Skip to main content

PyLipExtractor

PyLipExtractor is a powerful and easy-to-use Python package for extracting lip regions from videos. It leverages the high-precision MediaPipe Face Mesh to accurately detect and crop the lip area, providing a stable and reliable tool for researchers and developers working on lip-reading, facial analysis, and other related fields.

For detailed information about the package, its features, and how to use them, please refer to the Full Documentation.

Key Features

  • Accurate & Stable Lip Detection: Utilizes MediaPipe Face Mesh for precise landmark detection.
  • Temporal Smoothing: Applies an Exponential Moving Average (EMA) filter for smooth and consistent lip crops.
  • Illumination Normalization: Includes an optional histogram matching filter to normalize video brightness.
  • Flexible Configuration: Offers a wide range of customizable settings.
  • Customizable Hardware Acceleration: Choose your preferred processing device (auto, cuda, or cpu) for video conversion. The package leverages NVIDIA GPU acceleration (if available) for faster processing and uses lossless compression to ensure no quality is lost.

Demo

https://github.com/user-attachments/assets/a6841309-3e4d-4b7e-bd0f-b56a5cab28e4

Original video by Tima Miroshnichenko

Installation

pip install pylipextractor

Quick Start

Here is a basic example of how to use PyLipExtractor. For a more detailed and comprehensive example, please see examples/example_usage.py.

from pylipextractor.lip_extractor import LipExtractor

# Create a LipExtractor instance
extractor = LipExtractor()

# Specify the path to your video
video_path = "path/to/your/video.mp4"
output_path = "output/lip_frames.npy"

# Extract the lip frames
extracted_frames, rtf_value = extractor.extract_lip_frames(video_path, output_path)

if extracted_frames is not None:
    print(f"Successfully extracted {len(extracted_frames)} frames.")
    if rtf_value is not None:
        print(f"Real-Time Factor (RTF): {rtf_value:.4f}")

Documentation

For a deep dive into all the features, configurations, and technical details, please read our Comprehensive Documentation.

Contributing

Contributions are welcome! Please see our Contributing Guidelines for more details.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Metadata

Release files for pylipextractor 2.2.4

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

Source distribution (sdist)

Source distribution for pylipextractor 2.2.4
File Size Uploaded Provenance Actions
pylipextractor-2.2.4.tar.gz 15.8 kB Without provenance Details for pylipextractor-2.2.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for pylipextractor 2.2.4
File Interpreter ABI Platform Actions
pylipextractor-2.2.4-py3-none-any.whl Python 3 none any Details for pylipextractor-2.2.4-py3-none-any.whl

Total release size: 30.8 kB

Release files / pylipextractor-2.2.4.tar.gz

Download URL pylipextractor-2.2.4.tar.gz
Size 15.8 kB
Tags Source
SHA-256 checksum
How to use checksums
ea87d9e12aa4566788647f8c3414754dd0094e444fc9aa0485ce501e3fb87515
BLAKE2b-256 checksum
How to use checksums
680201c835318d8c08a74ff02c79382f633f387ed106eab2be252b99329cd0ff
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.18

Release files / pylipextractor-2.2.4-py3-none-any.whl

Download URL pylipextractor-2.2.4-py3-none-any.whl
Size 15.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4699356d6ce73f671e4bbe31db64bbb6a03e8c0d553113fc574c1e540b9cceba
BLAKE2b-256 checksum
How to use checksums
a8b849fadc29f79753944e055817515ab5e4b056282e1c2134bf5a263a54e3d6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.18

Security for pylipextractor 2.2.4

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