mirror of
https://github.com/qurator-spk/eynollah.git
synced 2025-11-04 03:34:16 +01:00
remove dead code (found with vulture)
This commit is contained in:
kba
parent
9ee9c4403b
commit
a5b178e1d1
4 changed files with 0 additions and 797 deletions
|
|
@ -1447,40 +1447,6 @@ class Eynollah():
|
|||
return prediction_textline[:, :, 0], prediction_textline_longshot_true_size[:, :, 0]
|
||||
|
||||
|
||||
def do_work_of_slopes(self, q, poly, box_sub, boxes_per_process, textline_mask_tot, contours_per_process):
|
||||
self.logger.debug('enter do_work_of_slopes')
|
||||
slope_biggest = 0
|
||||
slopes_sub = []
|
||||
boxes_sub_new = []
|
||||
poly_sub = []
|
||||
for mv in range(len(boxes_per_process)):
|
||||
crop_img, _ = crop_image_inside_box(boxes_per_process[mv], np.repeat(textline_mask_tot[:, :, np.newaxis], 3, axis=2))
|
||||
crop_img = crop_img[:, :, 0]
|
||||
crop_img = cv2.erode(crop_img, KERNEL, iterations=2)
|
||||
try:
|
||||
textline_con, hierarchy = return_contours_of_image(crop_img)
|
||||
textline_con_fil = filter_contours_area_of_image(crop_img, textline_con, hierarchy, max_area=1, min_area=0.0008)
|
||||
y_diff_mean = find_contours_mean_y_diff(textline_con_fil)
|
||||
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
|
||||
crop_img[crop_img > 0] = 1
|
||||
slope_corresponding_textregion = return_deskew_slop(crop_img, sigma_des, plotter=self.plotter)
|
||||
except Exception as why:
|
||||
self.logger.error(why)
|
||||
slope_corresponding_textregion = MAX_SLOPE
|
||||
|
||||
if slope_corresponding_textregion == MAX_SLOPE:
|
||||
slope_corresponding_textregion = slope_biggest
|
||||
slopes_sub.append(slope_corresponding_textregion)
|
||||
|
||||
cnt_clean_rot = textline_contours_postprocessing(crop_img, slope_corresponding_textregion, contours_per_process[mv], boxes_per_process[mv])
|
||||
|
||||
poly_sub.append(cnt_clean_rot)
|
||||
boxes_sub_new.append(boxes_per_process[mv])
|
||||
|
||||
q.put(slopes_sub)
|
||||
poly.put(poly_sub)
|
||||
box_sub.put(boxes_sub_new)
|
||||
|
||||
def get_regions_light_v(self,img,is_image_enhanced, num_col_classifier):
|
||||
self.logger.debug("enter get_regions_light_v")
|
||||
erosion_hurts = False
|
||||
|
|
|
|||
|
|
@ -531,192 +531,6 @@ def find_num_col(regions_without_separators, num_col_classifier, tables, multipl
|
|||
##print(len(peaks_neg_true))
|
||||
return len(peaks_neg_true), peaks_neg_true
|
||||
|
||||
def find_num_col_only_image(regions_without_separators, multiplier=3.8):
|
||||
regions_without_separators_0 = regions_without_separators[:, :].sum(axis=0)
|
||||
|
||||
##plt.plot(regions_without_separators_0)
|
||||
##plt.show()
|
||||
|
||||
sigma_ = 15
|
||||
|
||||
meda_n_updown = regions_without_separators_0[len(regions_without_separators_0) :: -1]
|
||||
|
||||
first_nonzero = next((i for i, x in enumerate(regions_without_separators_0) if x), 0)
|
||||
last_nonzero = next((i for i, x in enumerate(meda_n_updown) if x), 0)
|
||||
|
||||
last_nonzero = len(regions_without_separators_0) - last_nonzero
|
||||
|
||||
y = regions_without_separators_0 # [first_nonzero:last_nonzero]
|
||||
|
||||
y_help = np.zeros(len(y) + 20)
|
||||
|
||||
y_help[10 : len(y) + 10] = y
|
||||
|
||||
x = np.array(range(len(y)))
|
||||
|
||||
zneg_rev = -y_help + np.max(y_help)
|
||||
|
||||
zneg = np.zeros(len(zneg_rev) + 20)
|
||||
|
||||
zneg[10 : len(zneg_rev) + 10] = zneg_rev
|
||||
|
||||
z = gaussian_filter1d(y, sigma_)
|
||||
zneg = gaussian_filter1d(zneg, sigma_)
|
||||
|
||||
peaks_neg, _ = find_peaks(zneg, height=0)
|
||||
peaks, _ = find_peaks(z, height=0)
|
||||
|
||||
peaks_neg = peaks_neg - 10 - 10
|
||||
|
||||
peaks_neg_org = np.copy(peaks_neg)
|
||||
|
||||
peaks_neg = peaks_neg[(peaks_neg > first_nonzero) & (peaks_neg < last_nonzero)]
|
||||
|
||||
peaks = peaks[(peaks > 0.09 * regions_without_separators.shape[1]) & (peaks < 0.91 * regions_without_separators.shape[1])]
|
||||
|
||||
peaks_neg = peaks_neg[(peaks_neg > 500) & (peaks_neg < (regions_without_separators.shape[1] - 500))]
|
||||
# print(peaks)
|
||||
interest_pos = z[peaks]
|
||||
|
||||
interest_pos = interest_pos[interest_pos > 10]
|
||||
|
||||
interest_neg = z[peaks_neg]
|
||||
min_peaks_pos = np.mean(interest_pos) # np.min(interest_pos)
|
||||
min_peaks_neg = 0 # np.min(interest_neg)
|
||||
|
||||
# $print(min_peaks_pos)
|
||||
dis_talaei = (min_peaks_pos - min_peaks_neg) / multiplier
|
||||
# print(interest_pos)
|
||||
grenze = min_peaks_pos - dis_talaei # np.mean(y[peaks_neg[0]:peaks_neg[len(peaks_neg)-1]])-np.std(y[peaks_neg[0]:peaks_neg[len(peaks_neg)-1]])/2.0
|
||||
|
||||
interest_neg_fin = interest_neg[(interest_neg < grenze)]
|
||||
peaks_neg_fin = peaks_neg[(interest_neg < grenze)]
|
||||
|
||||
num_col = (len(interest_neg_fin)) + 1
|
||||
|
||||
p_l = 0
|
||||
p_u = len(y) - 1
|
||||
p_m = int(len(y) / 2.0)
|
||||
p_g_l = int(len(y) / 3.0)
|
||||
p_g_u = len(y) - int(len(y) / 3.0)
|
||||
|
||||
if num_col == 3:
|
||||
if (peaks_neg_fin[0] > p_g_u and peaks_neg_fin[1] > p_g_u) or (peaks_neg_fin[0] < p_g_l and peaks_neg_fin[1] < p_g_l) or (peaks_neg_fin[0] < p_m and peaks_neg_fin[1] < p_m) or (peaks_neg_fin[0] > p_m and peaks_neg_fin[1] > p_m):
|
||||
num_col = 1
|
||||
else:
|
||||
pass
|
||||
|
||||
if num_col == 2:
|
||||
if (peaks_neg_fin[0] > p_g_u) or (peaks_neg_fin[0] < p_g_l):
|
||||
num_col = 1
|
||||
else:
|
||||
pass
|
||||
|
||||
diff_peaks = np.abs(np.diff(peaks_neg_fin))
|
||||
|
||||
cut_off = 400
|
||||
peaks_neg_true = []
|
||||
forest = []
|
||||
|
||||
for i in range(len(peaks_neg_fin)):
|
||||
if i == 0:
|
||||
forest.append(peaks_neg_fin[i])
|
||||
if i < (len(peaks_neg_fin) - 1):
|
||||
if diff_peaks[i] <= cut_off:
|
||||
forest.append(peaks_neg_fin[i + 1])
|
||||
if diff_peaks[i] > cut_off:
|
||||
# print(forest[np.argmin(z[forest]) ] )
|
||||
if not isNaN(forest[np.argmin(z[forest])]):
|
||||
peaks_neg_true.append(forest[np.argmin(z[forest])])
|
||||
forest = []
|
||||
forest.append(peaks_neg_fin[i + 1])
|
||||
if i == (len(peaks_neg_fin) - 1):
|
||||
# print(print(forest[np.argmin(z[forest]) ] ))
|
||||
if not isNaN(forest[np.argmin(z[forest])]):
|
||||
peaks_neg_true.append(forest[np.argmin(z[forest])])
|
||||
|
||||
num_col = (len(peaks_neg_true)) + 1
|
||||
p_l = 0
|
||||
p_u = len(y) - 1
|
||||
p_m = int(len(y) / 2.0)
|
||||
p_quarter = int(len(y) / 4.0)
|
||||
p_g_l = int(len(y) / 3.0)
|
||||
p_g_u = len(y) - int(len(y) / 3.0)
|
||||
|
||||
p_u_quarter = len(y) - p_quarter
|
||||
|
||||
if num_col == 3:
|
||||
if (peaks_neg_true[0] > p_g_u and peaks_neg_true[1] > p_g_u) or (peaks_neg_true[0] < p_g_l and peaks_neg_true[1] < p_g_l) or (peaks_neg_true[0] < p_m and peaks_neg_true[1] < p_m) or (peaks_neg_true[0] > p_m and peaks_neg_true[1] > p_m):
|
||||
num_col = 1
|
||||
peaks_neg_true = []
|
||||
elif (peaks_neg_true[0] < p_g_u and peaks_neg_true[0] > p_g_l) and (peaks_neg_true[1] > p_u_quarter):
|
||||
peaks_neg_true = [peaks_neg_true[0]]
|
||||
elif (peaks_neg_true[1] < p_g_u and peaks_neg_true[1] > p_g_l) and (peaks_neg_true[0] < p_quarter):
|
||||
peaks_neg_true = [peaks_neg_true[1]]
|
||||
else:
|
||||
pass
|
||||
|
||||
if num_col == 2:
|
||||
if (peaks_neg_true[0] > p_g_u) or (peaks_neg_true[0] < p_g_l):
|
||||
num_col = 1
|
||||
peaks_neg_true = []
|
||||
|
||||
if num_col == 4:
|
||||
if len(np.array(peaks_neg_true)[np.array(peaks_neg_true) < p_g_l]) == 2 or len(np.array(peaks_neg_true)[np.array(peaks_neg_true) > (len(y) - p_g_l)]) == 2:
|
||||
num_col = 1
|
||||
peaks_neg_true = []
|
||||
else:
|
||||
pass
|
||||
|
||||
# no deeper hill around found hills
|
||||
|
||||
peaks_fin_true = []
|
||||
for i in range(len(peaks_neg_true)):
|
||||
hill_main = peaks_neg_true[i]
|
||||
# deep_depth=z[peaks_neg]
|
||||
hills_around = peaks_neg_org[((peaks_neg_org > hill_main) & (peaks_neg_org <= hill_main + 400)) | ((peaks_neg_org < hill_main) & (peaks_neg_org >= hill_main - 400))]
|
||||
deep_depth_around = z[hills_around]
|
||||
|
||||
# print(hill_main,z[hill_main],hills_around,deep_depth_around,'manoooo')
|
||||
try:
|
||||
if np.min(deep_depth_around) < z[hill_main]:
|
||||
pass
|
||||
else:
|
||||
peaks_fin_true.append(hill_main)
|
||||
except:
|
||||
pass
|
||||
|
||||
diff_peaks_annormal = diff_peaks[diff_peaks < 360]
|
||||
|
||||
if len(diff_peaks_annormal) > 0:
|
||||
arg_help = np.array(range(len(diff_peaks)))
|
||||
arg_help_ann = arg_help[diff_peaks < 360]
|
||||
|
||||
peaks_neg_fin_new = []
|
||||
|
||||
for ii in range(len(peaks_neg_fin)):
|
||||
if ii in arg_help_ann:
|
||||
arg_min = np.argmin([interest_neg_fin[ii], interest_neg_fin[ii + 1]])
|
||||
if arg_min == 0:
|
||||
peaks_neg_fin_new.append(peaks_neg_fin[ii])
|
||||
else:
|
||||
peaks_neg_fin_new.append(peaks_neg_fin[ii + 1])
|
||||
|
||||
elif (ii - 1) in arg_help_ann:
|
||||
pass
|
||||
else:
|
||||
peaks_neg_fin_new.append(peaks_neg_fin[ii])
|
||||
else:
|
||||
peaks_neg_fin_new = peaks_neg_fin
|
||||
|
||||
# sometime pages with one columns gives also some negative peaks. delete those peaks
|
||||
param = z[peaks_neg_true] / float(min_peaks_pos) * 100
|
||||
|
||||
if len(param[param <= 41]) == 0:
|
||||
peaks_neg_true = []
|
||||
|
||||
return len(peaks_fin_true), peaks_fin_true
|
||||
|
||||
def find_num_col_by_vertical_lines(regions_without_separators, multiplier=3.8):
|
||||
regions_without_separators_0 = regions_without_separators[:, :, 0].sum(axis=0)
|
||||
|
||||
|
|
|
|||
|
|
@ -171,35 +171,6 @@ def do_work_of_contours_in_image(queue_of_all_params, contours_per_process, inde
|
|||
queue_of_all_params.put([ cnts_org_per_each_subprocess, index_by_text_region_contours])
|
||||
|
||||
|
||||
def get_textregion_contours_in_org_image_multi(cnts, img, slope_first):
|
||||
|
||||
num_cores = cpu_count()
|
||||
queue_of_all_params = Queue()
|
||||
|
||||
processes = []
|
||||
nh = np.linspace(0, len(cnts), num_cores + 1)
|
||||
indexes_by_text_con = np.array(range(len(cnts)))
|
||||
for i in range(num_cores):
|
||||
contours_per_process = cnts[int(nh[i]) : int(nh[i + 1])]
|
||||
indexes_text_con_per_process = indexes_by_text_con[int(nh[i]) : int(nh[i + 1])]
|
||||
|
||||
processes.append(Process(target=do_work_of_contours_in_image, args=(queue_of_all_params, contours_per_process, indexes_text_con_per_process, img,slope_first )))
|
||||
for i in range(num_cores):
|
||||
processes[i].start()
|
||||
cnts_org = []
|
||||
all_index_text_con = []
|
||||
for i in range(num_cores):
|
||||
list_all_par = queue_of_all_params.get(True)
|
||||
contours_for_sub_process = list_all_par[0]
|
||||
indexes_for_sub_process = list_all_par[1]
|
||||
for j in range(len(contours_for_sub_process)):
|
||||
cnts_org.append(contours_for_sub_process[j])
|
||||
all_index_text_con.append(indexes_for_sub_process[j])
|
||||
for i in range(num_cores):
|
||||
processes[i].join()
|
||||
|
||||
print(all_index_text_con)
|
||||
return cnts_org
|
||||
def loop_contour_image(index_l, cnts,img, slope_first):
|
||||
img_copy = np.zeros(img.shape)
|
||||
img_copy = cv2.fillPoly(img_copy, pts=[cnts[index_l]], color=(1, 1, 1))
|
||||
|
|
|
|||
|
|
@ -17,114 +17,6 @@ from . import (
|
|||
isNaN,
|
||||
)
|
||||
|
||||
def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
|
||||
(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)]])
|
||||
|
||||
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=axis)
|
||||
|
||||
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)
|
||||
|
||||
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)
|
||||
|
||||
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.array(range(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]
|
||||
|
||||
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.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)
|
||||
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))
|
||||
# print(sigma_gaus,'sigma_gaus')
|
||||
except:
|
||||
sigma_gaus = 12
|
||||
if sigma_gaus < 3:
|
||||
sigma_gaus = 3
|
||||
# print(sigma_gaus,'sigma')
|
||||
|
||||
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)
|
||||
|
||||
peaks, _ = find_peaks(y_padded_smoothed, height=0)
|
||||
peaks_neg, _ = find_peaks(y_padded_up_to_down_padded, height=0)
|
||||
|
||||
return x, y, x_d, y_d, xv, x_min_cont, y_min_cont, x_max_cont, y_max_cont, first_nonzero, y_padded_up_to_down_padded, y_padded_smoothed, peaks, peaks_neg, rotation_matrix
|
||||
|
||||
def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
|
||||
|
||||
(h, w) = img_patch.shape[:2]
|
||||
|
|
@ -671,303 +563,6 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
|
|||
|
||||
return peaks, textline_boxes_rot
|
||||
|
||||
def separate_lines_vertical(img_patch, contour_text_interest, thetha):
|
||||
|
||||
thetha = thetha + 90
|
||||
contour_text_interest_copy = contour_text_interest.copy()
|
||||
x, y, x_d, y_d, xv, x_min_cont, y_min_cont, x_max_cont, y_max_cont, first_nonzero, y_padded_up_to_down_padded, y_padded_smoothed, peaks, peaks_neg, rotation_matrix = dedup_separate_lines(img_patch, contour_text_interest, thetha, 0)
|
||||
|
||||
|
||||
# plt.plot(y_padded_up_to_down_padded)
|
||||
# plt.plot(peaks_neg,y_padded_up_to_down_padded[peaks_neg],'*')
|
||||
# plt.title('negs')
|
||||
# plt.show()
|
||||
|
||||
# plt.plot(y_padded_smoothed)
|
||||
# plt.plot(peaks,y_padded_smoothed[peaks],'*')
|
||||
# plt.title('poss')
|
||||
# plt.show()
|
||||
|
||||
neg_peaks_max = np.max(y_padded_up_to_down_padded[peaks_neg])
|
||||
|
||||
arg_neg_must_be_deleted = np.array(range(len(peaks_neg)))[y_padded_up_to_down_padded[peaks_neg] / float(neg_peaks_max) < 0.42]
|
||||
|
||||
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]
|
||||
|
||||
peaks_new = peaks[:]
|
||||
peaks_neg_new = peaks_neg[:]
|
||||
clusters_to_be_deleted = []
|
||||
|
||||
if len(arg_diff_cluster) >= 2 and 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.append(arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :])
|
||||
elif len(arg_neg_must_be_deleted) >= 2 and len(arg_diff_cluster) == 0:
|
||||
clusters_to_be_deleted.append(arg_neg_must_be_deleted[:])
|
||||
|
||||
if len(arg_neg_must_be_deleted) == 1:
|
||||
clusters_to_be_deleted.append(arg_neg_must_be_deleted)
|
||||
|
||||
if len(clusters_to_be_deleted) > 0:
|
||||
peaks_new_extra = []
|
||||
for m in range(len(clusters_to_be_deleted)):
|
||||
min_cluster = np.min(peaks[clusters_to_be_deleted[m]])
|
||||
max_cluster = np.max(peaks[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[clusters_to_be_deleted[m][m1] - 1]]
|
||||
peaks_new = peaks_new[peaks_new != peaks[clusters_to_be_deleted[m][m1]]]
|
||||
|
||||
peaks_neg_new = peaks_neg_new[peaks_neg_new != peaks_neg[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)
|
||||
|
||||
peaks = peaks_new_tot[:]
|
||||
peaks_neg = peaks_neg_new[:]
|
||||
|
||||
else:
|
||||
peaks_new_tot = peaks[:]
|
||||
peaks = peaks_new_tot[:]
|
||||
peaks_neg = peaks_neg_new[:]
|
||||
|
||||
mean_value_of_peaks = np.mean(y_padded_smoothed[peaks])
|
||||
std_value_of_peaks = np.std(y_padded_smoothed[peaks])
|
||||
peaks_values = y_padded_smoothed[peaks]
|
||||
|
||||
peaks_neg = peaks_neg - 20 - 20
|
||||
peaks = peaks - 20
|
||||
|
||||
for jj in range(len(peaks_neg)):
|
||||
if peaks_neg[jj] > len(x) - 1:
|
||||
peaks_neg[jj] = len(x) - 1
|
||||
|
||||
for jj in range(len(peaks)):
|
||||
if peaks[jj] > len(x) - 1:
|
||||
peaks[jj] = len(x) - 1
|
||||
|
||||
textline_boxes = []
|
||||
textline_boxes_rot = []
|
||||
|
||||
if len(peaks_neg) == len(peaks) + 1 and len(peaks) >= 3:
|
||||
# print('11')
|
||||
for jj in range(len(peaks)):
|
||||
|
||||
if jj == (len(peaks) - 1):
|
||||
dis_to_next_up = abs(peaks[jj] - peaks_neg[jj])
|
||||
dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1])
|
||||
|
||||
if peaks_values[jj] > mean_value_of_peaks - std_value_of_peaks / 2.0:
|
||||
point_up = peaks[jj] + first_nonzero - int(1.3 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0)
|
||||
point_down = x_max_cont - 1 ##peaks[jj] + first_nonzero + int(1.3 * dis_to_next_down) #point_up# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0)
|
||||
else:
|
||||
point_up = peaks[jj] + first_nonzero - int(1.4 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0)
|
||||
point_down = x_max_cont - 1 ##peaks[jj] + first_nonzero + int(1.6 * dis_to_next_down) #point_up# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0)
|
||||
|
||||
point_down_narrow = peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./2)
|
||||
else:
|
||||
dis_to_next_up = abs(peaks[jj] - peaks_neg[jj])
|
||||
dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1])
|
||||
|
||||
if peaks_values[jj] > mean_value_of_peaks - std_value_of_peaks / 2.0:
|
||||
point_up = peaks[jj] + first_nonzero - int(1.1 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0)
|
||||
point_down = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0)
|
||||
else:
|
||||
point_up = peaks[jj] + first_nonzero - int(1.23 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0)
|
||||
point_down = peaks[jj] + first_nonzero + int(1.33 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0)
|
||||
|
||||
point_down_narrow = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./2)
|
||||
|
||||
if point_down_narrow >= img_patch.shape[0]:
|
||||
point_down_narrow = img_patch.shape[0] - 2
|
||||
|
||||
distances = [cv2.pointPolygonTest(contour_text_interest_copy, tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) for mj in range(len(xv))]
|
||||
distances = np.array(distances)
|
||||
|
||||
xvinside = xv[distances >= 0]
|
||||
|
||||
if len(xvinside) == 0:
|
||||
x_min = x_min_cont
|
||||
x_max = x_max_cont
|
||||
else:
|
||||
x_min = np.min(xvinside) # max(x_min_interest,x_min_cont)
|
||||
x_max = np.max(xvinside) # min(x_max_interest,x_max_cont)
|
||||
|
||||
p1 = np.dot(rotation_matrix, [int(point_up), int(y_min_cont)])
|
||||
p2 = np.dot(rotation_matrix, [int(point_down), int(y_min_cont)])
|
||||
p3 = np.dot(rotation_matrix, [int(point_down), int(y_max_cont)])
|
||||
p4 = np.dot(rotation_matrix, [int(point_up), int(y_max_cont)])
|
||||
|
||||
x_min_rot1, point_up_rot1 = p1[0] + x_d, p1[1] + y_d
|
||||
x_max_rot2, point_up_rot2 = p2[0] + x_d, p2[1] + y_d
|
||||
x_max_rot3, point_down_rot3 = p3[0] + x_d, p3[1] + y_d
|
||||
x_min_rot4, point_down_rot4 = p4[0] + x_d, p4[1] + y_d
|
||||
|
||||
if x_min_rot1 < 0:
|
||||
x_min_rot1 = 0
|
||||
if x_min_rot4 < 0:
|
||||
x_min_rot4 = 0
|
||||
if point_up_rot1 < 0:
|
||||
point_up_rot1 = 0
|
||||
if point_up_rot2 < 0:
|
||||
point_up_rot2 = 0
|
||||
|
||||
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)], [int(x_max_rot2), int(point_up_rot2)], [int(x_max_rot3), int(point_down_rot3)], [int(x_min_rot4), int(point_down_rot4)]]))
|
||||
|
||||
textline_boxes.append(np.array([[int(x_min), int(point_up)], [int(x_max), int(point_up)], [int(x_max), int(point_down)], [int(x_min), int(point_down)]]))
|
||||
|
||||
elif len(peaks) < 1:
|
||||
pass
|
||||
|
||||
elif len(peaks) == 1:
|
||||
x_min = x_min_cont
|
||||
x_max = x_max_cont
|
||||
|
||||
y_min = y_min_cont
|
||||
y_max = y_max_cont
|
||||
|
||||
p1 = np.dot(rotation_matrix, [int(point_up), int(y_min_cont)])
|
||||
p2 = np.dot(rotation_matrix, [int(point_down), int(y_min_cont)])
|
||||
p3 = np.dot(rotation_matrix, [int(point_down), int(y_max_cont)])
|
||||
p4 = np.dot(rotation_matrix, [int(point_up), int(y_max_cont)])
|
||||
|
||||
x_min_rot1, point_up_rot1 = p1[0] + x_d, p1[1] + y_d
|
||||
x_max_rot2, point_up_rot2 = p2[0] + x_d, p2[1] + y_d
|
||||
x_max_rot3, point_down_rot3 = p3[0] + x_d, p3[1] + y_d
|
||||
x_min_rot4, point_down_rot4 = p4[0] + x_d, p4[1] + y_d
|
||||
|
||||
if x_min_rot1 < 0:
|
||||
x_min_rot1 = 0
|
||||
if x_min_rot4 < 0:
|
||||
x_min_rot4 = 0
|
||||
if point_up_rot1 < 0:
|
||||
point_up_rot1 = 0
|
||||
if point_up_rot2 < 0:
|
||||
point_up_rot2 = 0
|
||||
|
||||
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)], [int(x_max_rot2), int(point_up_rot2)], [int(x_max_rot3), int(point_down_rot3)], [int(x_min_rot4), int(point_down_rot4)]]))
|
||||
|
||||
textline_boxes.append(np.array([[int(x_min), int(y_min)], [int(x_max), int(y_min)], [int(x_max), int(y_max)], [int(x_min), int(y_max)]]))
|
||||
|
||||
elif len(peaks) == 2:
|
||||
dis_to_next = np.abs(peaks[1] - peaks[0])
|
||||
for jj in range(len(peaks)):
|
||||
if jj == 0:
|
||||
point_up = 0 # peaks[jj] + first_nonzero - int(1. / 1.7 * dis_to_next)
|
||||
if point_up < 0:
|
||||
point_up = 1
|
||||
point_down = peaks[jj] + first_nonzero + int(1.0 / 1.8 * dis_to_next)
|
||||
elif jj == 1:
|
||||
point_down = peaks[jj] + first_nonzero + int(1.0 / 1.8 * dis_to_next)
|
||||
if point_down >= img_patch.shape[0]:
|
||||
point_down = img_patch.shape[0] - 2
|
||||
point_up = peaks[jj] + first_nonzero - int(1.0 / 1.8 * dis_to_next)
|
||||
|
||||
distances = [cv2.pointPolygonTest(contour_text_interest_copy, tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) for mj in range(len(xv))]
|
||||
distances = np.array(distances)
|
||||
|
||||
xvinside = xv[distances >= 0]
|
||||
|
||||
if len(xvinside) == 0:
|
||||
x_min = x_min_cont
|
||||
x_max = x_max_cont
|
||||
else:
|
||||
x_min = np.min(xvinside)
|
||||
x_max = np.max(xvinside)
|
||||
|
||||
p1 = np.dot(rotation_matrix, [int(point_up), int(y_min_cont)])
|
||||
p2 = np.dot(rotation_matrix, [int(point_down), int(y_min_cont)])
|
||||
p3 = np.dot(rotation_matrix, [int(point_down), int(y_max_cont)])
|
||||
p4 = np.dot(rotation_matrix, [int(point_up), int(y_max_cont)])
|
||||
|
||||
x_min_rot1, point_up_rot1 = p1[0] + x_d, p1[1] + y_d
|
||||
x_max_rot2, point_up_rot2 = p2[0] + x_d, p2[1] + y_d
|
||||
x_max_rot3, point_down_rot3 = p3[0] + x_d, p3[1] + y_d
|
||||
x_min_rot4, point_down_rot4 = p4[0] + x_d, p4[1] + y_d
|
||||
|
||||
if x_min_rot1 < 0:
|
||||
x_min_rot1 = 0
|
||||
if x_min_rot4 < 0:
|
||||
x_min_rot4 = 0
|
||||
if point_up_rot1 < 0:
|
||||
point_up_rot1 = 0
|
||||
if point_up_rot2 < 0:
|
||||
point_up_rot2 = 0
|
||||
|
||||
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)], [int(x_max_rot2), int(point_up_rot2)], [int(x_max_rot3), int(point_down_rot3)], [int(x_min_rot4), int(point_down_rot4)]]))
|
||||
|
||||
textline_boxes.append(np.array([[int(x_min), int(point_up)], [int(x_max), int(point_up)], [int(x_max), int(point_down)], [int(x_min), int(point_down)]]))
|
||||
else:
|
||||
for jj in range(len(peaks)):
|
||||
|
||||
if jj == 0:
|
||||
dis_to_next = peaks[jj + 1] - peaks[jj]
|
||||
# point_up=peaks[jj]+first_nonzero-int(1./3*dis_to_next)
|
||||
point_up = peaks[jj] + first_nonzero - int(1.0 / 1.9 * dis_to_next)
|
||||
if point_up < 0:
|
||||
point_up = 1
|
||||
# point_down=peaks[jj]+first_nonzero+int(1./3*dis_to_next)
|
||||
point_down = peaks[jj] + first_nonzero + int(1.0 / 1.9 * dis_to_next)
|
||||
elif jj == len(peaks) - 1:
|
||||
dis_to_next = peaks[jj] - peaks[jj - 1]
|
||||
# point_down=peaks[jj]+first_nonzero+int(1./3*dis_to_next)
|
||||
point_down = peaks[jj] + first_nonzero + int(1.0 / 1.7 * dis_to_next)
|
||||
if point_down >= img_patch.shape[0]:
|
||||
point_down = img_patch.shape[0] - 2
|
||||
# point_up=peaks[jj]+first_nonzero-int(1./3*dis_to_next)
|
||||
point_up = peaks[jj] + first_nonzero - int(1.0 / 1.9 * dis_to_next)
|
||||
else:
|
||||
dis_to_next_down = peaks[jj + 1] - peaks[jj]
|
||||
dis_to_next_up = peaks[jj] - peaks[jj - 1]
|
||||
|
||||
point_up = peaks[jj] + first_nonzero - int(1.0 / 1.9 * dis_to_next_up)
|
||||
point_down = peaks[jj] + first_nonzero + int(1.0 / 1.9 * dis_to_next_down)
|
||||
|
||||
distances = [cv2.pointPolygonTest(contour_text_interest_copy, tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) for mj in range(len(xv))]
|
||||
distances = np.array(distances)
|
||||
|
||||
xvinside = xv[distances >= 0]
|
||||
|
||||
if len(xvinside) == 0:
|
||||
x_min = x_min_cont
|
||||
x_max = x_max_cont
|
||||
else:
|
||||
x_min = np.min(xvinside) # max(x_min_interest,x_min_cont)
|
||||
x_max = np.max(xvinside) # min(x_max_interest,x_max_cont)
|
||||
|
||||
p1 = np.dot(rotation_matrix, [int(point_up), int(y_min_cont)])
|
||||
p2 = np.dot(rotation_matrix, [int(point_down), int(y_min_cont)])
|
||||
p3 = np.dot(rotation_matrix, [int(point_down), int(y_max_cont)])
|
||||
p4 = np.dot(rotation_matrix, [int(point_up), int(y_max_cont)])
|
||||
|
||||
x_min_rot1, point_up_rot1 = p1[0] + x_d, p1[1] + y_d
|
||||
x_max_rot2, point_up_rot2 = p2[0] + x_d, p2[1] + y_d
|
||||
x_max_rot3, point_down_rot3 = p3[0] + x_d, p3[1] + y_d
|
||||
x_min_rot4, point_down_rot4 = p4[0] + x_d, p4[1] + y_d
|
||||
|
||||
if x_min_rot1 < 0:
|
||||
x_min_rot1 = 0
|
||||
if x_min_rot4 < 0:
|
||||
x_min_rot4 = 0
|
||||
if point_up_rot1 < 0:
|
||||
point_up_rot1 = 0
|
||||
if point_up_rot2 < 0:
|
||||
point_up_rot2 = 0
|
||||
|
||||
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)], [int(x_max_rot2), int(point_up_rot2)], [int(x_max_rot3), int(point_down_rot3)], [int(x_min_rot4), int(point_down_rot4)]]))
|
||||
|
||||
textline_boxes.append(np.array([[int(x_min), int(point_up)], [int(x_max), int(point_up)], [int(x_max), int(point_down)], [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]
|
||||
|
|
@ -1183,149 +778,6 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
|
|||
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)
|
||||
|
||||
mada_n = img_path.sum(axis=1)
|
||||
|
||||
##plt.plot(mada_n)
|
||||
##plt.show()
|
||||
|
||||
first_nonzero = 0 # (next((i for i, x in enumerate(mada_n) if x), None))
|
||||
|
||||
y = mada_n[:] # [first_nonzero:last_nonzero]
|
||||
y_help = np.zeros(len(y) + 40)
|
||||
y_help[20 : len(y) + 20] = y
|
||||
x = np.array(range(len(y)))
|
||||
|
||||
peaks_real, _ = find_peaks(gaussian_filter1d(y, 3), height=0)
|
||||
if len(peaks_real) <= 2 and len(peaks_real) > 1:
|
||||
sigma_gaus = 10
|
||||
else:
|
||||
sigma_gaus = 5
|
||||
|
||||
z = gaussian_filter1d(y_help, sigma_gaus)
|
||||
zneg_rev = -y_help + np.max(y_help)
|
||||
zneg = np.zeros(len(zneg_rev) + 40)
|
||||
zneg[20 : len(zneg_rev) + 20] = zneg_rev
|
||||
zneg = gaussian_filter1d(zneg, sigma_gaus)
|
||||
|
||||
peaks, _ = find_peaks(z, height=0)
|
||||
peaks_neg, _ = find_peaks(zneg, height=0)
|
||||
|
||||
for nn in range(len(peaks_neg)):
|
||||
if peaks_neg[nn] > len(z) - 1:
|
||||
peaks_neg[nn] = len(z) - 1
|
||||
if peaks_neg[nn] < 0:
|
||||
peaks_neg[nn] = 0
|
||||
|
||||
diff_peaks = np.abs(np.diff(peaks_neg))
|
||||
|
||||
cut_off = 20
|
||||
peaks_neg_true = []
|
||||
forest = []
|
||||
|
||||
for i in range(len(peaks_neg)):
|
||||
if i == 0:
|
||||
forest.append(peaks_neg[i])
|
||||
if i < (len(peaks_neg) - 1):
|
||||
if diff_peaks[i] <= cut_off:
|
||||
forest.append(peaks_neg[i + 1])
|
||||
if diff_peaks[i] > cut_off:
|
||||
# print(forest[np.argmin(z[forest]) ] )
|
||||
if not isNaN(forest[np.argmin(z[forest])]):
|
||||
peaks_neg_true.append(forest[np.argmin(z[forest])])
|
||||
forest = []
|
||||
forest.append(peaks_neg[i + 1])
|
||||
if i == (len(peaks_neg) - 1):
|
||||
# print(print(forest[np.argmin(z[forest]) ] ))
|
||||
if not isNaN(forest[np.argmin(z[forest])]):
|
||||
peaks_neg_true.append(forest[np.argmin(z[forest])])
|
||||
|
||||
diff_peaks_pos = np.abs(np.diff(peaks))
|
||||
|
||||
cut_off = 20
|
||||
peaks_pos_true = []
|
||||
forest = []
|
||||
|
||||
for i in range(len(peaks)):
|
||||
if i == 0:
|
||||
forest.append(peaks[i])
|
||||
if i < (len(peaks) - 1):
|
||||
if diff_peaks_pos[i] <= cut_off:
|
||||
forest.append(peaks[i + 1])
|
||||
if diff_peaks_pos[i] > cut_off:
|
||||
# print(forest[np.argmin(z[forest]) ] )
|
||||
if not isNaN(forest[np.argmax(z[forest])]):
|
||||
peaks_pos_true.append(forest[np.argmax(z[forest])])
|
||||
forest = []
|
||||
forest.append(peaks[i + 1])
|
||||
if i == (len(peaks) - 1):
|
||||
# print(print(forest[np.argmin(z[forest]) ] ))
|
||||
if not isNaN(forest[np.argmax(z[forest])]):
|
||||
peaks_pos_true.append(forest[np.argmax(z[forest])])
|
||||
|
||||
# print(len(peaks_neg_true) ,len(peaks_pos_true) ,'lensss')
|
||||
|
||||
if len(peaks_neg_true) > 0:
|
||||
peaks_neg_true = np.array(peaks_neg_true)
|
||||
"""
|
||||
#plt.figure(figsize=(40,40))
|
||||
#plt.subplot(1,2,1)
|
||||
#plt.title('Textline segmentation von Textregion')
|
||||
#plt.imshow(img_path)
|
||||
#plt.xlabel('X')
|
||||
#plt.ylabel('Y')
|
||||
#plt.subplot(1,2,2)
|
||||
#plt.title('Dichte entlang X')
|
||||
#base = pyplot.gca().transData
|
||||
#rot = transforms.Affine2D().rotate_deg(90)
|
||||
#plt.plot(zneg,np.array(range(len(zneg))))
|
||||
#plt.plot(zneg[peaks_neg_true],peaks_neg_true,'*')
|
||||
#plt.gca().invert_yaxis()
|
||||
|
||||
#plt.xlabel('Dichte')
|
||||
#plt.ylabel('Y')
|
||||
##plt.plot([0,len(y)], [grenze,grenze])
|
||||
#plt.show()
|
||||
"""
|
||||
peaks_neg_true = peaks_neg_true - 20 - 20
|
||||
|
||||
# print(peaks_neg_true)
|
||||
for i in range(len(peaks_neg_true)):
|
||||
img_path[peaks_neg_true[i] - 6 : peaks_neg_true[i] + 6, :] = 0
|
||||
|
||||
else:
|
||||
pass
|
||||
|
||||
if len(peaks_pos_true) > 0:
|
||||
peaks_pos_true = np.array(peaks_pos_true)
|
||||
peaks_pos_true = peaks_pos_true - 20
|
||||
|
||||
for i in range(len(peaks_pos_true)):
|
||||
img_path[peaks_pos_true[i] - 8 : peaks_pos_true[i] + 8, :] = 1
|
||||
else:
|
||||
pass
|
||||
kernel = np.ones((5, 5), np.uint8)
|
||||
|
||||
# img_path = cv2.erode(img_path,kernel,iterations = 3)
|
||||
img_path = cv2.erode(img_path, kernel, iterations=2)
|
||||
return img_path
|
||||
|
||||
def separate_lines_vertical_cont(img_patch, contour_text_interest, thetha, box_ind, add_boxes_coor_into_textlines):
|
||||
kernel = np.ones((5, 5), np.uint8)
|
||||
pixel = 255
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue