Skip to content

windmark/static-gesture-recognition

Repository files navigation

Static Gesture Recognition using Leap motion

An automated bar ordering system for making orders in a bar using hand gestures.

The purpose of this project was to develop an ordering system for a bar where orders were made only by using static hand gestures. With the help of a Leap Motion controller, we used Machine Learning to train a model to recognize 8 different hand gestures, in which the user could (with the support of the UI) navigate the ordering system ordering any number of drinks, foods and even to select payment option solely by using hand gestures.

Paper available here.

Features

  • Static hand gesture recognition.
  • Voice and written response to different gestures.
  • Simple to add new gestures.

Requirements

Run

$ py mainProgram.py

Training and saving gesture data (optional)

Save gestures

Save each gesture multiple times using: $ py saveGesturesRaw.py # Where # is an integer representing each gesture.

Train

$ py training/training.py

Flow

Flow chart of the UI. The user interacts using gestures and receives both written and spoken response. OrderingFLow

Gestures

GestureGIF

  • Init.
  • Alcoholic drink.
  • Non alcoholic drink.
  • Food.
  • Undo.
  • Checkout.
  • Pay with cash.
  • Pay with credit card.

Blog

See our blog from the project here.

Report

Project report.

Team

Christofer Lind Maria Svensson Babak Toghiani-Rizi Marcus Windmark

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages