Latest results

As part of my hand tracking project I post these last videos. I believe I reached the top of the performance of the particle filter algorithm.

Unfortunately I want even better results so I should move to more complex algorithms. The problem is that real time performance is going to be much more difficult to achieve.

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.

Extracting and stabilizing contours

It's been a busy week. I'm now at the stage of contour extraction. Using my adaptive skin classifier and the samples gathered from the detector I build a histogram model for the hand and extract the contours around it. As you can see it is quite robust and works under different illumination. All these are possible with the assumption that the detector doesn't return a false positive. While HAAR cascades are fairly good at the job they don't have a 0% percent of false positives so I intend to add a Fourier hand validator.

Well I'm getting closer...

 

I'm usually very critical of the stuff I make but today I feel quite satisfied with the results.

Hand Tracking Testing

I finished the Particle filter , I tweaked at least a dozen parameters, so I just changed the detector and tried to track my hand. It still needs a lot of work but it's going well.

PS, haar cascade training failed after 2 weeks of computations, yippie !!!

The waiting is killing me

On October 29th I started training an hand detector using the Viola/Jones method and the openCV tools. I used 12k positive and 20k negative samples.
Today the training completed and the results were a bit off. I had a lot of false negatives. I collected lots of texture samples usually found in 3d modelling sites and started the training again with 32k positive and 32k negative samples. Hopefully the results will be better.

In the meantime I will keep using the old detector and concentrate on developing the tracker.