# sb-ai-lab/EmotiEffLib

Efficient face emotion recognition in photos and videos

Repository: https://github.com/sb-ai-lab/EmotiEffLib
Canonical: https://ross.abutalabs.com/products/emotiefflib
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: emotion-recognition, face-emotion-detection, face-expression, face-emotion-recognition, emotion-analysis, emotion-detection, facial-expression-recognition, facial-expressions
Last push: 2026-06-23T19:29:57+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 15, longevity 100
- inputs: {"age_days": 1995, "days_push": 71, "days_rel": 357, "gap_med": 198, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1057, forks 156 (observed 2026-08-28T04:03:24.863395+00:00)

## What it is
EmotiEffLib (formerly HSEmotion) is a lightweight library for facial emotion and engagement recognition in photos and videos, available in Python and C++. It supports PyTorch and ONNX backends for efficient real-time analysis across platforms.

## Use cases
- recognize emotions in photos
- detect facial expressions in video
- analyze user engagement from webcam footage
- run real-time emotion recognition with onnx
- classify emotions on the affectnet dataset
- integrate face emotion detection into a c++ application

## When to choose
- you need lightweight, real-time facial emotion recognition in Python or C++
- you want PyTorch or ONNX backend flexibility for deployment
- you need both image and video emotion analysis
- you want state-of-the-art accuracy on AffectNet benchmarks

## When to avoid
- you need full-body pose or gesture analysis
- you need text or speech emotion recognition
- you need training pipelines for custom emotion models from scratch

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing, video-processing, nlp
- domain: computer-vision, machine-learning, image-processing, artificial-intelligence
- platform: python, cpp, cross-platform
- tags: emotion-recognition, facial-expression-recognition, engagement-detection, onnx, pytorch, affectnet, video

## Member repositories
- sb-ai-lab/EmotiEffLib (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:24.863395+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:58:00.045627+00:00, confidence not recorded.
  - readme: https://github.com/sb-ai-lab/EmotiEffLib (fetched 2026-08-28T04:03:24.863395+00:00, sha e32196927f53)
  - registry_pypi: https://pypi.org/pypi/emotiefflib/json (fetched 2026-08-29T12:59:56.734572+00:00, sha 9ac9953d68ff)
- Data as of 2026-08-30T08:39:29.467469+00:00.