Static hand gesture recognition using deep learning.
Autoencoder_proj folder contains the code for static hand gesture recognition using 5 stacked denoising autoencoders. It is made using the starter code from http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial.
The HandTracker folder contains the code for extracting hand gesture images using kinect and then segmenting it. This then sends the images to matlab for classification.
The folder Arduino contains the code to control the motors for the movement of differential wheeled robot.`