How does the calibration method find the best threshold for the eye frame? about gazetracking

[antoinelame]

Hello @crissallan,

To avoid users to provide a threshold value themselves, I created an automatic calibration algorithm to find the right threshold value for the user/webcam.

I did some statistics and noticed that the size of the iris is always about 48% of the surface of the eye for all people (when they are looking to the center). Thresholds values to binarize images can differ a lot from person to person, but iris sizes are very stable.

However, I may not have done enough statistics on different types of eyes. Maybe for Asian eyes, the 48% size is slightly inaccurate. But I'm really not sure, I'd have to check it. I don't think the difference is significant, though.

So on the current version, here's how works the automatic calibration algorithm:

• During the first 20 frames, I send them to the Calibration class
• I try to binarize the frame with different thresholds values from 5 to 100 (with a step of 5) and I calculate iris sizes
• For each frame, I save the value that gives the closest iris size to 48%
• When the first 20 frames are analyzed, the final threshold value is the average of the best 20 values

More information there!

[ANYMS-A]

Thank you so much！This is really helpful for me!