# asingh33/CNNGestureRecognizer

Gesture recognition via CNN. Implemented in Keras + Tensorflow/Theano + OpenCV

Repository: https://github.com/asingh33/CNNGestureRecognizer
Canonical: https://ross.abutalabs.com/products/cnngesturerecognizer
Language: Python
License: MIT
License Family: permissive
Topics: gesture-recognition, machine-learning, theano, python, tensorflow, keras
Last push: 2026-05-21T09:48:24+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 8, longevity 100
- inputs: {"age_days": 3412, "days_push": 104, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1041, forks 352 (observed 2026-08-28T04:03:20.677398+00:00)

## What it is
A desktop application that recognizes hand gestures from webcam video using a convolutional neural network built with Keras, TensorFlow/Theano, and OpenCV. It includes training scripts, a dataset of ~4015 gesture images, and pretrained weight files.

## Use cases
- recognize hand gestures from webcam
- train a CNN on gesture images
- gesture-controlled interface prototype
- visualize CNN feature maps
- learn gesture recognition with Keras and OpenCV

## When to choose
- you want a working gesture recognition demo with pretrained weights
- you're learning CNNs with Keras and OpenCV
- you need a small gesture dataset to experiment with

## When to avoid
- you need production-grade, real-time multi-hand tracking
- you require modern maintained dependencies (Theano is obsolete)
- you need mobile or embedded deployment

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: gesture-recognition, cnn, keras, opencv, hand-gestures, desktop

## Member repositories
- asingh33/CNNGestureRecognizer (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.677398+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 2026-08-30T07:02:53.214214+00:00, confidence not recorded.
  - readme: https://github.com/asingh33/CNNGestureRecognizer (fetched 2026-08-28T04:03:20.677398+00:00, sha b8816e77f13f)
- Data as of 2026-08-30T08:39:29.467469+00:00.