This page is optimized for mobile devices, if you would prefer the desktop version just click here

0.2 Feature extraction

We start with Vulcan! Here is an original picture for our gesture.

Vulcan

The Original "Vulcan" Gesture

Convert image to grayscale.

Vulcan converted to grayscale

Filter out noise and convert the image into a binary image.

Binary Form of Vulcan

Label the largest connected component in our image matrix and get the edge of our gesture.

Edge of Vulcan

Get polar form of the edge matrix. Divide the polar form into n(here n=8) equal bins and count number of 1’s(dots) in each bin.

A demonstration of how our algorithm works

Finally, we compare the data we get here with distribution of dots in our training set and get our predicted gesture of this image

<< Chapter < Page Page > Chapter >>

OpenStax, 2d hand gesture recognition. OpenStax CNX. Dec 19, 2013 Download for free at http://cnx.org/content/col11606/1.1

Google Play and the Google Play logo are trademarks of Google Inc.