qurator-spk
/
eynollah
mirror of https://github.com/qurator-spk/eynollah.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

typo: s,seperator,separator,

Browse Source
pull/23/head
Konstantin Baierer 3 years ago
parent ec9939c3c7
commit 526769354a
2 changed files with 117 additions and 117 deletions
Show Stats Download Patch File Download Diff File

58
qurator/eynollah/eynollah.py
Unescape Escape View File

@ -1461,9 +1461,9 @@ class Eynollah:
if num_col_classifier in (1, 2): if num_col_classifier in (1, 2):
try: try:
regions_without_seperators = (text_regions_p[:, :] == 1) * 1 regions_without_separators = (text_regions_p[:, :] == 1) * 1
regions_without_seperators = regions_without_seperators.astype(np.uint8) regions_without_separators = regions_without_separators.astype(np.uint8)
text_regions_p = get_marginals(rotate_image(regions_without_seperators, slope_deskew), text_regions_p, num_col_classifier, slope_deskew, kernel=KERNEL) text_regions_p = get_marginals(rotate_image(regions_without_separators, slope_deskew), text_regions_p, num_col_classifier, slope_deskew, kernel=KERNEL)
except Exception as e: except Exception as e:
self.logger.error("exception %s", e) self.logger.error("exception %s", e)
@ -1478,12 +1478,12 @@ class Eynollah:
_, textline_mask_tot_d, text_regions_p_1_n = rotation_not_90_func(image_page, textline_mask_tot, text_regions_p, slope_deskew) _, textline_mask_tot_d, text_regions_p_1_n = rotation_not_90_func(image_page, textline_mask_tot, text_regions_p, slope_deskew)
text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1]) text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1])
textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1]) textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1])
regions_without_seperators_d = (text_regions_p_1_n[:, :] == 1) * 1 regions_without_separators_d = (text_regions_p_1_n[:, :] == 1) * 1
regions_without_seperators = (text_regions_p[:, :] == 1) * 1 # ( (text_regions_p[:,:]==1) | (text_regions_p[:,:]==2) )*1 #self.return_regions_without_seperators_new(text_regions_p[:,:,0],img_only_regions) regions_without_separators = (text_regions_p[:, :] == 1) * 1 # ( (text_regions_p[:,:]==1) | (text_regions_p[:,:]==2) )*1 #self.return_regions_without_separators_new(text_regions_p[:,:,0],img_only_regions)
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
text_regions_p_1_n = None text_regions_p_1_n = None
textline_mask_tot_d = None textline_mask_tot_d = None
regions_without_seperators_d = None regions_without_separators_d = None
pixel_lines = 3 pixel_lines = 3
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
_, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(np.repeat(text_regions_p[:, :, np.newaxis], 3, axis=2), num_col_classifier, pixel_lines) _, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(np.repeat(text_regions_p[:, :, np.newaxis], 3, axis=2), num_col_classifier, pixel_lines)
@ -1496,18 +1496,18 @@ class Eynollah:
if num_col_classifier >= 3: if num_col_classifier >= 3:
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
regions_without_seperators = regions_without_seperators.astype(np.uint8) regions_without_separators = regions_without_separators.astype(np.uint8)
regions_without_seperators = cv2.erode(regions_without_seperators[:, :], KERNEL, iterations=6) regions_without_separators = cv2.erode(regions_without_separators[:, :], KERNEL, iterations=6)
else: else:
regions_without_seperators_d = regions_without_seperators_d.astype(np.uint8) regions_without_separators_d = regions_without_separators_d.astype(np.uint8)
regions_without_seperators_d = cv2.erode(regions_without_seperators_d[:, :], KERNEL, iterations=6) regions_without_separators_d = cv2.erode(regions_without_separators_d[:, :], KERNEL, iterations=6)
t1 = time.time() t1 = time.time()
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
boxes = return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_without_seperators, matrix_of_lines_ch, num_col_classifier) boxes = return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_without_separators, matrix_of_lines_ch, num_col_classifier)
boxes_d = None boxes_d = None
self.logger.debug("len(boxes): %s", len(boxes)) self.logger.debug("len(boxes): %s", len(boxes))
else: else:
boxes_d = return_boxes_of_images_by_order_of_reading_new(splitter_y_new_d, regions_without_seperators_d, matrix_of_lines_ch_d, num_col_classifier) boxes_d = return_boxes_of_images_by_order_of_reading_new(splitter_y_new_d, regions_without_separators_d, matrix_of_lines_ch_d, num_col_classifier)
boxes = None boxes = None
self.logger.debug("len(boxes): %s", len(boxes_d)) self.logger.debug("len(boxes): %s", len(boxes_d))
@ -1519,7 +1519,7 @@ class Eynollah:
# plt.show() # plt.show()
K.clear_session() K.clear_session()
self.logger.debug('exit run_boxes_no_full_layout') self.logger.debug('exit run_boxes_no_full_layout')
return polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_seperators_d, boxes, boxes_d return polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, boxes, boxes_d
def run_boxes_full_layout(self, image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions): def run_boxes_full_layout(self, image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions):
self.logger.debug('enter run_boxes_full_layout') self.logger.debug('enter run_boxes_full_layout')
@ -1570,19 +1570,19 @@ class Eynollah:
text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1]) text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1])
textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1]) textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1])
regions_fully_n = resize_image(regions_fully_n, text_regions_p.shape[0], text_regions_p.shape[1]) regions_fully_n = resize_image(regions_fully_n, text_regions_p.shape[0], text_regions_p.shape[1])
regions_without_seperators_d = (text_regions_p_1_n[:, :] == 1) * 1 regions_without_separators_d = (text_regions_p_1_n[:, :] == 1) * 1
else: else:
text_regions_p_1_n = None text_regions_p_1_n = None
textline_mask_tot_d = None textline_mask_tot_d = None
regions_without_seperators_d = None regions_without_separators_d = None
regions_without_seperators = (text_regions_p[:, :] == 1) * 1 # ( (text_regions_p[:,:]==1) | (text_regions_p[:,:]==2) )*1 #self.return_regions_without_seperators_new(text_regions_p[:,:,0],img_only_regions) regions_without_separators = (text_regions_p[:, :] == 1) * 1 # ( (text_regions_p[:,:]==1) | (text_regions_p[:,:]==2) )*1 #self.return_regions_without_separators_new(text_regions_p[:,:,0],img_only_regions)
K.clear_session() K.clear_session()
img_revised_tab = np.copy(text_regions_p[:, :]) img_revised_tab = np.copy(text_regions_p[:, :])
polygons_of_images = return_contours_of_interested_region(img_revised_tab, 5) polygons_of_images = return_contours_of_interested_region(img_revised_tab, 5)
self.logger.debug('exit run_boxes_full_layout') self.logger.debug('exit run_boxes_full_layout')
return polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_seperators_d, regions_fully, regions_without_seperators return polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, regions_fully, regions_without_separators
def run(self): def run(self):
""" """
@ -1627,14 +1627,14 @@ class Eynollah:
t1 = time.time() t1 = time.time()
if not self.full_layout: if not self.full_layout:
polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_seperators_d, boxes, boxes_d = self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier) polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, boxes, boxes_d = self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier)
pixel_img = 4 pixel_img = 4
min_area_mar = 0.00001 min_area_mar = 0.00001
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar) polygons_of_marginals = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
if self.full_layout: if self.full_layout:
polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_seperators_d, regions_fully, regions_without_seperators = self.run_boxes_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions) polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_separators_d, regions_fully, regions_without_separators = self.run_boxes_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions)
text_only = ((img_revised_tab[:, :] == 1)) * 1 text_only = ((img_revised_tab[:, :] == 1)) * 1
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
@ -1775,24 +1775,24 @@ class Eynollah:
if num_col_classifier >= 3: if num_col_classifier >= 3:
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
regions_without_seperators = regions_without_seperators.astype(np.uint8) regions_without_separators = regions_without_separators.astype(np.uint8)
regions_without_seperators = cv2.erode(regions_without_seperators[:, :], KERNEL, iterations=6) regions_without_separators = cv2.erode(regions_without_separators[:, :], KERNEL, iterations=6)
random_pixels_for_image = np.random.randn(regions_without_seperators.shape[0], regions_without_seperators.shape[1]) random_pixels_for_image = np.random.randn(regions_without_separators.shape[0], regions_without_separators.shape[1])
random_pixels_for_image[random_pixels_for_image < -0.5] = 0 random_pixels_for_image[random_pixels_for_image < -0.5] = 0
random_pixels_for_image[random_pixels_for_image != 0] = 1 random_pixels_for_image[random_pixels_for_image != 0] = 1
regions_without_seperators[(random_pixels_for_image[:, :] == 1) & (text_regions_p[:, :] == 5)] = 1 regions_without_separators[(random_pixels_for_image[:, :] == 1) & (text_regions_p[:, :] == 5)] = 1
else: else:
regions_without_seperators_d = regions_without_seperators_d.astype(np.uint8) regions_without_separators_d = regions_without_separators_d.astype(np.uint8)
regions_without_seperators_d = cv2.erode(regions_without_seperators_d[:, :], KERNEL, iterations=6) regions_without_separators_d = cv2.erode(regions_without_separators_d[:, :], KERNEL, iterations=6)
random_pixels_for_image = np.random.randn(regions_without_seperators_d.shape[0], regions_without_seperators_d.shape[1]) random_pixels_for_image = np.random.randn(regions_without_separators_d.shape[0], regions_without_separators_d.shape[1])
random_pixels_for_image[random_pixels_for_image < -0.5] = 0 random_pixels_for_image[random_pixels_for_image < -0.5] = 0
random_pixels_for_image[random_pixels_for_image != 0] = 1 random_pixels_for_image[random_pixels_for_image != 0] = 1
regions_without_seperators_d[(random_pixels_for_image[:, :] == 1) & (text_regions_p_1_n[:, :] == 5)] = 1 regions_without_separators_d[(random_pixels_for_image[:, :] == 1) & (text_regions_p_1_n[:, :] == 5)] = 1
if np.abs(slope_deskew) < SLOPE_THRESHOLD: if np.abs(slope_deskew) < SLOPE_THRESHOLD:
boxes = return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_without_seperators, matrix_of_lines_ch, num_col_classifier) boxes = return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_without_separators, matrix_of_lines_ch, num_col_classifier)
else: else:
boxes_d = return_boxes_of_images_by_order_of_reading_new(splitter_y_new_d, regions_without_seperators_d, matrix_of_lines_ch_d, num_col_classifier) boxes_d = return_boxes_of_images_by_order_of_reading_new(splitter_y_new_d, regions_without_separators_d, matrix_of_lines_ch_d, num_col_classifier)
if self.plotter: if self.plotter:
self.plotter.write_images_into_directory(polygons_of_images, image_page) self.plotter.write_images_into_directory(polygons_of_images, image_page)

176
qurator/eynollah/utils/__init__.py
Unescape Escape View File

@ -353,22 +353,22 @@ def boosting_headers_by_longshot_region_segmentation(textregion_pre_p, textregio
return textregion_pre_p return textregion_pre_p
def find_num_col_deskew(regions_without_seperators, sigma_, multiplier=3.8): def find_num_col_deskew(regions_without_separators, sigma_, multiplier=3.8):
regions_without_seperators_0 = regions_without_seperators[:,:].sum(axis=1) regions_without_separators_0 = regions_without_separators[:,:].sum(axis=1)
z = gaussian_filter1d(regions_without_seperators_0, sigma_) z = gaussian_filter1d(regions_without_separators_0, sigma_)
return np.std(z) return np.std(z)
def find_num_col(regions_without_seperators, multiplier=3.8): def find_num_col(regions_without_separators, multiplier=3.8):
regions_without_seperators_0 = regions_without_seperators[:, :].sum(axis=0) regions_without_separators_0 = regions_without_separators[:, :].sum(axis=0)
##plt.plot(regions_without_seperators_0) ##plt.plot(regions_without_separators_0)
##plt.show() ##plt.show()
sigma_ = 35 # 70#35 sigma_ = 35 # 70#35
meda_n_updown = regions_without_seperators_0[len(regions_without_seperators_0) :: -1] meda_n_updown = regions_without_separators_0[len(regions_without_separators_0) :: -1]
first_nonzero = next((i for i, x in enumerate(regions_without_seperators_0) if x), 0) 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 = next((i for i, x in enumerate(meda_n_updown) if x), 0)
last_nonzero = len(regions_without_seperators_0) - last_nonzero last_nonzero = len(regions_without_separators_0) - last_nonzero
y = regions_without_seperators_0 # [first_nonzero:last_nonzero] y = regions_without_separators_0 # [first_nonzero:last_nonzero]
y_help = np.zeros(len(y) + 20) y_help = np.zeros(len(y) + 20)
y_help[10 : len(y) + 10] = y y_help[10 : len(y) + 10] = y
x = np.array(range(len(y))) x = np.array(range(len(y)))
@ -386,8 +386,8 @@ def find_num_col(regions_without_seperators, multiplier=3.8):
first_nonzero = first_nonzero + 200 first_nonzero = first_nonzero + 200
peaks_neg = peaks_neg[(peaks_neg > first_nonzero) & (peaks_neg < last_nonzero)] peaks_neg = peaks_neg[(peaks_neg > first_nonzero) & (peaks_neg < last_nonzero)]
peaks = peaks[(peaks > 0.06 * regions_without_seperators.shape[1]) & (peaks < 0.94 * regions_without_seperators.shape[1])] peaks = peaks[(peaks > 0.06 * regions_without_separators.shape[1]) & (peaks < 0.94 * regions_without_separators.shape[1])]
peaks_neg = peaks_neg[(peaks_neg > 370) & (peaks_neg < (regions_without_seperators.shape[1] - 370))] peaks_neg = peaks_neg[(peaks_neg > 370) & (peaks_neg < (regions_without_separators.shape[1] - 370))]
interest_pos = z[peaks] interest_pos = z[peaks]
interest_pos = interest_pos[interest_pos > 10] interest_pos = interest_pos[interest_pos > 10]
# plt.plot(z) # plt.plot(z)
@ -517,22 +517,22 @@ def find_num_col(regions_without_seperators, multiplier=3.8):
##print(len(peaks_neg_true)) ##print(len(peaks_neg_true))
return len(peaks_neg_true), peaks_neg_true return len(peaks_neg_true), peaks_neg_true
def find_num_col_only_image(regions_without_seperators, multiplier=3.8): def find_num_col_only_image(regions_without_separators, multiplier=3.8):
regions_without_seperators_0 = regions_without_seperators[:, :].sum(axis=0) regions_without_separators_0 = regions_without_separators[:, :].sum(axis=0)
##plt.plot(regions_without_seperators_0) ##plt.plot(regions_without_separators_0)
##plt.show() ##plt.show()
sigma_ = 15 sigma_ = 15
meda_n_updown = regions_without_seperators_0[len(regions_without_seperators_0) :: -1] meda_n_updown = regions_without_separators_0[len(regions_without_separators_0) :: -1]
first_nonzero = next((i for i, x in enumerate(regions_without_seperators_0) if x), 0) 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 = next((i for i, x in enumerate(meda_n_updown) if x), 0)
last_nonzero = len(regions_without_seperators_0) - last_nonzero last_nonzero = len(regions_without_separators_0) - last_nonzero
y = regions_without_seperators_0 # [first_nonzero:last_nonzero] y = regions_without_separators_0 # [first_nonzero:last_nonzero]
y_help = np.zeros(len(y) + 20) y_help = np.zeros(len(y) + 20)
@ -558,9 +558,9 @@ def find_num_col_only_image(regions_without_seperators, multiplier=3.8):
peaks_neg = peaks_neg[(peaks_neg > first_nonzero) & (peaks_neg < last_nonzero)] peaks_neg = peaks_neg[(peaks_neg > first_nonzero) & (peaks_neg < last_nonzero)]
peaks = peaks[(peaks > 0.09 * regions_without_seperators.shape[1]) & (peaks < 0.91 * regions_without_seperators.shape[1])] 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_seperators.shape[1] - 500))] peaks_neg = peaks_neg[(peaks_neg > 500) & (peaks_neg < (regions_without_separators.shape[1] - 500))]
# print(peaks) # print(peaks)
interest_pos = z[peaks] interest_pos = z[peaks]
@ -703,31 +703,31 @@ def find_num_col_only_image(regions_without_seperators, multiplier=3.8):
return len(peaks_fin_true), peaks_fin_true return len(peaks_fin_true), peaks_fin_true
def find_num_col_by_vertical_lines(regions_without_seperators, multiplier=3.8): def find_num_col_by_vertical_lines(regions_without_separators, multiplier=3.8):
regions_without_seperators_0 = regions_without_seperators[:, :, 0].sum(axis=0) regions_without_separators_0 = regions_without_separators[:, :, 0].sum(axis=0)
##plt.plot(regions_without_seperators_0) ##plt.plot(regions_without_separators_0)
##plt.show() ##plt.show()
sigma_ = 35 # 70#35 sigma_ = 35 # 70#35
z = gaussian_filter1d(regions_without_seperators_0, sigma_) z = gaussian_filter1d(regions_without_separators_0, sigma_)
peaks, _ = find_peaks(z, height=0) peaks, _ = find_peaks(z, height=0)
# print(peaks,'peaksnew') # print(peaks,'peaksnew')
return peaks return peaks
def return_regions_without_seperators(regions_pre): def return_regions_without_separators(regions_pre):
kernel = np.ones((5, 5), np.uint8) kernel = np.ones((5, 5), np.uint8)
regions_without_seperators = ((regions_pre[:, :] != 6) & (regions_pre[:, :] != 0)) * 1 regions_without_separators = ((regions_pre[:, :] != 6) & (regions_pre[:, :] != 0)) * 1
# regions_without_seperators=( (image_regions_eraly_p[:,:,:]!=6) & (image_regions_eraly_p[:,:,:]!=0) & (image_regions_eraly_p[:,:,:]!=5) & (image_regions_eraly_p[:,:,:]!=8) & (image_regions_eraly_p[:,:,:]!=7))*1 # regions_without_separators=( (image_regions_eraly_p[:,:,:]!=6) & (image_regions_eraly_p[:,:,:]!=0) & (image_regions_eraly_p[:,:,:]!=5) & (image_regions_eraly_p[:,:,:]!=8) & (image_regions_eraly_p[:,:,:]!=7))*1
regions_without_seperators = regions_without_seperators.astype(np.uint8) regions_without_separators = regions_without_separators.astype(np.uint8)
regions_without_seperators = cv2.erode(regions_without_seperators, kernel, iterations=6) regions_without_separators = cv2.erode(regions_without_separators, kernel, iterations=6)
return regions_without_seperators return regions_without_separators
def put_drop_out_from_only_drop_model(layout_no_patch, layout1): def put_drop_out_from_only_drop_model(layout_no_patch, layout1):
@ -1219,7 +1219,7 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
#print(all_args_uniq,'all_args_uniq') #print(all_args_uniq,'all_args_uniq')
if len(all_args_uniq)>0: if len(all_args_uniq)>0:
if type(all_args_uniq[0]) is list: if type(all_args_uniq[0]) is list:
special_seperators=[] special_separators=[]
contours_new=[] contours_new=[]
for dd in range(len(all_args_uniq)): for dd in range(len(all_args_uniq)):
merged_all=None merged_all=None
@ -1228,7 +1228,7 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
some_x_min=x_min_main_hor[all_args_uniq[dd]] some_x_min=x_min_main_hor[all_args_uniq[dd]]
some_x_max=x_max_main_hor[all_args_uniq[dd]] some_x_max=x_max_main_hor[all_args_uniq[dd]]
#img_in=np.zeros(seperators_closeup_n[:,:,2].shape) #img_in=np.zeros(separators_closeup_n[:,:,2].shape)
#print(img_p_in_ver.shape[1],some_x_max-some_x_min,'xdiff') #print(img_p_in_ver.shape[1],some_x_max-some_x_min,'xdiff')
diff_x_some=some_x_max-some_x_min diff_x_some=some_x_max-some_x_min
for jv in range(len(some_args)): for jv in range(len(some_args)):
@ -1245,14 +1245,14 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
if diff_max_min_uniques>sum_dis and ( (sum_dis/float(diff_max_min_uniques) ) >0.85 ) and ( (diff_max_min_uniques/float(img_p_in_ver.shape[1]))>0.85 ) and np.std( dist_x_hor[some_args] )<(0.55*np.mean( dist_x_hor[some_args] )): if diff_max_min_uniques>sum_dis and ( (sum_dis/float(diff_max_min_uniques) ) >0.85 ) and ( (diff_max_min_uniques/float(img_p_in_ver.shape[1]))>0.85 ) and np.std( dist_x_hor[some_args] )<(0.55*np.mean( dist_x_hor[some_args] )):
#print(dist_x_hor[some_args],dist_x_hor[some_args].sum(),np.min(x_min_main_hor[some_args]) ,np.max(x_max_main_hor[some_args]),'jalibdi') #print(dist_x_hor[some_args],dist_x_hor[some_args].sum(),np.min(x_min_main_hor[some_args]) ,np.max(x_max_main_hor[some_args]),'jalibdi')
#print(np.mean( dist_x_hor[some_args] ),np.std( dist_x_hor[some_args] ),np.var( dist_x_hor[some_args] ),'jalibdiha') #print(np.mean( dist_x_hor[some_args] ),np.std( dist_x_hor[some_args] ),np.var( dist_x_hor[some_args] ),'jalibdiha')
special_seperators.append(np.mean(cy_main_hor[some_args])) special_separators.append(np.mean(cy_main_hor[some_args]))
else: else:
img_p_in=img_in_hor img_p_in=img_in_hor
special_seperators=[] special_separators=[]
else: else:
img_p_in=img_in_hor img_p_in=img_in_hor
special_seperators=[] special_separators=[]
img_p_in_ver[:,:,0][img_p_in_ver[:,:,0]==255]=1 img_p_in_ver[:,:,0][img_p_in_ver[:,:,0]==255]=1
@ -1275,8 +1275,8 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
else: else:
img_p_in=np.copy(img_in_hor) img_p_in=np.copy(img_in_hor)
special_seperators=[] special_separators=[]
return img_p_in[:,:,0],special_seperators return img_p_in[:,:,0],special_separators
def return_points_with_boundies(peaks_neg_fin, first_point, last_point): def return_points_with_boundies(peaks_neg_fin, first_point, last_point):
peaks_neg_tot = [] peaks_neg_tot = []
@ -1288,45 +1288,45 @@ def return_points_with_boundies(peaks_neg_fin, first_point, last_point):
def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_lines, contours_h=None): def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_lines, contours_h=None):
seperators_closeup=( (region_pre_p[:,:,:]==pixel_lines))*1 separators_closeup=( (region_pre_p[:,:,:]==pixel_lines))*1
seperators_closeup[0:110,:,:]=0 separators_closeup[0:110,:,:]=0
seperators_closeup[seperators_closeup.shape[0]-150:,:,:]=0 separators_closeup[separators_closeup.shape[0]-150:,:,:]=0
kernel = np.ones((5,5),np.uint8) kernel = np.ones((5,5),np.uint8)
seperators_closeup=seperators_closeup.astype(np.uint8) separators_closeup=separators_closeup.astype(np.uint8)
seperators_closeup = cv2.dilate(seperators_closeup,kernel,iterations = 1) separators_closeup = cv2.dilate(separators_closeup,kernel,iterations = 1)
seperators_closeup = cv2.erode(seperators_closeup,kernel,iterations = 1) separators_closeup = cv2.erode(separators_closeup,kernel,iterations = 1)
seperators_closeup_new=np.zeros((seperators_closeup.shape[0] ,seperators_closeup.shape[1] )) separators_closeup_new=np.zeros((separators_closeup.shape[0] ,separators_closeup.shape[1] ))
##_,seperators_closeup_n=self.combine_hor_lines_and_delete_cross_points_and_get_lines_features_back(region_pre_p[:,:,0]) ##_,separators_closeup_n=self.combine_hor_lines_and_delete_cross_points_and_get_lines_features_back(region_pre_p[:,:,0])
seperators_closeup_n=np.copy(seperators_closeup) separators_closeup_n=np.copy(separators_closeup)
seperators_closeup_n=seperators_closeup_n.astype(np.uint8) separators_closeup_n=separators_closeup_n.astype(np.uint8)
##plt.imshow(seperators_closeup_n[:,:,0]) ##plt.imshow(separators_closeup_n[:,:,0])
##plt.show() ##plt.show()
seperators_closeup_n_binary=np.zeros(( seperators_closeup_n.shape[0],seperators_closeup_n.shape[1]) ) separators_closeup_n_binary=np.zeros(( separators_closeup_n.shape[0],separators_closeup_n.shape[1]) )
seperators_closeup_n_binary[:,:]=seperators_closeup_n[:,:,0] separators_closeup_n_binary[:,:]=separators_closeup_n[:,:,0]
seperators_closeup_n_binary[:,:][seperators_closeup_n_binary[:,:]!=0]=1 separators_closeup_n_binary[:,:][separators_closeup_n_binary[:,:]!=0]=1
#seperators_closeup_n_binary[:,:][seperators_closeup_n_binary[:,:]==0]=255 #separators_closeup_n_binary[:,:][separators_closeup_n_binary[:,:]==0]=255
#seperators_closeup_n_binary[:,:][seperators_closeup_n_binary[:,:]==-255]=0 #separators_closeup_n_binary[:,:][separators_closeup_n_binary[:,:]==-255]=0
#seperators_closeup_n_binary=(seperators_closeup_n_binary[:,:]==2)*1 #separators_closeup_n_binary=(separators_closeup_n_binary[:,:]==2)*1
#gray = cv2.cvtColor(seperators_closeup_n, cv2.COLOR_BGR2GRAY) #gray = cv2.cvtColor(separators_closeup_n, cv2.COLOR_BGR2GRAY)
### ###
#print(seperators_closeup_n_binary.shape) #print(separators_closeup_n_binary.shape)
gray_early=np.repeat(seperators_closeup_n_binary[:, :, np.newaxis], 3, axis=2) gray_early=np.repeat(separators_closeup_n_binary[:, :, np.newaxis], 3, axis=2)
gray_early=gray_early.astype(np.uint8) gray_early=gray_early.astype(np.uint8)
#print(gray_early.shape,'burda') #print(gray_early.shape,'burda')
@ -1364,9 +1364,9 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
### ###
seperators_closeup_n_binary=cv2.fillPoly(seperators_closeup_n_binary,pts=cnts_hor_e,color=(0,0,0)) separators_closeup_n_binary=cv2.fillPoly(separators_closeup_n_binary,pts=cnts_hor_e,color=(0,0,0))
gray = cv2.bitwise_not(seperators_closeup_n_binary) gray = cv2.bitwise_not(separators_closeup_n_binary)
gray=gray.astype(np.uint8) gray=gray.astype(np.uint8)
@ -1418,18 +1418,18 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
vertical = cv2.dilate(vertical,kernel,iterations = 1) vertical = cv2.dilate(vertical,kernel,iterations = 1)
# Show extracted vertical lines # Show extracted vertical lines
horizontal,special_seperators=combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(vertical,horizontal,num_col_classifier) horizontal,special_separators=combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(vertical,horizontal,num_col_classifier)
#plt.imshow(horizontal) #plt.imshow(horizontal)
#plt.show() #plt.show()
#print(vertical.shape,np.unique(vertical),'verticalvertical') #print(vertical.shape,np.unique(vertical),'verticalvertical')
seperators_closeup_new[:,:][vertical[:,:]!=0]=1 separators_closeup_new[:,:][vertical[:,:]!=0]=1
seperators_closeup_new[:,:][horizontal[:,:]!=0]=1 separators_closeup_new[:,:][horizontal[:,:]!=0]=1
##plt.imshow(seperators_closeup_new) ##plt.imshow(separators_closeup_new)
##plt.show() ##plt.show()
##seperators_closeup_n ##separators_closeup_n
vertical=np.repeat(vertical[:, :, np.newaxis], 3, axis=2) vertical=np.repeat(vertical[:, :, np.newaxis], 3, axis=2)
vertical=vertical.astype(np.uint8) vertical=vertical.astype(np.uint8)
@ -1454,7 +1454,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
x_max_main_ver=x_max_main[slope_lines==1] x_max_main_ver=x_max_main[slope_lines==1]
cx_main_ver=cx_main[slope_lines==1] cx_main_ver=cx_main[slope_lines==1]
dist_y_ver=y_max_main_ver-y_min_main_ver dist_y_ver=y_max_main_ver-y_min_main_ver
len_y=seperators_closeup.shape[0]/3.0 len_y=separators_closeup.shape[0]/3.0
#plt.imshow(horizontal) #plt.imshow(horizontal)
@ -1470,7 +1470,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
slope_lines_org_hor=slope_lines_org[slope_lines==0] slope_lines_org_hor=slope_lines_org[slope_lines==0]
args=np.array( range(len(slope_lines) )) args=np.array( range(len(slope_lines) ))
len_x=seperators_closeup.shape[1]/5.0 len_x=separators_closeup.shape[1]/5.0
dist_y=np.abs(y_max_main-y_min_main) dist_y=np.abs(y_max_main-y_min_main)
@ -1551,7 +1551,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
cy_main_splitters=cy_main_hor[ (x_min_main_hor<=.16*region_pre_p.shape[1]) & (x_max_main_hor>=.84*region_pre_p.shape[1] )] cy_main_splitters=cy_main_hor[ (x_min_main_hor<=.16*region_pre_p.shape[1]) & (x_max_main_hor>=.84*region_pre_p.shape[1] )]
cy_main_splitters=np.array( list(cy_main_splitters)+list(special_seperators)) cy_main_splitters=np.array( list(cy_main_splitters)+list(special_separators))
if contours_h is not None: if contours_h is not None:
try: try:
@ -1576,10 +1576,10 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
regions_without_seperators=return_regions_without_seperators(region_pre_p) regions_without_separators=return_regions_without_separators(region_pre_p)
length_y_threshold=regions_without_seperators.shape[0]/4.0 length_y_threshold=regions_without_separators.shape[0]/4.0
num_col_fin=0 num_col_fin=0
peaks_neg_fin_fin=[] peaks_neg_fin_fin=[]
@ -1587,18 +1587,18 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
for itiles in args_big_parts: for itiles in args_big_parts:
regions_without_seperators_tile=regions_without_seperators[int(splitter_y_new[iteils]):int(splitter_y_new[iteils+1]),:,0] regions_without_separators_tile=regions_without_separators[int(splitter_y_new[iteils]):int(splitter_y_new[iteils+1]),:,0]
#image_page_background_zero_tile=image_page_background_zero[int(splitter_y_new[iteils]):int(splitter_y_new[iteils+1]),:] #image_page_background_zero_tile=image_page_background_zero[int(splitter_y_new[iteils]):int(splitter_y_new[iteils+1]),:]
#print(regions_without_seperators_tile.shape) #print(regions_without_separators_tile.shape)
##plt.imshow(regions_without_seperators_tile) ##plt.imshow(regions_without_separators_tile)
##plt.show() ##plt.show()
#num_col, peaks_neg_fin=self.find_num_col(regions_without_seperators_tile,multiplier=6.0) #num_col, peaks_neg_fin=self.find_num_col(regions_without_separators_tile,multiplier=6.0)
#regions_without_seperators_tile=cv2.erode(regions_without_seperators_teil,kernel,iterations = 3) #regions_without_separators_tile=cv2.erode(regions_without_separators_teil,kernel,iterations = 3)
# #
num_col, peaks_neg_fin=find_num_col(regions_without_seperators_tile,multiplier=7.0) num_col, peaks_neg_fin=find_num_col(regions_without_separators_tile,multiplier=7.0)
if num_col>num_col_fin: if num_col>num_col_fin:
num_col_fin=num_col num_col_fin=num_col
@ -1614,10 +1614,10 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
#print(peaks_neg_fin_fin,'peaks_neg_fin_fintaza') #print(peaks_neg_fin_fin,'peaks_neg_fin_fintaza')
return num_col_fin, peaks_neg_fin_fin,matrix_of_lines_ch,splitter_y_new,seperators_closeup_n return num_col_fin, peaks_neg_fin_fin,matrix_of_lines_ch,splitter_y_new,separators_closeup_n
def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_without_seperators, matrix_of_lines_ch, num_col_classifier): def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_without_separators, matrix_of_lines_ch, num_col_classifier):
boxes=[] boxes=[]
@ -1628,11 +1628,11 @@ def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_witho
#print(matrix_new[:,8][matrix_new[:,9]==1],'gaddaaa') #print(matrix_new[:,8][matrix_new[:,9]==1],'gaddaaa')
# check to see is there any vertical seperator to find holes. # check to see is there any vertical separator to find holes.
if 1>0:#len( matrix_new[:,9][matrix_new[:,9]==1] )>0 and np.max(matrix_new[:,8][matrix_new[:,9]==1])>=0.1*(np.abs(splitter_y_new[i+1]-splitter_y_new[i] )): if 1>0:#len( matrix_new[:,9][matrix_new[:,9]==1] )>0 and np.max(matrix_new[:,8][matrix_new[:,9]==1])>=0.1*(np.abs(splitter_y_new[i+1]-splitter_y_new[i] )):
try: try:
num_col, peaks_neg_fin=find_num_col(regions_without_seperators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:],multiplier=7.) num_col, peaks_neg_fin=find_num_col(regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:],multiplier=7.)
except: except:
peaks_neg_fin=[] peaks_neg_fin=[]
@ -1644,28 +1644,28 @@ def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_witho
#print('burda') #print('burda')
if len(peaks_neg_fin)==0: if len(peaks_neg_fin)==0:
num_col, peaks_neg_fin=find_num_col(regions_without_seperators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:],multiplier=3.) num_col, peaks_neg_fin=find_num_col(regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:],multiplier=3.)
peaks_neg_fin_early=[] peaks_neg_fin_early=[]
peaks_neg_fin_early.append(0) peaks_neg_fin_early.append(0)
#print(peaks_neg_fin,'peaks_neg_fin') #print(peaks_neg_fin,'peaks_neg_fin')
for p_n in peaks_neg_fin: for p_n in peaks_neg_fin:
peaks_neg_fin_early.append(p_n) peaks_neg_fin_early.append(p_n)
peaks_neg_fin_early.append(regions_without_seperators.shape[1]-1) peaks_neg_fin_early.append(regions_without_separators.shape[1]-1)
#print(peaks_neg_fin_early,'burda2') #print(peaks_neg_fin_early,'burda2')
peaks_neg_fin_rev=[] peaks_neg_fin_rev=[]
for i_n in range(len(peaks_neg_fin_early)-1): for i_n in range(len(peaks_neg_fin_early)-1):
#print(i_n,'i_n') #print(i_n,'i_n')
#plt.plot(regions_without_seperators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),peaks_neg_fin_early[i_n]:peaks_neg_fin_early[i_n+1]].sum(axis=0) ) #plt.plot(regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),peaks_neg_fin_early[i_n]:peaks_neg_fin_early[i_n+1]].sum(axis=0) )
#plt.show() #plt.show()
try: try:
num_col, peaks_neg_fin1=find_num_col(regions_without_seperators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),peaks_neg_fin_early[i_n]:peaks_neg_fin_early[i_n+1]],multiplier=7.) num_col, peaks_neg_fin1=find_num_col(regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),peaks_neg_fin_early[i_n]:peaks_neg_fin_early[i_n+1]],multiplier=7.)
except: except:
peaks_neg_fin1=[] peaks_neg_fin1=[]
try: try:
num_col, peaks_neg_fin2=find_num_col(regions_without_seperators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),peaks_neg_fin_early[i_n]:peaks_neg_fin_early[i_n+1]],multiplier=5.) num_col, peaks_neg_fin2=find_num_col(regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),peaks_neg_fin_early[i_n]:peaks_neg_fin_early[i_n+1]],multiplier=5.)
except: except:
peaks_neg_fin2=[] peaks_neg_fin2=[]
@ -1698,7 +1698,7 @@ def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_witho
#print(peaks_neg_fin,'peaks_neg_fin') #print(peaks_neg_fin,'peaks_neg_fin')
except: except:
pass pass
#num_col, peaks_neg_fin=find_num_col(regions_without_seperators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:],multiplier=7.0) #num_col, peaks_neg_fin=find_num_col(regions_without_separators[int(splitter_y_new[i]):int(splitter_y_new[i+1]),:],multiplier=7.0)
x_min_hor_some=matrix_new[:,2][ (matrix_new[:,9]==0) ] x_min_hor_some=matrix_new[:,2][ (matrix_new[:,9]==0) ]
x_max_hor_some=matrix_new[:,3][ (matrix_new[:,9]==0) ] x_max_hor_some=matrix_new[:,3][ (matrix_new[:,9]==0) ]
cy_hor_some=matrix_new[:,5][ (matrix_new[:,9]==0) ] cy_hor_some=matrix_new[:,5][ (matrix_new[:,9]==0) ]
@ -1709,7 +1709,7 @@ def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_witho
peaks_neg_tot=return_points_with_boundies(peaks_neg_fin,0, regions_without_seperators[:,:].shape[1]) peaks_neg_tot=return_points_with_boundies(peaks_neg_fin,0, regions_without_separators[:,:].shape[1])
reading_order_type,x_starting,x_ending,y_type_2,y_diff_type_2,y_lines_without_mother,x_start_without_mother,x_end_without_mother,there_is_sep_with_child,y_lines_with_child_without_mother,x_start_with_child_without_mother,x_end_with_child_without_mother=return_x_start_end_mothers_childs_and_type_of_reading_order(x_min_hor_some,x_max_hor_some,cy_hor_some,peaks_neg_tot,cy_hor_diff) reading_order_type,x_starting,x_ending,y_type_2,y_diff_type_2,y_lines_without_mother,x_start_without_mother,x_end_without_mother,there_is_sep_with_child,y_lines_with_child_without_mother,x_start_with_child_without_mother,x_end_with_child_without_mother=return_x_start_end_mothers_childs_and_type_of_reading_order(x_min_hor_some,x_max_hor_some,cy_hor_some,peaks_neg_tot,cy_hor_diff)
@ -2263,6 +2263,6 @@ def return_boxes_of_images_by_order_of_reading_new(splitter_y_new, regions_witho
#else: #else:
#boxes.append([ 0, regions_without_seperators[:,:].shape[1] ,splitter_y_new[i],splitter_y_new[i+1]]) #boxes.append([ 0, regions_without_separators[:,:].shape[1] ,splitter_y_new[i],splitter_y_new[i+1]])
return boxes return boxes

Write Preview
Loading…
Cancel
Save