cosanlab/py-feat

Facial Expression Analysis Toolbox

What it solves

Py-FEAT provides a comprehensive toolkit for researchers to analyze facial expressions (FEX) from images and videos. It simplifies the process of extracting emotional states, muscle movements, and facial landmarks, which would otherwise require integrating multiple separate tools.

How it works

The library uses a Detectorv1 class to process visual data. It automatically downloads necessary model weights from the HuggingFace Hub and can run on CPU, NVIDIA GPUs (CUDA), or Apple Silicon (MPS). The suite handles the entire pipeline from face detection to the extraction of specific facial features and provides methods for preprocessing, analyzing, and visualizing the resulting data.

Who it’s for

It is primarily designed for researchers in the field of facial expression analysis and affective computing.

Highlights

  • Extracts emotional expressions (e.g., happiness, sadness, anger).
  • Detects facial muscle movements known as action units.
  • Identifies facial landmarks.
  • Supports hardware acceleration across CPU, CUDA, and Metal (MPS).

Related

  • Project
    tomas-gajarsky/facetorch

    A Python library for facial detection and analysis that curates and optimizes open-source deep learning models for tasks like emotion recognition and deepfake detection.

  • Project
    yakhyo/uniface

    UniFace is a Python library that unifies 15 face‑analysis tasks—detection, landmarks, 3‑D mesh, parsing, matting, gaze, head pose, demographics, emotion, quality, anti‑spoofing, recognition, anonymisation, and FAISS‑based similarity—into a single, easy‑to‑install package (CPU, Apple Silicon, or CUDA). It provides a consistent API, auto‑downloads verified model weights, and includes extensive docs, notebooks, and a community Discord.

  • Project
    serengil/deepface

    A lightweight Python framework for face recognition and facial attribute analysis that wraps multiple state-of-the-art models into a single, easy-to-use API.

  • Dispatch
    Getting Started with Sentiment Analysis using Python

    Hugging Face provides a comprehensive guide on implementing sentiment analysis using Python, leveraging pre-trained models from the Hugging Face Hub, the Trainer API for fine-tuning, and the no-code AutoNLP tool.

  • Project
    phamquiluan/ResidualMaskingNetwork

    A facial expression recognition system using a Residual Masking Network to detect human emotions from images and live video feeds.