https://github.com/julianfbeck/hand_recognition

Handpose recognition to trigger Windows System Actions
https://github.com/julianfbeck/hand_recognition

Last synced: about 2 months ago
JSON representation

Handpose recognition to trigger Windows System Actions

• Host: GitHub
• URL: https://github.com/julianfbeck/hand_recognition
• Owner: julianfbeck
• License: mit
• Created: 2019-08-01T11:45:59.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2021-03-11T09:18:49.000Z (about 4 years ago)
• Last Synced: 2025-02-06T05:33:07.366Z (4 months ago)
• Language: Python
• Homepage:
• Size: 23 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Handpose regognition programmm

![](https://i.imgur.com/gDYoqN2.jpg)

A real-time object recognition application using [Google's TensorFlow Object Detection API](https://github.com/tensorflow/models/tree/master/research/object_detection) and [OpenCV](http://opencv.org/).

This Repo is based on [datitran](https://github.com/datitran) [Object-Detector-App](https://github.com/datitran/object_detector_app).

We trained our model on different hand poses using the [IBM cloud-annotation traing CLI](https://github.com/cloud-annotations/training)

To trigger system action we used multiple poses.

## Getting Started

1. `conda env create -f environment.yml`

2. `python object_detection_multithreading.py`

## Requirements

- [Anaconda / Python 3.5](https://www.continuum.io/downloads)

- [TensorFlow 1.2](https://www.tensorflow.org/)

- [OpenCV 3.0](http://opencv.org/)