b) Test for recognition using a webcam: use the flesh interest regions to find “potential hands”; take
gradients in each flesh region; use histogram matching above a threshold to detect the gesture. If
two models are above threshold, take the better match as the winner.
c) Move your hand one to two feet further back and see if the gradient histogram can still recognize
the gestures. Report.
8. Repeat exercise 7 but with EMD for the matching. What happens to EMD as you move your hand
back?
9. With the same images as before but with captured image patches instead of histograms of the flesh
around the hand, use cv::matchTemplate() instead of histogram matching. What happens to
template matching when you move your hand backwards so that its size is smaller in the image?
10. With your hands facing a camera, take the gradient direction of several pictures of your open hand, a
closed fist and a “thumbs up” gesture. Collect histograms of the gradient direction in a window around
your hands. This becomes your trained “model”. Now run live and use the various histogram matching
techniques to see how well they can recognize your gestures.