From c80fddb3b80cee5208b9657afb90fbf5090e55c6 Mon Sep 17 00:00:00 2001 From: Konstantin Baierer Date: Wed, 24 Feb 2021 15:23:55 +0100 Subject: [PATCH] remove unused delete_seperator_around --- sbb_newspapers_org_image/eynollah.py | 10 ++++------ sbb_newspapers_org_image/unused.py | 20 ++++++++++++++++++++ sbb_newspapers_org_image/utils/__init__.py | 22 ---------------------- 3 files changed, 24 insertions(+), 28 deletions(-) diff --git a/sbb_newspapers_org_image/eynollah.py b/sbb_newspapers_org_image/eynollah.py index 0a80342..7d32c14 100644 --- a/sbb_newspapers_org_image/eynollah.py +++ b/sbb_newspapers_org_image/eynollah.py @@ -1,6 +1,6 @@ # pylint: disable=no-member,invalid-name,line-too-long,missing-function-docstring -# pylint: disable=too-many-locals,wrong-import-position,too-many-lines -# pylint: disable=too-many-public-methods +# pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements +# pylint: disable=too-many-public-methods,too-many-arguments,too-many-instance-attributes,too-many-public-methods, """ tool to extract table form data from alto xml data """ @@ -67,8 +67,6 @@ from .utils import ( crop_image_inside_box, find_num_col, otsu_copy_binary, - delete_seperator_around, - return_regions_without_seperators, put_drop_out_from_only_drop_model, putt_bb_of_drop_capitals_of_model_in_patches_in_layout, check_any_text_region_in_model_one_is_main_or_header, @@ -107,7 +105,7 @@ class eynollah: allow_scaling=False, headers_off=False ): - self.image_filename = image_filename # XXX This does not seem to be a directory as the name suggests, but a file + self.image_filename = image_filename self.cont_page = [] self.dir_out = dir_out self.image_filename_stem = image_filename_stem @@ -137,7 +135,7 @@ class eynollah: self.model_region_dir_fully = dir_models + "/model_3up_new_good_no_augmentation.h5" self.model_page_dir = dir_models + "/model_page_mixed_best.h5" self.model_region_dir_p_ens = dir_models + "/model_ensemble_s.h5" - self.model_textline_dir = dir_models + "/model_textline_newspapers.h5" + self.model_textline_dir = dir_models + "/model_textline_newspapers.h5" self._imgs = {} diff --git a/sbb_newspapers_org_image/unused.py b/sbb_newspapers_org_image/unused.py index d61af37..e3514b8 100644 --- a/sbb_newspapers_org_image/unused.py +++ b/sbb_newspapers_org_image/unused.py @@ -3344,4 +3344,24 @@ def implent_law_head_main_not_parallel(text_regions): return text_regions +def delete_seperator_around(spliter_y, peaks_neg, image_by_region): + # format of subboxes box=[x1, x2 , y1, y2] + + if len(image_by_region.shape) == 3: + for i in range(len(spliter_y) - 1): + for j in range(1, len(peaks_neg[i]) - 1): + image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0] == 6] = 0 + image_by_region[spliter_y[i] : spliter_y[i + 1], peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 1] == 6] = 0 + image_by_region[spliter_y[i] : spliter_y[i + 1], peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 2] == 6] = 0 + + image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0] == 7] = 0 + image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 1] == 7] = 0 + image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 2] == 7] = 0 + else: + for i in range(len(spliter_y) - 1): + for j in range(1, len(peaks_neg[i]) - 1): + image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])] == 6] = 0 + + image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])] == 7] = 0 + return image_by_region diff --git a/sbb_newspapers_org_image/utils/__init__.py b/sbb_newspapers_org_image/utils/__init__.py index a3f7686..120dfc5 100644 --- a/sbb_newspapers_org_image/utils/__init__.py +++ b/sbb_newspapers_org_image/utils/__init__.py @@ -718,28 +718,6 @@ def find_num_col_by_vertical_lines(regions_without_seperators, multiplier=3.8): # print(peaks,'peaksnew') return peaks - -def delete_seperator_around(spliter_y, peaks_neg, image_by_region): - # format of subboxes box=[x1, x2 , y1, y2] - - if len(image_by_region.shape) == 3: - for i in range(len(spliter_y) - 1): - for j in range(1, len(peaks_neg[i]) - 1): - image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0] == 6] = 0 - image_by_region[spliter_y[i] : spliter_y[i + 1], peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 1] == 6] = 0 - image_by_region[spliter_y[i] : spliter_y[i + 1], peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 2] == 6] = 0 - - image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0] == 7] = 0 - image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 1] == 7] = 0 - image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 0][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j]), 2] == 7] = 0 - else: - for i in range(len(spliter_y) - 1): - for j in range(1, len(peaks_neg[i]) - 1): - image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])] == 6] = 0 - - image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])][image_by_region[int(spliter_y[i]) : int(spliter_y[i + 1]), peaks_neg[i][j] - int(1.0 / 20.0 * peaks_neg[i][j]) : peaks_neg[i][j] + int(1.0 / 20.0 * peaks_neg[i][j])] == 7] = 0 - return image_by_region - def return_regions_without_seperators(regions_pre): kernel = np.ones((5, 5), np.uint8) regions_without_seperators = ((regions_pre[:, :] != 6) & (regions_pre[:, :] != 0)) * 1