# oarriaga/face_classification

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

Repository: https://github.com/oarriaga/face_classification
Canonical: https://ross.abutalabs.com/products/face_classification
Language: Python
License: MIT
License Family: permissive
Last push: 2024-03-08T20:04:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3492, "days_push": 908, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5735, forks 1606 (observed 2026-08-28T04:09:28.365548+00:00)

## What it is
A Python project providing real-time face detection with emotion and gender classification using a Keras CNN trained on fer2013 and IMDB datasets, with OpenCV for video capture. It includes demo scripts, training pipelines, and a Docker image, but is deprecated in favor of the author's PAZ library.

## Use cases
- detect faces in webcam video in real time
- classify facial emotions from images
- predict gender from face photos
- train an emotion classifier on fer2013
- run face classification in a docker container
- visualize CNN attention with grad-cam

## When to choose
- you need a simple, well-known baseline for face emotion or gender classification
- you want reference code for training CNNs on fer2013 or IMDB-WIKI datasets
- you need a quick real-time webcam demo with OpenCV and Keras

## When to avoid
- you need maintained code or TensorFlow 2.x support - the repo is deprecated in favor of oarriaga/paz
- you need high accuracy emotion recognition (fer2013 accuracy is only 66%)
- you need production-grade face analysis pipelines

## Facets
- artifact type: library
- maturity: abandoned
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: face-detection, emotion-recognition, gender-classification, keras, opencv, fer2013, real-time, deprecated, docker

## Member repositories
- oarriaga/face_classification (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.365548+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 2026-08-29T17:53:22.485399+00:00, confidence not recorded.
  - readme: https://github.com/oarriaga/face_classification (fetched 2026-08-28T04:09:28.365548+00:00, sha 5da08db4db93)
- Data as of 2026-08-30T08:39:29.467469+00:00.