Skip to main content

ORTHO Mask Editor

A PyQT5-based mask editor tool for the ORTHO (Old Research Text Hebrew OCR) project. This tool helps create training data for the ORTHO U-Net AI model by allowing users to create and edit image masks of Hebrew text documents.

About ORTHO

ORTHO (Old Research Text Hebrew OCR) is a project focused on optical character recognition for historical Hebrew texts. The project uses a U-Net architecture for text segmentation and recognition.

Screenshot

ORTHO Mask Editor

Purpose

This mask editor serves as a crucial tool in the ORTHO pipeline by:

  • Creating binary masks for training data
  • Marking text regions in historical Hebrew documents
  • Preparing ground truth data for the U-Net model
  • Enabling manual correction of automated segmentation results

Installation

Prerequisites

  • Python 3.6 or higher
  • PyQt5
  • NumPy

Setup

You can install ORTHO Mask Editor using pip:

pip install ortho-editor

Or install from source:

  1. Clone the repository:
git clone https://github.com/yaacov/ortho-editor.git
cd ortho-editor

Usage

  1. Prepare a directory that contains two subdirectories named inputs and targets.

    • inputs holds the original images.
    • targets holds the corresponding mask images (same filenames, same dimensions).
  2. Install the required dependencies:

    pip install -r requirements.txt
    
  3. Run the application:

    python main.py
    
  4. When prompted, select your directory with inputs and targets subdirectories.

  5. A list of files from the inputs folder will appear. Choose a file to display the image as the background, then draw or edit the mask on top.

Development

The project includes a Makefile with useful commands for development:

make install  # Install the required packages
make run      # Run the editor
make format   # Format the code using black
make lint     # Lint the code using flake8
make package  # Create a pip package
make push     # Upload package to PyPI using twine
make clean    # Remove build artifacts and Python cache files

If you're contributing to the project, make sure to run make format and make lint before submitting your changes.

License

MIT License

Metadata

Release files for ortho-editor 0.1.14

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ortho-editor 0.1.14
File Size Uploaded Provenance
ortho_editor-0.1.14.tar.gz 204.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for ortho-editor 0.1.14
File Interpreter ABI Platform
ortho_editor-0.1.14-py3-none-any.whl Python 3 none any Details

Total release size: 409.1 kB

Release files / ortho_editor-0.1.14.tar.gz

Download URL ortho_editor-0.1.14.tar.gz
Size 204.5 kB
Tags Source
SHA-256 checksum
How to use checksums
72f3b16e3cb581a17b64787172376965fde86584a35f173f43d44ca7a1e1d643
BLAKE2b-256 checksum
How to use checksums
4caa9893acb20ce76ba5530be24259916823594f0d9ea7c01a20182b5d642fe8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.8

Release files / ortho_editor-0.1.14-py3-none-any.whl

Download URL ortho_editor-0.1.14-py3-none-any.whl
Size 204.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f719156bb213b718404536cf5de583bb273c1855861d76b1330147048cd85370
BLAKE2b-256 checksum
How to use checksums
8e9ad6610eb6851ccb9c123830fac22e4bc1ba56d37e880a193b9f060ca21d0a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.0.1 CPython/3.12.8

Security for ortho-editor 0.1.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page