0
votes

I am developing an eye tracker application in emgu CV, To track eyes i need to detect iris accurately ,So i used hough circles , but in some cases it fails because the shape of iris is not a perfect circle, So i decided to convert eye image in to binary and detect iris ,

To convert it to binary i used

grayframeright_1 = grayframeright_1.ThresholdBinary(new Gray(threshold_value), new Gray(220));

and the result is

enter image description here

Now how can i detect iris in the above binary image ?Can i run blob detector to detect iris ?

Please help me to figure this out, your help will be highly appreciated , I am running out of time for my deadline.

Providing code sample would be useful

Thanks in advance

1
What does this have to do with C#? What have you tried? - Adam Modlin
Actually, it doesn't have to do with any programming language despite the fact maybe he's coding it in C#. - pid
I have tried blob detection but it is detecting whole image as blob... I am implementing this application in emgu CV. - gouthaman93

1 Answers

0
votes

You can try erosion. I've used it in a image processing class at university to find the visual center of airplanes in the sky and it worked surprisingly well.

Erosion is a fairly simple operator used in broader practice like blob detection, which you already mentioned.

Erode should remove border pixels of irregular shapes, leaving at last, just a moment before the shape completely vanishes, only few pixels. The geometrical center of those pixels is c, the visual center of the irregular shape. Starting from c draw a circle of radius r which is completely inscribed in the irregular shape. The circle at c with radius r is an approximation of the iris. Or at least so the story goes.

When I say erosion I mean this: example of erosion

This was just my personal idea based on university work, I've never done this in the industry.

Maybe you should look at a more serious approach to the problem which does not use erosion but wavelets: Iris recognition

I'm very curious. If you try this could you please share your results/findings? A quick comment would suffice!