From eb64cc030f255e3da1d7bae6933a4f7cad2fff6c Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Thu, 5 Dec 2019 22:01:47 +0100 Subject: [PATCH 01/18] Create LICENSE --- LICENSE | 201 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 201 insertions(+) create mode 100644 LICENSE diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..261eeb9 --- /dev/null +++ b/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. From b22a81297998ced8234120755899f099f52f402d Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Thu, 5 Dec 2019 22:06:44 +0100 Subject: [PATCH 02/18] Improve README.md --- README.md | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-) diff --git a/README.md b/README.md index d3da05f..b9317bb 100644 --- a/README.md +++ b/README.md @@ -1,24 +1,17 @@ # Textline-Recognition *** -# Tool -This tool does textline detection of image and throw result as xml data. - -# Models -In order to run this tool you need corresponding models. You can find them here: - -https://file.spk-berlin.de:8443/textline_detection/ +# Introduction +This tool performs textline detection from image data and returns the results as PAGE-XML. # Installation -sudo pip install . - -# Usage - -sbb_textline_detector -i 'image file name' -o 'directory to write output xml' -m 'directory of models' - - - +`sudo pip install .` +# Models +In order to run this tool you also need trained models. You can download them here: +https://file.spk-berlin.de:8443/textline_detection/ +# Usage +`sbb_textline_detector -i -o -m ` From 58f5d2b3c598153cc789e856d1c5ae92f1c62a11 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Thu, 5 Dec 2019 22:11:16 +0100 Subject: [PATCH 03/18] Update requirements.txt --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 42de57a..b6b8cfa 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,4 @@ -opencv-python +opencv-python-headless numpy matplotlib seaborn From d90dad48fdf4dde7138441ad50d7fbbb44f964d1 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Thu, 5 Dec 2019 22:24:28 +0100 Subject: [PATCH 04/18] PAGE2019 --- qurator/sbb_textline_detector/main.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qurator/sbb_textline_detector/main.py b/qurator/sbb_textline_detector/main.py index e70e475..00181a7 100644 --- a/qurator/sbb_textline_detector/main.py +++ b/qurator/sbb_textline_detector/main.py @@ -1236,9 +1236,9 @@ class textlineerkenner: # create the file structure data = ET.Element('PcGts') - data.set('xmlns',"http://schema.primaresearch.org/PAGE/gts/pagecontent/2017-07-15") + data.set('xmlns',"http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15") data.set('xmlns:xsi',"http://www.w3.org/2001/XMLSchema-instance") - data.set('xsi:schemaLocation',"http://schema.primaresearch.org/PAGE/gts/pagecontent/2017-07-15") + data.set('xsi:schemaLocation',"http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15") From e696a068cb5f7ba8425f57ef1790dd19abc80b7e Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 00:20:34 +0100 Subject: [PATCH 05/18] Fix typos --- qurator/sbb_textline_detector/main.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/qurator/sbb_textline_detector/main.py b/qurator/sbb_textline_detector/main.py index e70e475..249bf1b 100644 --- a/qurator/sbb_textline_detector/main.py +++ b/qurator/sbb_textline_detector/main.py @@ -70,7 +70,7 @@ class textlineerkenner: np.array([point for point in polygon.exterior.coords], dtype=np.uint)) return found_polygons_early - def filter_contours_area_of_image(self, image, contours, hirarchy, max_area, min_area): + def filter_contours_area_of_image(self, image, contours, hierarchy, max_area, min_area): found_polygons_early = list() jv = 0 @@ -81,13 +81,13 @@ class textlineerkenner: polygon = geometry.Polygon([point[0] for point in c]) area = polygon.area if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod( - image.shape[:2]) and hirarchy[0][jv][3] == -1 : # and hirarchy[0][jv][3]==-1 : + image.shape[:2]) and hierarchy[0][jv][3] == -1 : # and hierarchy[0][jv][3]==-1 : found_polygons_early.append( np.array([ [point] for point in polygon.exterior.coords], dtype=np.uint)) jv += 1 return found_polygons_early - def filter_contours_area_of_image_interiors(self, image, contours, hirarchy, max_area, min_area): + def filter_contours_area_of_image_interiors(self, image, contours, hierarchy, max_area, min_area): found_polygons_early = list() jv = 0 @@ -98,7 +98,7 @@ class textlineerkenner: polygon = geometry.Polygon([point[0] for point in c]) area = polygon.area if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]) and \ - hirarchy[0][jv][3] != -1: + hierarchy[0][jv][3] != -1: # print(c[0][0][1]) found_polygons_early.append( np.array([point for point in polygon.exterior.coords], dtype=np.uint)) @@ -486,9 +486,9 @@ class textlineerkenner: _, thresh = cv2.threshold(imgray, 0, 255, 0) - contours, hirarchy = cv2.findContours(thresh.copy(), cv2.cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) + contours, hierarchy = cv2.findContours(thresh.copy(), cv2.cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) - main_contours = self.filter_contours_area_of_image(thresh, contours, hirarchy, max_area=1, min_area=0.00001) + main_contours = self.filter_contours_area_of_image(thresh, contours, hierarchy, max_area=1, min_area=0.00001) self.boxes = [] for jj in range(len(main_contours)): From 2ecb0218701051e68d661eaa55acbcd62ffe4764 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 00:35:11 +0100 Subject: [PATCH 06/18] refactor class name --- qurator/sbb_textline_detector/main.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qurator/sbb_textline_detector/main.py b/qurator/sbb_textline_detector/main.py index e70e475..245b70b 100644 --- a/qurator/sbb_textline_detector/main.py +++ b/qurator/sbb_textline_detector/main.py @@ -38,7 +38,7 @@ __doc__ = \ """ -class textlineerkenner: +class textline_detector: def __init__(self, image_dir, dir_out, f_name, dir_models): self.image_dir = image_dir # XXX This does not seem to be a directory as the name suggests, but a file self.dir_out = dir_out @@ -1475,7 +1475,7 @@ class textlineerkenner: def main(image, out, model): possibles = globals() # XXX unused? possibles.update(locals()) - x = textlineerkenner(image, out, None, model) + x = textline_detector(image, out, None, model) x.run() From c8bc46862817493258ec24d39c8e5ccd098c6617 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 00:40:05 +0100 Subject: [PATCH 07/18] fix docstring --- qurator/sbb_textline_detector/main.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qurator/sbb_textline_detector/main.py b/qurator/sbb_textline_detector/main.py index e70e475..5b2473f 100644 --- a/qurator/sbb_textline_detector/main.py +++ b/qurator/sbb_textline_detector/main.py @@ -34,7 +34,7 @@ with warnings.catch_warnings(): __doc__ = \ """ - tool to extract table form data from alto xml data + tool to extract text lines from document images """ From 02388a759dbe9f05b81189ecf46a27967ff9dc80 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 00:47:53 +0100 Subject: [PATCH 08/18] Update README.md --- README.md | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index b9317bb..162d471 100644 --- a/README.md +++ b/README.md @@ -1,17 +1,16 @@ # Textline-Recognition -*** -# Introduction -This tool performs textline detection from image data and returns the results as PAGE-XML. +## Introduction +This tool performs textline detection from document image data and returns the results as PAGE-XML. -# Installation +## Installation `sudo pip install .` -# Models -In order to run this tool you also need trained models. You can download them here: +## Models +In order to run this tool you also need trained models. You can download our pre-trained models from here: https://file.spk-berlin.de:8443/textline_detection/ -# Usage +## Usage `sbb_textline_detector -i -o -m ` From 5113d28e13b7be21089b9f4c5553d4e7b757bc50 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 00:48:38 +0100 Subject: [PATCH 09/18] do not require sudo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 162d471..729ab12 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,7 @@ This tool performs textline detection from document image data and returns the r ## Installation -`sudo pip install .` +`pip install .` ## Models In order to run this tool you also need trained models. You can download our pre-trained models from here: From 6c0bfba686c49da2e78a020e0b80c384413ab397 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 02:21:04 +0100 Subject: [PATCH 10/18] fix typos --- qurator/sbb_textline_detector/main.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qurator/sbb_textline_detector/main.py b/qurator/sbb_textline_detector/main.py index 249bf1b..3813bda 100644 --- a/qurator/sbb_textline_detector/main.py +++ b/qurator/sbb_textline_detector/main.py @@ -1378,7 +1378,7 @@ class textlineerkenner: def run(self): - #get image and sclaes, then extract the page of scanned image + #get image and scales, then extract the page of scanned image t1=time.time() self.get_image_and_scales() image_page,page_coord=self.extract_page() From 3b526ef40d9c4d01a61a83cce44ae6011818df5d Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 02:27:23 +0100 Subject: [PATCH 11/18] refactor class name --- qurator/sbb_textline_detector/ocrd_cli.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qurator/sbb_textline_detector/ocrd_cli.py b/qurator/sbb_textline_detector/ocrd_cli.py index d090e46..272d671 100644 --- a/qurator/sbb_textline_detector/ocrd_cli.py +++ b/qurator/sbb_textline_detector/ocrd_cli.py @@ -12,7 +12,7 @@ from ocrd_models.ocrd_page_generateds import MetadataItemType, LabelsType, Label from ocrd_utils import concat_padded, getLogger, MIMETYPE_PAGE from pkg_resources import resource_string -from qurator.sbb_textline_detector import textlineerkenner +from qurator.sbb_textline_detector import textline_detector log = getLogger('processor.OcrdSbbTextlineDetectorRecognize') @@ -67,7 +67,7 @@ class OcrdSbbTextlineDetectorRecognize(Processor): # Segment the image image_file = self._resolve_image_file(input_file) model = self.parameter['model'] - x = textlineerkenner(image_file, tmp_dirname, file_id, model) + x = textline_detector(image_file, tmp_dirname, file_id, model) x.run() # Read segmentation results From 3935204338fb977ba4429b7af93817c4006cc827 Mon Sep 17 00:00:00 2001 From: "Gerber, Mike" Date: Fri, 6 Dec 2019 11:42:23 +0100 Subject: [PATCH 12/18] =?UTF-8?q?=F0=9F=93=9D=20sbb=5Ftextline=5Fdetector:?= =?UTF-8?q?=20Document=20OCR-D=20Usage?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- README.md | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index d3da05f..a8905be 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,14 @@ sudo pip install . sbb_textline_detector -i 'image file name' -o 'directory to write output xml' -m 'directory of models' - - - - +## Usage with OCR-D +~~~ +ocrd-example-binarize -I OCR-D-IMG -O OCR-D-IMG-BIN +ocrd_sbb_textline_detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB -p '{ "model": "/path/to/the/models/textline_detection" }' +~~~ + +Segmentation works on raw RGB images, but respects and retains +`AlternativeImage`s from binarization steps, so it's a good idea to do +binarization first, then perform the textline detection. The used binarization +processor must produce an `AlternativeImage` for the binarized image, not +replace the original raw RGB image. From eb4c8ee99c68a948cbfdd05d6d4ce3280b21b7c0 Mon Sep 17 00:00:00 2001 From: "Gerber, Mike" Date: Fri, 6 Dec 2019 12:34:15 +0100 Subject: [PATCH 13/18] =?UTF-8?q?=F0=9F=93=9D=20sbb=5Ftextline=5Fdetector:?= =?UTF-8?q?=20Break=20long=20line=20for=20ocrd=5Fsbb=5Ftextline=5Fdetector?= =?UTF-8?q?=20example?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index a8905be..e7b28fd 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,8 @@ sbb_textline_detector -i 'image file name' -o 'directory to write output xml' -m ## Usage with OCR-D ~~~ ocrd-example-binarize -I OCR-D-IMG -O OCR-D-IMG-BIN -ocrd_sbb_textline_detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB -p '{ "model": "/path/to/the/models/textline_detection" }' +ocrd_sbb_textline_detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB \ + -p '{ "model": "/path/to/the/models/textline_detection" }' ~~~ Segmentation works on raw RGB images, but respects and retains From b6ca1a7c5368e8611a90709f3e1813846f1fa0eb Mon Sep 17 00:00:00 2001 From: Konstantin Baierer Date: Fri, 6 Dec 2019 18:21:00 +0100 Subject: [PATCH 14/18] kebab-case snake_case executable, fix #9 --- .gitignore | 2 ++ qurator/sbb_textline_detector/ocrd-tool.json | 4 ++-- setup.py | 2 +- 3 files changed, 5 insertions(+), 3 deletions(-) create mode 100644 .gitignore diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..3fafd07 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +__pycache__ +*.egg-info diff --git a/qurator/sbb_textline_detector/ocrd-tool.json b/qurator/sbb_textline_detector/ocrd-tool.json index b76f439..241f551 100644 --- a/qurator/sbb_textline_detector/ocrd-tool.json +++ b/qurator/sbb_textline_detector/ocrd-tool.json @@ -1,8 +1,8 @@ { "version": "0.0.1", "tools": { - "ocrd_sbb_textline_detector": { - "executable": "ocrd_sbb_textline_detector", + "ocrd-sbb-textline-detector": { + "executable": "ocrd-sbb-textline-detector", "description": "Detect lines", "steps": ["layout/segmentation/line"], "input_file_grp": [ diff --git a/setup.py b/setup.py index 1c9075f..92c88cf 100644 --- a/setup.py +++ b/setup.py @@ -24,7 +24,7 @@ setup( entry_points={ 'console_scripts': [ "sbb_textline_detector=qurator.sbb_textline_detector:main", - "ocrd_sbb_textline_detector=qurator.sbb_textline_detector:ocrd_sbb_textline_detector", + "ocrd-sbb-textline-detector=qurator.sbb_textline_detector:ocrd_sbb_textline_detector", ] }, python_requires='>=3.6.0', From 7c7f035b69bb4bf273e60bd0d3663bb2ea425384 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 19:02:50 +0100 Subject: [PATCH 15/18] matplotlib implies numpy --- requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index b6b8cfa..e915936 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,4 @@ opencv-python-headless -numpy matplotlib seaborn tqdm From 9b784e3a81062231899c88d3bb1fd9a5b703871b Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 19:03:10 +0100 Subject: [PATCH 16/18] ocrd implies click --- requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index e915936..9240226 100644 --- a/requirements.txt +++ b/requirements.txt @@ -7,5 +7,4 @@ shapely scikit-learn tensorflow-gpu < 2.0 scipy -click ocrd >= 2.0.0 From be7b101f39dff67f20bbee97046eabc54b83d336 Mon Sep 17 00:00:00 2001 From: Clemens Neudecker <952378+cneud@users.noreply.github.com> Date: Fri, 6 Dec 2019 20:06:43 +0100 Subject: [PATCH 17/18] Update README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index bf1fd89..46a8295 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# Textline-Recognition +# Textline Detection ## Introduction This tool performs textline detection from document image data and returns the results as PAGE-XML. @@ -19,7 +19,7 @@ https://file.spk-berlin.de:8443/textline_detection/ ~~~ ocrd-example-binarize -I OCR-D-IMG -O OCR-D-IMG-BIN -ocrd_sbb_textline_detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB \ +ocrd-sbb-textline-detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB \ -p '{ "model": "/path/to/the/models/textline_detection" }' ~~~ @@ -27,4 +27,4 @@ Segmentation works on raw RGB images, but respects and retains `AlternativeImage`s from binarization steps, so it's a good idea to do binarization first, then perform the textline detection. The used binarization processor must produce an `AlternativeImage` for the binarized image, not -replace the original raw RGB image. \ No newline at end of file +replace the original raw RGB image. From ea3e7737acaa35e8adbffcac35deb39691eb7ded Mon Sep 17 00:00:00 2001 From: Stefan Weil Date: Fri, 6 Dec 2019 23:42:51 +0100 Subject: [PATCH 18/18] Fix more typos (found by codespell) Signed-off-by: Stefan Weil --- qurator/sbb_textline_detector/main.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qurator/sbb_textline_detector/main.py b/qurator/sbb_textline_detector/main.py index 18aeaa5..6f6c516 100644 --- a/qurator/sbb_textline_detector/main.py +++ b/qurator/sbb_textline_detector/main.py @@ -916,8 +916,8 @@ class textlineerkenner: image_box_tabels=image_box_tabels.astype(np.uint8) imgray = cv2.cvtColor(image_box_tabels, cv2.COLOR_BGR2GRAY) ret, thresh = cv2.threshold(imgray, 0, 255, 0) - contours,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) - return contours,hierachy + contours,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) + return contours,hierarchy def find_contours_mean_y_diff(self,contours_main): M_main=[cv2.moments(contours_main[j]) for j in range(len(contours_main))]