0

I need to implement algorithm for eye gaze to know the direction of eye using opencv ,

i have been struggling for one month to do it using viola-jones algorithm with training classifiers provided by opencv

in a first step i based my research starting with facedetection.cpp with xml's for face and eye , it can detect faces and eye just for < 1m but i haven't found a method to know the eye direction

Now after some research , i've found some algorithms for eye-gaze but i don't wich one to chooose in term of it simplicity (because i'm just a newbie) and efficiency :

Distance-Threshold Algorithm

Mean-Shift Algorithm

Edge detetction ==> Hough Transformation

the Longest Line Scanning Occluded Circular Edge

Matching “one-circle” and "two-circle" algorithm

Neural network based approaches

Principal component analysis (PCA).

Starburst Algorithm

Kalman filter Velocity

Threshold Eye Movement Identification

Active appearence model (AAM)

CCL : Connected component labeling algorithm

CCA : colonial competitive algorithm

Blob detection

Lucas Kanade

So what algorithm you recommended me , and if there is another algorithm algorithms that i haven't mentionned , i need also a comparaison between those algorithms but it must be someone experienced in this field NB : i'm using ubuntu 14.04 and developping with C++

Any help will be much appreciated , thanks :)

Community
  • 1
  • 1
The Beast
  • 1,629
  • 2
  • 29
  • 42
  • I think you are approaching this the wrong way; it does not matter how fast an algorithm does NOT work. Meaning focus on getting something to work first worry about complexity later. – Pandrei Jul 27 '15 at 13:04
  • @Pandrei but you cannot make something work if it's so complex , i don't want to start an algorithm wich is worse than the others .... i need the best algorithm for eye direction so i can mimimize the time and effort for looking for smth else . thanks you – The Beast Jul 27 '15 at 15:21
  • There is no such thing as the best algorithm for a complex task, all algorithms have strengths and weaknesses, on some cases they will perform brilliant and not so good on others. You really have to decide yourself which one is best for you. – Pandrei Jul 28 '15 at 08:12
  • @Padrei , this the problem man , i don't have the status to decide the algorithm that is best for me because simply i haven't used any of them in the past and it the first time that i discovered them ... maybe someone how work on image processing and opencv could help :) – The Beast Jul 28 '15 at 08:57

0 Answers0