inventory-ocr 0.0.1__tar.gz

inventory_ocr-0.0.1/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.

inventory_ocr-0.0.1/PKG-INFO

@@ -0,0 +1,24 @@
+Metadata-Version: 2.4
+Name: inventory-ocr
+Version: 0.0.1
+Summary: Read inventory cards, extract images, and create structured data.
+Author-email: Mathias Zinnen <mathias.zinnen@gmail.com>
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: ultralytics
+Requires-Dist: appdirs
+Requires-Dist: tqdm
+Requires-Dist: Levenshtein
+Requires-Dist: gradio
+Requires-Dist: gradio_image_annotation
+Provides-Extra: pero
+Requires-Dist: pero-ocr; extra == "pero"
+Requires-Dist: configparser; extra == "pero"
+Provides-Extra: mistral
+Requires-Dist: mistralai; extra == "mistral"
+Requires-Dist: dotenv; extra == "mistral"
+Dynamic: license-file

inventory_ocr-0.0.1/README.md

@@ -0,0 +1,109 @@
+# inventory-ocr
+
+This is a tool to extract structured data from fixed layout documents such as inventory cards, inventory books or tables. It requires layout definitions provided in `inventory_ocr/config/regions.yaml`. Currently, it is optimized to work with a collection of jewelry from the Schmuckmuseum Pforzheim, but with minor adaptations it should be adaptable to other use cases. 
+
+Specifically, to adapt this for your own data:
+- Define a different document layout in `inventory_ocr/config/regions.yaml`
+- Implement your own post-processing by subclassing the abstract PostProcessor class in `inventory_ocr/postprocessor.py`
+
+## Installation
+
+Set up your environment using your favourite environment management tool. We recommend [venv](https://docs.python.org/3/library/venv.html). 
+
+Install using `pip install inventory-ocr`
+
+## Usage
+
+Invoke using `inventory-ocr <input folder>` with input folder specifying a path to the inventory cards to be processed. Results will be saved to `output/` relative to the current working directory.
+
+### Command Line Arguments
+
+```
+inventory-ocr <input_dir> [options]
+```
+
+**Required Arguments:**
+- `input_dir`: Path to the input directory containing files to process
+
+**Optional Arguments:**
+- `--output_dir`: Path to the output directory (default: `./output`)
+- `--layout_config`: Path to the layout configuration file (default: `config/regions.yaml`)
+- `--annotate`: Launch the interactive layout annotation UI to create/save a regions file
+- `--ocr_engine`: OCR engine to use (choices: `auto`, `ocrmac`, `pero`, `mistral`, `dummy`; default: `auto`)
+- `--eval`: Run in evaluation mode (uses dummy detector and benchmarking postprocessor)
+
+### Annotation / Generating Regions
+
+- The repository contains an example regions file under `inventory_ocr/config/example_regions.yaml`. If present, that example will be used by default as the layout definition.
+- To create your own layout interactively, run the tool with the `--annotate` flag. This launches a small Gradio UI that lets you mark regions on a template image. When you press "Extract Layout" the regions are written to the layout configuration path (see `--layout_config`, default `inventory_ocr/config/regions.yaml`) and the annotation UI will close.
+- If you prefer not to use the example, simply remove `inventory_ocr/config/example_regions.yaml` (or replace it with your own `regions.yaml`), or run with `--annotate` to generate a new regions file which will be saved to the configured `--layout_config` path.
+
+Example:
+```
+# use the bundled example regions (if present)
+inventory-ocr ./data
+
+# interactively generate and save regions to the default config path
+inventory-ocr ./data --annotate
+
+# specify a custom path for the generated regions
+inventory-ocr ./data --annotate --layout_config ./my_regions.yaml
+```
+
+Generated YAML uses a top-level `regions:` mapping where each field name maps to a 4-element list `[x1, y1, x2, y2]` with normalized coordinates (0..1).
+
+### Supported OCR Engines
+
+The tool supports multiple OCR engines with automatic platform-based selection:
+
+- **PERO OCR** (`pero`): Default for non-macOS platforms
+- **Apple Vision API** (`ocrmac`): Default for macOS platforms  
+- **Mistral OCR** (`mistral`): AI-powered OCR using Mistral models
+- **Dummy** (`dummy`): For development and testing purposes
+- **Auto** (`auto`): Automatically selects `ocrmac` on macOS, `pero` on other platforms
+
+### Installing Optional Dependencies
+
+Different OCR engines require additional dependencies:
+
+**For PERO OCR (non-macOS default):**
+```bash
+pip install inventory-ocr[pero]
+```
+
+**For Mistral OCR:**
+```bash
+pip install inventory-ocr[mistral]
+```
+
+You'll also need to obtain a Mistral API key and store it in a `.env` file in your project root:
+
+1. Copy `.env.template` to `.env`:
+   ```bash
+   cp .env.template .env
+   ```
+
+2. Edit `.env` and replace `INSERT_YOUR_KEY_HERE` with your actual Mistral API key:
+   ```
+   MISTRAL_API_KEY=your_actual_api_key_here
+   ```
+
+**Note:** Never share your API key publicly or commit it to version control.
+
+**For Apple Vision API (macOS only):**
+The `ocrmac` package is automatically installed on macOS systems. No additional installation required.
+
+**Note:** The `auto` engine selection will use Apple Vision API on macOS (if available) and PERO OCR on other platforms.
+
+## Configuration
+
+### Region Definition
+
+Regions (in relative coordinates) and field names are stored in `inventory_ocr/config/regions.yaml` (or the path you pass via `--layout_config`) and can be adapted according to the use case.
+
+The region definition format uses normalized coordinates where each region is defined as `[x1, y1, x2, y2]` with values between 0 and 1:
+- `x1, y1`: Top-left corner coordinates (relative to document width and height)
+- `x2, y2`: Bottom-right corner coordinates (relative to document width and height)
+
+custom_header_mappings:
+  am: 'erworben am'  # Maps "am" field to "erworben am" in output

inventory_ocr-0.0.1/inventory_ocr/annotate.py

@@ -0,0 +1,53 @@
+import gradio as gr
+from gradio_image_annotation import image_annotator
+import os
+import yaml
+
+def create_annotation_app(input_dir, layout_file_path):
+    """
+    Returns a gr.Blocks app to annotate the layout. 
+    TODOS: Display a nice success message and close the browser window before killing the app serving process. But gradio conditional rendering is a pain in the...
+    """
+    print("Loading template image for region annotation...")
+    img_files = [f for f in os.listdir(input_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg'))]
+    assert img_files, "No image files found in the input directory."
+    template_image_path = os.path.join(input_dir, img_files[0])
+
+    def set_layout(layout, state):
+        return state + [layout]
+
+    def extract_layout(annotations, layout_state):
+        (h, w, c) = annotations['image'].shape
+
+        regions = {}
+        for box in annotations['boxes']:
+            xmin = int(box['xmin']) / w
+            xmax = int(box['xmax']) / w
+            ymin = int(box['ymin']) / h
+            ymax = int(box['ymax']) / h
+            label = box['label']
+            regions[label] = [xmin, ymin, xmax, ymax]
+        print(f"Saving layout configuration to {layout_file_path}...")
+        with open(layout_file_path, 'w') as f:
+            yaml.dump({'regions': regions}, f, default_flow_style=False)
+        os._exit(0) 
+        return gr.Markdown("Layout succesfully defined. You may now close this window."), regions
+
+    with gr.Blocks() as annotation_app:
+        gr.Markdown("# Layout Annotation Tool")
+
+        layout_state = gr.State([])
+
+        gr.Markdown("### Annotate the Image")
+
+        @gr.render(inputs=layout_state)
+        def show_annotation_interface(layout):
+            annotations = image_annotator({"image": template_image_path, "boxes": []},
+                                            label_list=["Field Name"],
+                                            label_colors=[(0, 255, 0)],
+                                            boxes_alpha=0.4)
+            extract_layout_button = gr.Button("Extract Layout")
+            close_message =  gr.Markdown("", visible=False)
+            extract_layout_button.click(extract_layout, inputs=[annotations, layout_state], outputs=[close_message, layout_state])
+
+    return annotation_app

inventory_ocr-0.0.1/inventory_ocr/config/example_regions.yaml

@@ -0,0 +1,16 @@
+regions:
+  Gegenstand: [0, 0, 1, 0.1]
+  Inv. Nr.: [0.044, 0.08, 0.275, 0.145]
+  Herkunft: [0.2737, 0.0806, 0.5054, 0.237]
+  Foto Notes: [0.5054, 0.0806, 1, 0.237]
+  Standort: [0.047, 0.135, 0.275, 0.235]
+  Material: [0.047, 0.237, 0.275, 0.435]
+  Datierung: [0.275, 0.237, 0.505, 0.317]
+  Maße: [0.275, 0.317, 0.505, 0.435]
+  erworben von: [0.047, 0.435, 0.505, 0.521]
+  Beschreibung: [0.047, 0.521, 0.505, 0.794]
+  Ausstellungen: [0.047, 0.795, 0.505, 1]
+  am: [0.505, 0.435, 0.707, 0.53]
+  Preis: [0.707, 0.435, 0.869, 0.53]
+  Vers.-Wert: [0.870, 0.435, 1.0, 0.53]
+  Literatur: [0.50, 0.53, 1.0, 1.0]

inventory_ocr-0.0.1/inventory_ocr/detection.py

@@ -0,0 +1,95 @@
+from ultralytics import YOLO
+from inventory_ocr.utils import download_and_unzip
+import glob
+import shutil
+import torch
+import cv2
+import os
+
+
+class Detector:
+    """Abstract base class for different detector implementations."""
+    def parse_directory(self, input_dir, crop_dir='tmp', output_base_dir='output'):
+        """Parse a directory of images and save cropped images to the output directory."""
+        raise NotImplementedError("This method should be overridden by subclasses.")
+
+    def detect(self, image):
+        """Detect objects in a single image."""
+        raise NotImplementedError("This method should be overridden by subclasses.")
+
+    def crop_and_save(self, detections, out_dir, name):
+        """Crop detected objects and save them to the specified directory."""
+        raise NotImplementedError("This method should be overridden by subclasses.")
+
+
+class YoloImageDetector(Detector):
+    def __init__(self, resources_path, chunk_size=50,
+                 weights_url='https://faubox.rrze.uni-erlangen.de/dl/fi9iK4rseupfrrTeXWQUGP/weights.zip'):
+        self._prepare_resources(resources_path, weights_url)
+        self.model = YOLO(os.path.join(resources_path, 'yolov8.pt'))
+        self.chunk_size = chunk_size
+        self.device = 'mps' if torch.backends.mps.is_available() else 'cpu'
+        print(f'Detection running on {self.device}')
+
+    def _prepare_resources(self, resources_path, weights_url):
+        if os.path.exists(os.path.join(resources_path, 'yolov8.pt')):
+            return
+        print(f'Downloading YOLO weights to {os.path.abspath(resources_path)}...')
+        download_and_unzip(weights_url, resources_path)
+
+    def _batch(self, iterable, n=1):
+        l = len(iterable)
+        for ndx in range(0, l, n):
+            yield iterable[ndx:ndx+n]
+
+    def _move_crops(self, yolo_name, out_dir):
+        yolo_output = os.path.join(out_dir, yolo_name)
+        crop_dir = os.path.join(out_dir, 'images')
+        if not os.path.isdir(crop_dir):
+            os.makedirs(crop_dir)
+        for file in glob.glob(os.path.join(yolo_output, '**', '*.jpg'), recursive=True):
+            fn = os.path.basename(file)
+            shutil.move(file, os.path.join(crop_dir, fn))
+        shutil.rmtree(yolo_output)
+        print(f'Detected images moved to \033[1m{crop_dir}\033[0m')
+
+    def parse_directory(self, input_dir, crop_dir='tmp', output_base_dir='output'):
+        image_exts = ['.jpg', '.jpeg']
+        images_to_process = [os.path.join(input_dir, fn) for fn in os.listdir(input_dir) if os.path.splitext(fn)[1] in image_exts]
+        n_chunks = len(images_to_process) // self.chunk_size + 1
+        i = 1
+        for img_chunk in self._batch(images_to_process, self.chunk_size):
+            print(f'Detecting images in chunk {i}/{n_chunks}..')
+            self.model.predict(img_chunk, save_crop=True, device=self.device, name=crop_dir, project=output_base_dir)
+            self._move_crops(crop_dir, output_base_dir)
+            i += 1
+
+    def detect(self,image):
+        results = self.model.predict(image, device=self.device, max_det=1)
+        return results
+
+    def crop_and_save(self, detections, out_dir, name):
+        if not os.path.isdir(out_dir):
+            os.makedirs(out_dir)
+        for i, result in enumerate(detections):
+            if result.boxes is None or len(result.boxes) == 0:
+                continue # no image found
+            # Sort boxes by confidence in descending order
+            x1,y1,x2,y2 = sorted(result.boxes, key=lambda box: box.conf, reverse=True)[0].xyxy[0].flatten().int().tolist()
+            crop = result.orig_img[y1:y2,x1:x2]
+            cv2.imwrite(os.path.join(out_dir, name),crop)
+
+
+class DummyDetector(Detector):
+    def __init__(self, chunk_size=50):
+        self.chunk_size = chunk_size
+        print(f'Dummy detector doing nothing, OCR only.')
+
+    def parse_directory(self, input_dir, crop_dir='tmp', output_base_dir='output'):
+        pass
+
+    def detect(self, image):
+        return []
+
+    def crop_and_save(self, detections, out_dir, name):
+        pass