Merge branch 'refs/heads/main' into extracting_images_only

# Conflicts:
#	src/eynollah/eynollah.py

.circleci/config.yml

@@ -1,51 +0,0 @@
-version: 2
-
-jobs:
-
-  build-python37:
-    machine:
-      - image: ubuntu-2004:2023.02.1
-
-    steps:
-      - checkout
-      - restore_cache:
-          keys:
-            - model-cache
-      - run: make models
-      - save_cache:
-          key: model-cache
-          paths:
-            models_eynollah.tar.gz
-            models_eynollah
-      - run:
-          name: "Set Python Version"
-          command: pyenv install -s 3.7.16 && pyenv global 3.7.16
-      - run: make install
-      - run: make smoke-test
-
-  build-python38:
-    machine:
-      - image: ubuntu-2004:2023.02.1
-    steps:
-      - checkout
-      - restore_cache:
-          keys:
-            - model-cache
-      - run: make models
-      - save_cache:
-          key: model-cache
-          paths:
-            models_eynollah.tar.gz
-            models_eynollah
-      - run:
-          name: "Set Python Version"
-          command: pyenv install -s 3.8.16 && pyenv global 3.8.16           
-      - run: make install
-      - run: make smoke-test
-
-workflows:
-  version: 2
-  build:
-    jobs:
-      # - build-python37
-      - build-python38

.github/workflows/test-eynollah.yml

@@ -1,7 +1,7 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
 
-name: Python package
+name: Test
 
 on: [push]
 
@@ -14,8 +14,8 @@ jobs:
         python-version: ['3.8', '3.9', '3.10', '3.11']
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
-    - uses: actions/cache@v2
+    - uses: actions/cache@v4
       id: model_cache
       with:
         path: models_eynollah
@@ -24,7 +24,7 @@ jobs:
       if: steps.model_cache.outputs.cache-hit != 'true'
       run: make models
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

CHANGELOG.md

@@ -5,6 +5,14 @@ Versioned according to [Semantic Versioning](http://semver.org/).
 
 ## Unreleased
 
+## [0.3.1] - 2024-08-27
+
+Fixed:
+
+  * regression in OCR-D processor, #106
+  * Expected Ptrcv::UMat for argument 'contour', #110
+  * Memory usage explosion with very narrow images (e.g. book spine), #67
+
 ## [0.3.0] - 2023-05-13
 
 Changed:
@@ -117,6 +125,8 @@ Fixed:
 Initial release
 
 <!-- link-labels -->
+[0.3.1]: ../../compare/v0.3.1...v0.3.0
+[0.3.0]: ../../compare/v0.3.0...v0.2.0
 [0.2.0]: ../../compare/v0.2.0...v0.1.0
 [0.1.0]: ../../compare/v0.1.0...v0.0.11
 [0.0.11]: ../../compare/v0.0.11...v0.0.10

Makefile

@@ -24,12 +24,15 @@ models: models_eynollah
 models_eynollah: models_eynollah.tar.gz
 	# tar xf models_eynollah_renamed.tar.gz --transform 's/models_eynollah_renamed/models_eynollah/'
 	# tar xf models_eynollah_renamed.tar.gz
-	tar xf 2022-04-05.SavedModel.tar.gz --transform 's/models_eynollah_renamed/models_eynollah/'
+	# tar xf models_eynollah_renamed_savedmodel.tar.gz --transform 's/models_eynollah_renamed_savedmodel/models_eynollah/'
+	tar xf models_eynollah.tar.gz
 
 models_eynollah.tar.gz:
 	# wget 'https://qurator-data.de/eynollah/2021-04-25/models_eynollah.tar.gz'
 	# wget 'https://qurator-data.de/eynollah/2022-04-05/models_eynollah_renamed.tar.gz'
-	wget 'https://ocr-d.kba.cloud/2022-04-05.SavedModel.tar.gz'
+	# wget 'https://ocr-d.kba.cloud/2022-04-05.SavedModel.tar.gz'
+	# wget 'https://qurator-data.de/eynollah/2022-04-05/models_eynollah_renamed_savedmodel.tar.gz'
+	wget https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz
 
 # Install with pip
 install:

README.md

@@ -1,10 +1,10 @@
 # Eynollah
-> Document Layout Analysis (segmentation) using pre-trained models and heuristics
+> Document Layout Analysis with Deep Learning and Heuristics
 
 [![PyPI Version](https://img.shields.io/pypi/v/eynollah)](https://pypi.org/project/eynollah/)
-[![CircleCI Build Status](https://circleci.com/gh/qurator-spk/eynollah.svg?style=shield)](https://circleci.com/gh/qurator-spk/eynollah)
 [![GH Actions Test](https://github.com/qurator-spk/eynollah/actions/workflows/test-eynollah.yml/badge.svg)](https://github.com/qurator-spk/eynollah/actions/workflows/test-eynollah.yml)
 [![License: ASL](https://img.shields.io/github/license/qurator-spk/eynollah)](https://opensource.org/license/apache-2-0/)
+[![DOI](https://img.shields.io/badge/DOI-10.1145%2F3604951.3605513-red)](https://doi.org/10.1145/3604951.3605513)
 
 ![](https://user-images.githubusercontent.com/952378/102350683-8a74db80-3fa5-11eb-8c7e-f743f7d6eae2.jpg)
 
@@ -14,17 +14,18 @@
 * Support for various image optimization operations:
   * cropping (border detection), binarization, deskewing, dewarping, scaling, enhancing, resizing
 * Text line segmentation to bounding boxes or polygons (contours) including for curved lines and vertical text
-* Detection of reading order
+* Detection of reading order (left-to-right or right-to-left)
 * Output in [PAGE-XML](https://github.com/PRImA-Research-Lab/PAGE-XML)
 * [OCR-D](https://github.com/qurator-spk/eynollah#use-as-ocr-d-processor) interface
 
+:warning: Development is currently focused on achieving the best possible quality of results for a wide variety of historical documents and therefore processing can be very slow. We aim to improve this, but contributions are welcome.
+
 ## Installation
-Python versions `3.8-3.11` with Tensorflow versions >=`2.12` on Linux are currently supported. Unfortunately we can not currently support Windows or MacOS. 
+Python `3.8-3.11` with Tensorflow `2.12-2.15` on Linux are currently supported.
-Windows users may be able to successfully run the tool through [WSL](https://learn.microsoft.com/en-us/windows/wsl/).
 
 For (limited) GPU support the CUDA toolkit needs to be installed.
 
-You can either install via 
+You can either install from PyPI
 
 ```
 pip install eynollah
@@ -40,45 +41,48 @@ cd eynollah; pip install -e .
 Alternatively, you can run `make install` or `make install-dev` for editable installation.
 
 ## Models
-Pre-trained models can be downloaded from [qurator-data.de](https://qurator-data.de/eynollah/).
+Pre-trained models can be downloaded from [qurator-data.de](https://qurator-data.de/eynollah/) or [huggingface](https://huggingface.co/SBB?search_models=eynollah). 
 
-In case you want to train your own model to use with Eynollah, have a look at [sbb_pixelwise_segmentation](https://github.com/qurator-spk/sbb_pixelwise_segmentation). 
+## Train
+🚧 **Work in progress**  
+  
+In case you want to train your own model, have a look at [`sbb_pixelwise_segmentation`](https://github.com/qurator-spk/sbb_pixelwise_segmentation). 
 
 ## Usage
 The command-line interface can be called like this:
 
 ```sh
 eynollah \
-  -i <image file> \
+  -i <single image file> | -di <directory containing image files> \
   -o <output directory> \
-  -m <path to directory containing model files> \
+  -m <directory containing model files> \
      [OPTIONS]
 ```
 
 The following options can be used to further configure the processing:
 
-| option   |      description      |
+| option            | description                                                                    |
-|----------|:-------------|
+|-------------------|:-------------------------------------------------------------------------------|
-| `-fl`  | full layout analysis including all steps and segmentation classes |
+| `-fl`             | full layout analysis including all steps and segmentation classes              |
-| `-light` | lighter and faster but simpler method for main region detection and deskewing |
+| `-light`          | lighter and faster but simpler method for main region detection and deskewing  |
-| `-tab` | apply table detection |
+| `-tab`            | apply table detection                                                          |
-| `-ae`  | apply enhancement (the resulting image is saved to the output directory) |
+| `-ae`             | apply enhancement (the resulting image is saved to the output directory)       |
-| `-as`  | apply scaling |
+| `-as`             | apply scaling                                                                  |
-| `-cl`  | apply contour detection for curved text lines instead of bounding boxes |
+| `-cl`             | apply contour detection for curved text lines instead of bounding boxes        |
-| `-ib`  | apply binarization (the resulting image is saved to the output directory)  |
+| `-ib`             | apply binarization (the resulting image is saved to the output directory)      |
-| `-ep`  | enable plotting (MUST always be used with `-sl`, `-sd`, `-sa`, `-si` or `-ae`) |
+| `-ep`             | enable plotting (MUST always be used with `-sl`, `-sd`, `-sa`, `-si` or `-ae`) |
-| `-ho`  | ignore headers for reading order dectection |
+| `-ho`             | ignore headers for reading order dectection                                    |
-| `-di <directory>`  | process all images in a directory in batch mode |
+| `-si <directory>` | save image regions detected to this directory                                  |
-| `-si <directory>`  | save image regions detected to this directory |
+| `-sd <directory>` | save deskewed image to this directory                                          |
-| `-sd <directory>`  | save deskewed image to this directory |
+| `-sl <directory>` | save layout prediction as plot to this directory                               |
-| `-sl <directory>`  | save layout prediction as plot to this directory |
+| `-sp <directory>` | save cropped page image to this directory                                      |
-| `-sp <directory>`  | save cropped page image to this directory |
+| `-sa <directory>` | save all (plot, enhanced/binary image, layout) to this directory               |
-| `-sa <directory>`  | save all (plot, enhanced/binary image, layout) to this directory |
 
-If no option is set, the tool will perform layout detection of main regions (background, text, images, separators and marginals).
+If no option is set, the tool performs layout detection of main regions (background, text, images, separators and marginals).
-The tool produces better quality output when RGB images are used as input than greyscale or binarized images.
+The best output quality is produced when RGB images are used as input rather than greyscale or binarized images.
 
 #### Use as OCR-D processor
+🚧 **Work in progress** 
 
 Eynollah ships with a CLI interface to be used as [OCR-D](https://ocr-d.de) processor. 
 
@@ -96,11 +100,14 @@ ocrd-eynollah-segment -I OCR-D-IMG-BIN -O SEG-LINE -P models
     
 uses the original (RGB) image despite any binarization that may have occured in previous OCR-D processing steps
 
+#### Additional documentation
+Please check the [wiki](https://github.com/qurator-spk/eynollah/wiki).
+
 ## How to cite
 If you find this tool useful in your work, please consider citing our paper:
 
 ```bibtex
-@inproceedings{rezanezhad2023eynollah,
+@inproceedings{hip23rezanezhad,
   title     = {Document Layout Analysis with Deep Learning and Heuristics},
   author    = {Rezanezhad, Vahid and Baierer, Konstantin and Gerber, Mike and Labusch, Kai and Neudecker, Clemens},
   booktitle = {Proceedings of the 7th International Workshop on Historical Document Imaging and Processing {HIP} 2023,

ocrd-tool.json

@@ -1 +1 @@
-qurator/eynollah/ocrd-tool.json
+src/eynollah/ocrd-tool.json

pyproject.toml

@@ -0,0 +1,43 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel", "setuptools-ocrd"]
+
+[project]
+name = "eynollah"
+authors = [
+    {name = "Vahid Rezanezhad"},
+    {name = "Staatsbibliothek zu Berlin - Preußischer Kulturbesitz"},
+]
+description = "Document Layout Analysis"
+readme = "README.md"
+license.file = "LICENSE"
+requires-python = ">=3.8"
+keywords = ["document layout analysis", "image segmentation"]
+
+dynamic = ["dependencies", "version"]
+
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Scientific/Engineering :: Image Processing",
+]
+
+[project.scripts]
+eynollah = "eynollah.cli:main"
+ocrd-eynollah-segment = "eynollah.ocrd_cli:main"
+
+[project.urls]
+Homepage = "https://github.com/qurator-spk/eynollah"
+Repository = "https://github.com/qurator-spk/eynollah.git"
+
+[tool.setuptools.dynamic]
+dependencies = {file = ["requirements.txt"]}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"*" = ["*.json", '*.yml', '*.xml', '*.xsd']

qurator/__init__.py

@@ -1 +0,0 @@
-__import__("pkg_resources").declare_namespace(__name__)

qurator/eynollah/__init__.py

@@ -1 +0,0 @@
-

requirements.txt

@@ -2,7 +2,7 @@
 ocrd >= 2.23.3
 numpy <1.24.0
 scikit-learn >= 0.23.2
-tensorflow >=2.12.0
+tensorflow == 2.12.1
 imutils >= 0.5.3
 matplotlib
 setuptools >= 50

setup.py

@@ -1,28 +0,0 @@
-from setuptools import setup, find_packages
-from json import load
-
-install_requires = open('requirements.txt').read().split('\n')
-with open('ocrd-tool.json', 'r', encoding='utf-8') as f:
-    version = load(f)['version']
-
-setup(
-    name='eynollah',
-    version=version,
-    long_description=open('README.md').read(),
-    long_description_content_type='text/markdown',
-    author='Vahid Rezanezhad',
-    url='https://github.com/qurator-spk/eynollah',
-    license='Apache License 2.0',
-    namespace_packages=['qurator'],
-    packages=find_packages(exclude=['tests']),
-    install_requires=install_requires,
-    package_data={
-        '': ['*.json']
-    },
-    entry_points={
-        'console_scripts': [
-            'eynollah=qurator.eynollah.cli:main',
-            'ocrd-eynollah-segment=qurator.eynollah.ocrd_cli:main',
-        ]
-    },
-)

src/eynollah/cli.py

@@ -1,7 +1,7 @@
 import sys
 import click
 from ocrd_utils import initLogging, setOverrideLogLevel
-from qurator.eynollah.eynollah import Eynollah
+from eynollah.eynollah import Eynollah
 
 
 @click.command()
@@ -209,9 +209,11 @@ def main(
         light_version=light_version,
         ignore_page_extraction=ignore_page_extraction,
     )
-    eynollah.run()
+    if dir_in:
-    #pcgts = eynollah.run()
+        eynollah.run()
-    ##eynollah.writer.write_pagexml(pcgts)
+    else:
+        pcgts = eynollah.run()
+        eynollah.writer.write_pagexml(pcgts)
 
 if __name__ == "__main__":
     main()

src/eynollah/eynollah.py

@@ -29,7 +29,8 @@ warnings.filterwarnings("ignore")
 from scipy.signal import find_peaks
 import matplotlib.pyplot as plt
 from scipy.ndimage import gaussian_filter1d
-from tensorflow.python.keras.backend import set_session
+# use tf1 compatibility for keras backend
+from tensorflow.compat.v1.keras.backend import set_session
 from tensorflow.keras import layers
 
 from .utils.contour import (
@@ -287,7 +288,6 @@ class Eynollah:
             self.ls_imgs  = os.listdir(self.dir_in)
             
         
-        
     def _cache_images(self, image_filename=None, image_pil=None):
         ret = {}
         if image_filename:
@@ -624,9 +624,6 @@ class Eynollah:
                 image_res = np.copy(img)
                 is_image_enhanced = False
         else:
-            #img_new, num_column_is_classified = self.calculate_width_height_by_columns_extract_only_images(img, num_col, width_early, label_p_pred)
-            #image_res = np.copy(img_new)
-            #is_image_enhanced = True
             num_column_is_classified = True
             image_res = np.copy(img)
             is_image_enhanced = False
@@ -925,6 +922,7 @@ class Eynollah:
                         seg_not_base[seg_not_base<1] =0
 
                     
+                    
                     seg_test = label_p_pred[0,:,:,1]
                     ##seg2 = -label_p_pred[0,:,:,2]
                     
@@ -3273,19 +3271,23 @@ class Eynollah:
                     else:
                         order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered, boxes_d, textline_mask_tot_d)
 
-                    pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_found_textline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml)
+                pcgts = self.writer.build_pagexml_full_layout(contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_found_textline_polygons_h, all_box_coord, all_box_coord_h, polygons_of_images, contours_tables, polygons_of_drop_capitals, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_xml)
-                    self.logger.info("Job done in %.1fs", time.time() - t0)
+                self.logger.info("Job done in %.1fs", time.time() - t0)
-                    ##return pcgts
+                if not self.dir_in:
+                    return pcgts
+            else:
+                contours_only_text_parent_h = None
+                if np.abs(slope_deskew) < SLOPE_THRESHOLD:
+                    order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot)
                 else:
-                    contours_only_text_parent_h = None
+                    contours_only_text_parent_d_ordered = list(np.array(contours_only_text_parent_d_ordered, dtype=object)[index_by_text_par_con])
-                    if np.abs(slope_deskew) < SLOPE_THRESHOLD:
+                    order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h, boxes_d, textline_mask_tot_d)
-                        order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot)
+                pcgts = self.writer.build_pagexml_no_full_layout(txt_con_org, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_box_coord, polygons_of_images, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml, contours_tables)
-                    else:
+                self.logger.info("Job done in %.1fs", time.time() - t0)
-                        contours_only_text_parent_d_ordered = list(np.array(contours_only_text_parent_d_ordered, dtype=object)[index_by_text_par_con])
+                if not self.dir_in:
-                        order_text_new, id_of_texts_tot = self.do_order_of_regions(contours_only_text_parent_d_ordered, contours_only_text_parent_h, boxes_d, textline_mask_tot_d)
+                    return pcgts
-                    pcgts = self.writer.build_pagexml_no_full_layout(txt_con_org, page_coord, order_text_new, id_of_texts_tot, all_found_textline_polygons, all_box_coord, polygons_of_images, polygons_of_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_xml, contours_tables)
+
-                    self.logger.info("Job done in %.1fs", time.time() - t0)
+            if self.dir_in:
-                    ##return pcgts
                 self.writer.write_pagexml(pcgts)
                 #self.logger.info("Job done in %.1fs", time.time() - t0)
         if self.dir_in:

src/eynollah/ocrd-tool.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.3.0",
+  "version": "0.3.1",
   "git_url": "https://github.com/qurator-spk/eynollah",
   "tools": {
     "ocrd-eynollah-segment": {

src/eynollah/processor.py

@@ -42,7 +42,7 @@ class EynollahProcessor(Processor):
             page = pcgts.get_Page()
             # XXX loses DPI information
             # page_image, _, _ = self.workspace.image_from_page(page, page_id, feature_filter='binarized')
-            image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(url=page.imageFilename))).local_filename
+            image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(local_filename=page.imageFilename))).local_filename
             eynollah_kwargs = {
                 'dir_models': self.resolve_resource(self.parameter['models']),
                 'allow_enhancement': False,

tests/test_counter.py

@@ -1,5 +1,5 @@
 from tests.base import main
-from qurator.eynollah.utils.counter import EynollahIdCounter
+from eynollah.utils.counter import EynollahIdCounter
 
 def test_counter_string():
     c = EynollahIdCounter()

tests/test_dpi.py

@@ -1,6 +1,6 @@
 import cv2
 from pathlib import Path
-from qurator.eynollah.utils.pil_cv2 import check_dpi
+from eynollah.utils.pil_cv2 import check_dpi
 from tests.base import main
 
 def test_dpi():

tests/test_run.py

@@ -2,7 +2,7 @@ from os import environ
 from pathlib import Path
 from ocrd_utils import pushd_popd
 from tests.base import CapturingTestCase as TestCase, main
-from qurator.eynollah.cli import main as eynollah_cli
+from eynollah.cli import main as eynollah_cli
 
 testdir = Path(__file__).parent.resolve()
 

tests/test_smoke.py

@@ -1,7 +1,7 @@
 def test_utils_import():
-    import qurator.eynollah.utils
+    import eynollah.utils
-    import qurator.eynollah.utils.contour
+    import eynollah.utils.contour
-    import qurator.eynollah.utils.drop_capitals
+    import eynollah.utils.drop_capitals
-    import qurator.eynollah.utils.drop_capitals
+    import eynollah.utils.drop_capitals
-    import qurator.eynollah.utils.is_nan
+    import eynollah.utils.is_nan
-    import qurator.eynollah.utils.rotate
+    import eynollah.utils.rotate

tests/test_xml.py

@@ -1,5 +1,5 @@
 from pytest import main
-from qurator.eynollah.utils.xml import create_page_xml
+from eynollah.utils.xml import create_page_xml
 from ocrd_models.ocrd_page import to_xml
 
 PAGE_2019 = 'http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15'