One thing to remember in the panic over automation killing off jobs is that handling the normal case is maybe 20% of the work. Handling routine errors is 80% of the work. Handling the errors that crop up once in a thousand parts - or dozens of times in this small sample - is why running lights-out is so difficult, and why we'll always need human operators and maintenance staff who can diagnose and correct unexpected problems.
That said, I'm at least 97% confident that OP, in manually counting and marking down these 27,000 items, mis-counted or mis-marked at least once. So I'm not feeling too bad about my pessimism regarding the automated solution. Even if it can't identify if a given sample is "gross" or not, it will add 1 to a counter reliably!
Also, one test of 468 bags that shows one result does not prove anything about the average number required. You'd need to run this test many times for that, and for that you'd need automation!
The only requirement was a hopper for the teacher to dump the skittles into at the beginning. She would have a different amount for each group that was pre-counted and our numbers had to match hers at the end within a certain % of error.
It was a month+ long project and really fun to see each team's solution in how they moved/sorted/stored the final product. Some teams used long conveyor belts, others used short stacked belts, etc. It was all really interesting and I thoroughly enjoyed it!
Designing a hopper was a recently project for me and it was really fun. I learned a bunch about mass flow and realized that there are all sorts of interesting industrial problems involving hoppers.
I ended up learning there is a whole area of computer vision in industry- relatively "boring" stuff like just looking at a line of bottles going by. I went on a tour of the money making machines in DC and they stream sheets of bills by industrial vision cameras to detect whether the bills are within QC.
Still amazes me people get paid to do this. To me it's just like a big fun game.
I was thinking that time could be saved by not sorting the skittles so nicely. Just take a picture of the skittles from each bag spread out randomly. You should be able to figure out the color distribution just by counting pixels within each color range.
"That's why we built Loppy the Chopper over there."
The only difference is, I normally spend my time automating the process with computer vision (a skittle sorter/counter wouldn't be that hard to build; opening the bag is harder than identifying colors). And then I never really finish the project.