Open Source Eye Tracking

Zafer Savas is an electronics engineer living in Ankara in Turkey who has released an eye tracker implemented in C++ using the OpenCV library. The project is well documented and enables crude DIY eye tracking within minutes, hence it is a good starting point. It contains a sample database of eye images used to train the algorithm, the program has a function to capture images so that users can build their own database. Great!

Download the executable as well as the source code. See the extensive documentation.

You will also need to download the OpenCV library.

“The purpose of the project is to implement a real-time eye-feature tracker with the following capabilities:

  • RealTime face tracking with scale and rotation invariance
  • Tracking the eye areas individually
  • Tracking eye features
  • Eye gaze direction finding
  • Remote controlling using eye movements

The implemented project is on three components:

  1. Face detection: Performs scale invariant face detection
  2. Eye detection: Both eyes are detected as a result of this step
  3. Eye feature extraction: Features of eyes are extracted at the end of this step

Two different methods for face detection were implemented in the project:

  1. Continuously Adaptive Means-Shift Algorithm
  2. Haar Face Detection method

Two different methods of eye tracking were implemented in the project:

  1. Template-Matching
  2. Adaptive EigenEye Method

schematics for the procedure/algorithms

Thursday, June 12, 2008

Response to demonstration video

The response for my video demonstration has been overwhelming with several articles and over 7000 viewings in a during the first three days (google neovisus). There has been an interest from the gaming community, Human–Computer Interaction researchers, users and caretakers in the assistive technology sector, medical and science applications such as radiology.

I wish give thanks to everyone for their feedback. At times during the long days and nights in the lab I’ve been wondering if this would be just another paper in the pile. The response has proven the interest and gives motivation for continuous work. Right now I feel that this is just the beginning and determined to take it towards the next level.

Please do not hesitate to contact me with ideas and suggestions.

Thank you.

Monday, June 9, 2008

Video demonstration online

The associated video demonstration for my masters thesis on gaze interaction is now online!
Click on the image to view or download the video.

Thesis release

My masters thesis on gaze interaction, the NeoVisus prototype, is now out! Download it by clicking on the image below.