_cont, x_max_cont, 1000) xv = np.linspace(x_min_cont, x_max_cont, 1000)
textline_patch_sum_along_width = img_patch.sum(axis=axis) 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)]]])) [[int(x_min), int(point_down)]]]))
return peaks, textline_boxes_rot return peaks, textline_boxes_rot
def separate_lines_new_inside_tiles2(img_patch, thetha): def separate_lines_new_inside_tiles2(img_patch, _):
(h, w) = img_patch.shape[:2] y = img_patch.sum(axis=1)
center = (w // 2, h // 2) y_padded = np.pad(y, (20,))
M = cv2.getRotationMatrix2D(center, -thetha, 1.0) x = np.arange(len(y))
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)))
peaks_real, _ = find_peaks(gaussian_filter1d(y, 3), height=0) peaks_real, _ = find_peaks(gaussian_filter1d(y, 3), height=0)
if 1 > 0: try:
try: y_padded_smoothed_e = gaussian_filter1d(y_padded, 2)
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_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 = 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[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)
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_e, _ = find_peaks(y_padded_smoothed_e, height=0)
peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_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]) 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))[ 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] 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) 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.array(range(len(diff_arg_neg_must_be_deleted)))
arg_diff_cluster = arg_diff[diff_arg_neg_must_be_deleted > 1] arg_diff_cluster = arg_diff[diff_arg_neg_must_be_deleted > 1]
peaks_new = peaks_e[:] peaks_new = peaks_e[:]
peaks_neg_new = peaks_neg_e[:] peaks_neg_new = peaks_neg_e[:]
clusters_to_be_deleted = [] clusters_to_be_deleted = []
if len(arg_diff_cluster) > 0: if len(arg_diff_cluster) > 0:
clusters_to_be_deleted.append(arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1]) 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): 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.append( clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :]) arg_neg_must_be_deleted[arg_diff_cluster[i] + 1:
if len(clusters_to_be_deleted) > 0: arg_diff_cluster[i + 1] + 1])
peaks_new_extra = [] clusters_to_be_deleted.append(
for m in range(len(clusters_to_be_deleted)): arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :])
min_cluster = np.min(peaks_e[clusters_to_be_deleted[m]]) if len(clusters_to_be_deleted) > 0:
max_cluster = np.max(peaks_e[clusters_to_be_deleted[m]]) peaks_new_extra = []
peaks_new_extra.append(int((min_cluster + max_cluster) / 2.0)) for m in range(len(clusters_to_be_deleted)):
for m1 in range(len(clusters_to_be_deleted[m])): min_cluster = np.min(peaks_e[clusters_to_be_deleted[m]])
peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1] - 1]] max_cluster = np.max(peaks_e[clusters_to_be_deleted[m]])
peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1]]] peaks_new_extra.append(int((min_cluster + max_cluster) / 2.0))
peaks_neg_new = peaks_neg_new[peaks_neg_new != peaks_neg_e[clusters_to_be_deleted[m][m1]]] for m1 in range(len(clusters_to_be_deleted[m])):
peaks_new_tot = [] peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1] - 1]]
for i1 in peaks_new: peaks_new = peaks_new[peaks_new != peaks_e[clusters_to_be_deleted[m][m1]]]
peaks_new_tot.append(i1) peaks_neg_new = peaks_neg_new[peaks_neg_new != peaks_neg_e[clusters_to_be_deleted[m][m1]]]
for i1 in peaks_new_extra: peaks_new_tot = []
peaks_new_tot.append(i1) for i1 in peaks_new:
peaks_new_tot = np.sort(peaks_new_tot) peaks_new_tot.append(i1)
else: for i1 in peaks_new_extra:
peaks_new_tot = peaks_e[:] 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, hierarchy = return_contours_of_image(img_patch)
textline_con_fil = filter_contours_area_of_image(img_patch, textline_con_fil = filter_contours_area_of_image(img_patch,
textline_con, hierarchy, textline_con, hierarchy,
max_area=1, min_area=0.0008) max_area=1, min_area=0.0008)
if len(np.diff(peaks_new_tot)): 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) 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)) sigma_gaus = int(y_diff_mean * (7.0 / 40.0))
else: else:
sigma_gaus = 12
except:
sigma_gaus = 12 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_smoothed = gaussian_filter1d(y_padded, sigma_gaus)
y_padded_up_to_down = -y_padded + np.max(y_padded) y_padded_neg = np.pad(np.max(y_padded) - y_padded, (20,))
y_padded_up_to_down_padded = np.zeros(len(y_padded_up_to_down) + 40) y_padded_neg_smoothed = gaussian_filter1d(y_padded_neg, sigma_gaus)
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)
peaks, _ = find_peaks(y_padded_smoothed, height=0) 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_new = peaks[:]
peaks_neg_new = peaks_neg[:] peaks_neg_new = peaks_neg[:]
try: try:
neg_peaks_max = np.max(y_padded_smoothed[peaks])
arg_neg_must_be_deleted = np.arange(len(peaks_neg))[ 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) 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] arg_diff_cluster = arg_diff[diff_arg_neg_must_be_deleted > 1]
clusters_to_be_deleted = [] 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.append(i1)
peaks_new_tot = np.sort(peaks_new_tot) peaks_new_tot = np.sort(peaks_new_tot)
# plt.plot(y_padded_up_to_down_padded) # plt.plot(y_padded_neg_smoothed)
# plt.plot(peaks_neg,y_padded_up_to_down_padded[peaks_neg],'*') # plt.plot(peaks_neg,y_padded_neg_smoothed[peaks_neg],'*')
# plt.show() # plt.show()
# plt.plot(y_padded_up_to_down_padded) # plt.plot(y_padded_neg_smoothed)
# plt.plot(peaks_neg_new,y_padded_up_to_down_padded[peaks_neg_new],'*') # plt.plot(peaks_neg_new,y_padded_neg_smoothed[peaks_neg_new],'*')
# plt.show() # plt.show()
# plt.plot(y_padded_smoothed) # plt.plot(y_padded_smoothed)
@ -1128,62 +1097,48 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
peaks = peaks_new_tot[:] peaks = peaks_new_tot[:]
peaks_neg = peaks_neg_new[:] peaks_neg = peaks_neg_new[:]
if len(y_padded_smoothed[peaks]) > 1: # if len(y_padded_smoothed[peaks]) > 1:
mean_value_of_peaks = np.mean(y_padded_smoothed[peaks]) # mean_value_of_peaks = np.mean(y_padded_smoothed[peaks])
std_value_of_peaks = np.std(y_padded_smoothed[peaks]) # std_value_of_peaks = np.std(y_padded_smoothed[peaks])
else: # else:
mean_value_of_peaks = np.nan # mean_value_of_peaks = np.nan
std_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 def clip(positions):
###peaks = peaks - 20 # prevent wrap around array bounds
peaks_neg_true = peaks_neg[:] return np.maximum(0, np.minimum(img_patch.shape[0] - 1, positions))
peaks_pos_true = peaks[:]
if len(peaks_neg_true) > 0: peaks_neg_true = clip(np.array(peaks_neg) - 40)
peaks_neg_true = np.array(peaks_neg_true) peaks_pos_true = clip(np.array(peaks) - 20)
peaks_neg_true = peaks_neg_true - 20 - 20
for i in range(len(peaks_neg_true)): # ax1 = plt.subplot(1, 2, 1, title="textline mask slice")
img_patch[peaks_neg_true[i] - 6 : peaks_neg_true[i] + 6, :] = 0 # plt.imshow(img_patch, aspect="auto")
else: # ax2 = plt.subplot(1, 2, 2, title="projection profile", sharey=ax1)
pass # 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: offsets = np.arange(-6, 6)
peaks_pos_true = np.array(peaks_pos_true) def add_offsets(positions):
peaks_pos_true = peaks_pos_true - 20 # 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) kernel = np.ones((5, 5), np.uint8)
# img_patch = cv2.erode(img_patch,kernel,iterations = 3) # 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) img_patch = cv2.erode(img_patch, kernel, iterations=1)
return img_patch return img_patch
def separate_lines_new_inside_tiles(img_path, thetha): def separate_lines_new_inside_tiles(img_path, _):
(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)
mada_n = img_path.sum(axis=1) mada_n = img_path.sum(axis=1)
##plt.plot(mada_n) ##plt.plot(mada_n)
@ -1371,26 +1326,18 @@ def textline_contours_postprocessing(textline_mask, angle, contour_parent):
if len(contour) > 3] if len(contour) > 3]
return contours_rotated_clean 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: if logger is None:
logger = getLogger(__package__) logger = getLogger(__package__)
if not np.prod(img_crop.shape): if not np.prod(img_crop.shape):
return img_crop return img_crop
if num_col == 1: height, width = img_crop.shape
num_patches = int(img_crop.shape[1] / 200.0) num_patches = max(1, width // (200 if num_col == 1 else 140))
else: length_x = width // num_patches
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))
# margin = int(0.04 * length_x) just recently this was changed because it break lines into 2 # margin = int(0.04 * length_x) just recently this was changed because it break lines into 2
margin = int(0.04 * length_x) margin = int(0.04 * length_x)
# if margin<=4: # if margin<=4:
@ -1398,85 +1345,68 @@ def separate_lines_new2(img_crop, thetha, num_col, slope_region, logger=None, pl
# margin=0 # margin=0
width_mid = length_x - 2 * margin width_mid = length_x - 2 * margin
nxf = img_crop.shape[1] / float(width_mid)
if nxf > int(nxf): img_crop_revised = np.zeros_like(img_crop)
nxf = int(nxf) + 1 for index_x_d in range(0, width, width_mid):
else: index_x_u = index_x_d + length_x
nxf = int(nxf) 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 = [] # box = (slice(index_y_d, index_y_u), slice(index_x_d, index_x_u))
for i in range(nxf): # img_patch = img_crop[box]
if i == 0: box = (slice(None), slice(index_x_d, index_x_u))
index_x_d = i * width_mid img_xline = img_crop[box]
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]: if img_xline.any():
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()
slope_xline = return_deskew_slop(img_xline, 2, logger=logger, plotter=plotter) slope_xline = return_deskew_slop(img_xline, 2, logger=logger, plotter=plotter)
except: else:
slope_xline = 0 continue
if abs(slope_region) < 25 and abs(slope_xline) > 25: if (abs(slope_region) < 25 and
slope_xline = [slope_region][0] abs(slope_xline) > 25):
slope_xline = slope_region
# if abs(slope_region)>70 and abs(slope_xline)<25: # if abs(slope_region)>70 and abs(slope_xline)<25:
# slope_xline=[slope_region][0] # slope_xline = slope_region
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 ,:] pad_above = pad_below = int(img_xline.shape[0] * 0.1)
pad_left = pad_right = img_xline.shape[1]
img_patch_interest_revised = np.zeros(img_patch_interest.shape) img_xline_padded = np.pad(img_xline, ((pad_above, pad_below),
(pad_left, pad_right)))
for i in range(nxf): # plt.subplot(2, 2, 1, title="xline padded")
if i == 0: # plt.imshow(img_xline_padded)
index_x_d = i * width_mid img_xline_rotated = rotate_image(img_xline_padded, slope_xline)
index_x_u = index_x_d + length_x #img_xline_rotated[img_xline_rotated != 0] = 1
elif i > 0: # plt.subplot(2, 2, 2, title="xline rotated")
index_x_d = i * width_mid # plt.imshow(img_xline_rotated)
index_x_u = index_x_d + length_x img_xline_separated = separate_lines_new_inside_tiles2(img_xline_rotated, 0)
# plt.subplot(2, 2, 3, title="xline separated")
if index_x_u > img_crop.shape[1]: # plt.imshow(img_xline_separated)
index_x_u = img_crop.shape[1] img_xline_separated = rotate_image(img_xline_separated, -slope_xline)
index_x_d = img_crop.shape[1] - length_x #img_xline_separated[img_xline_separated != 0] = 1
# plt.subplot(2, 2, 4, title="xline unrotated")
img_xline = img_patch_interest[:, index_x_d:index_x_u] # plt.imshow(img_xline_separated)
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)
# plt.show() # 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]) # window
img_patch_separated_returned[:, :][img_patch_separated_returned[:, :] != 0] = 1 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[ return img_crop_revised
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
def do_image_rotation(angle, img=None, sigma_des=1.0, logger=None): def do_image_rotation(angle, img=None, sigma_des=1.0, logger=None):
if logger is None: if logger is None: