This week turned out to be unexpectedly much slower for me due to some projects being due and a round of midterms.

Overall, the goal was to pick out some pictures of human beings, provide them to the OpenCV program that I have so far, and be able to accurately detect the eyes (hopefully, more specifically, the pupils) in the photo.

That did not go so well despite hours of tinkering with the parameters:

I spent some time trying to tinker with all the SimpleBlobDetector parameters to try and get a combination that would detect only his eyes (or be able to detect at least his eyes and potential other stuff). Unfortunately there was nothing that would work. My speculation is that this may be due to the picture quality/shade.

For next week I shall try to use this same process with other pictures to get a feel for the parameters and how they work. Once I get used to that, if I’m able to make quick progress, the next big step would be to develop an algorithm / some sort of code that does blob detection on the live webcam.

Ultimately, once I’m able to get to that point, the plan is probably to use OpenCV’s checkerboard features to detect some kind of checkerboard pattern applied to the forehead to calculate the distance between the two detected pupils.