Monday, January 30, 2012

Recognising Fingertips

Pulling an all nighter is always rewarding , so Friday night I made my first attempt at detecting the fingertips on the hand. Most people use the "convex irregularities" method. I really didn't like that method. It seems sloppy and doesn't detect all fingers. I prefer the kcosines method as described in "Vision-Based Finger Action Recognition by Angle Detection and Contour Analysis".

These are the results of my first attempt.

This week I'll concentrate on making tracking and contour extraction more robust because as you can see at some points the contours break up. I guess selecting my wooden office desk as a testing area proved to be quite a challenge.


  1. Hey nikolas, is this able to detect hand even if some skin color object is behind ( overlaps ) with hand ??

  2. If you visit my youtube channel you can see that I have some what managed to do that.
    The problem is preventing it from leaking.

  3. Hello..

    What is the value of your
    acceptable error when you compute for the error between chord and arc?