more outfactoring run code to methods

pull/19/head
Konstantin Baierer 4 years ago
parent b06acbf754
commit 420a9ca252

@ -2212,16 +2212,7 @@ class eynollah:
self.logger.info("slope_deskew: %s", slope_deskew)
return slope_deskew, slope_first
def run_marginals(
self,
image_page,
textline_mask_tot_ea,
mask_images,
mask_lines,
num_col_classifier,
slope_deskew,
text_regions_p_1
):
def run_marginals(self, image_page, textline_mask_tot_ea, mask_images, mask_lines, num_col_classifier, slope_deskew, text_regions_p_1):
image_page_rotated, textline_mask_tot = image_page[:, :], textline_mask_tot_ea[:, :]
textline_mask_tot[mask_images[:, :] == 1] = 0
@ -2249,47 +2240,8 @@ class eynollah:
self.plotter.save_plot_of_layout_main(text_regions_p, image_page)
return textline_mask_tot, text_regions_p, image_page_rotated
def run(self):
"""
Get image and scales, then extract the page of scanned image
"""
self.logger.debug("enter run")
is_image_enhanced = False
t1 = time.time()
img_res, is_image_enhanced, num_column_is_classified = self.run_enhancement()
self.logger.info("Enhancing took %ss ", str(time.time() - t1))
t1 = time.time()
text_regions_p_1 = self.get_regions_from_xy_2models(img_res, is_image_enhanced)
self.logger.info("Textregion detection took %ss ", str(time.time() - t1))
t1 = time.time()
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines = \
self.run_graphics_and_columns(text_regions_p_1, num_column_is_classified)
self.logger.info("Graphics detection took %ss ", str(time.time() - t1))
if not num_col:
self.logger.info("No columns detected, outputting an empty PAGE-XML")
self.write_into_page_xml([], page_coord, self.dir_out, [], [], [], [], [], [], [], [], self.curved_line, [], [])
self.logger.info("Job done in %ss", str(time.time() - t1))
return
t1 = time.time()
textline_mask_tot_ea, textline_mask_tot_long_shot = self.run_textline(image_page)
self.logger.info("textline detection took %ss", str(time.time() - t1))
t1 = time.time()
slope_deskew, slope_first = self.run_deskew(textline_mask_tot_ea)
self.logger.info("deskewing took %ss", str(time.time() - t1))
t1 = time.time()
textline_mask_tot, text_regions_p, image_page_rotated = self.run_marginals(image_page, textline_mask_tot_ea, mask_images, mask_lines, num_col_classifier, slope_deskew, text_regions_p_1)
self.logger.info("detection of marginals took %ss", str(time.time() - t1))
t1 = time.time()
if not self.full_layout:
def run_boxes_no_full_layout(self, image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier):
self.logger.debug('enter run_boxes_no_full_layout')
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
image_page_rotated_n, 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])
@ -2325,27 +2277,24 @@ class eynollah:
#regions_without_seperators_d[(random_pixels_for_image[:, :] == 1) & (text_regions_p_1_n[:, :] == 2)] = 1
t1 = time.time()
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
boxes = return_boxes_of_images_by_order_of_reading_new(spliter_y_new, regions_without_seperators, matrix_of_lines_ch, num_col_classifier)
else:
boxes_d = return_boxes_of_images_by_order_of_reading_new(spliter_y_new_d, regions_without_seperators_d, matrix_of_lines_ch_d, num_col_classifier)
self.logger.debug("len(boxes): %s", len(boxes))
self.logger.info("detecting boxes took %ss", str(time.time() - t1))
t1 = time.time()
img_revised_tab = text_regions_p[:, :]
pixel_img = 2
polygons_of_images = return_contours_of_interested_region(img_revised_tab, pixel_img)
polygons_of_images = return_contours_of_interested_region(img_revised_tab, 2)
# plt.imshow(img_revised_tab)
# plt.show()
K.clear_session()
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
pixel_img = 4
min_area_mar = 0.00001
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
if self.full_layout:
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')
# set first model with second model
text_regions_p[:, :][text_regions_p[:, :] == 2] = 5
text_regions_p[:, :][text_regions_p[:, :] == 3] = 6
@ -2417,11 +2366,58 @@ class eynollah:
K.clear_session()
gc.collect()
img_revised_tab = np.copy(text_regions_p[:, :])
self.logger.info("detection of full layout took %ss", str(time.time() - t1))
t1 = time.time()
pixel_img = 5
polygons_of_images = return_contours_of_interested_region(img_revised_tab, pixel_img)
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
def run(self):
"""
Get image and scales, then extract the page of scanned image
"""
self.logger.debug("enter run")
t1 = time.time()
img_res, is_image_enhanced, num_column_is_classified = self.run_enhancement()
self.logger.info("Enhancing took %ss ", str(time.time() - t1))
t1 = time.time()
text_regions_p_1 = self.get_regions_from_xy_2models(img_res, is_image_enhanced)
self.logger.info("Textregion detection took %ss ", str(time.time() - t1))
t1 = time.time()
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines = \
self.run_graphics_and_columns(text_regions_p_1, num_column_is_classified)
self.logger.info("Graphics detection took %ss ", str(time.time() - t1))
if not num_col:
self.logger.info("No columns detected, outputting an empty PAGE-XML")
self.write_into_page_xml([], page_coord, self.dir_out, [], [], [], [], [], [], [], [], self.curved_line, [], [])
self.logger.info("Job done in %ss", str(time.time() - t1))
return
t1 = time.time()
textline_mask_tot_ea, textline_mask_tot_long_shot = self.run_textline(image_page)
self.logger.info("textline detection took %ss", str(time.time() - t1))
t1 = time.time()
slope_deskew, slope_first = self.run_deskew(textline_mask_tot_ea)
self.logger.info("deskewing took %ss", str(time.time() - t1))
t1 = time.time()
textline_mask_tot, text_regions_p, image_page_rotated = self.run_marginals(image_page, textline_mask_tot_ea, mask_images, mask_lines, num_col_classifier, slope_deskew, text_regions_p_1)
self.logger.info("detection of marginals took %ss", str(time.time() - t1))
t1 = time.time()
if not self.full_layout:
polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d, regions_without_seperators_d = self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier)
pixel_img = 4
min_area_mar = 0.00001
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
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 = self.run_boxes_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew, num_col_classifier, img_only_regions)
# plt.imshow(img_revised_tab)
# plt.show()

Loading…
Cancel
Save