Machine vision heuristics

If you look up “heuristic” in the dictionary you’ll find that it’s a fancy way of saying “rule of thumb.” But it sounds much more scientific, so I’m sticking with heuristic for now.

And why do I need this word?

Well if, like me, you’ve worked in machine vision for a long time you’ll have picked up many tips and tricks which, while not exactly scientific, enable you to get the job done quickly and effectively. In fact in “How many pixels does it take to find a flaw?” I posited the “Grey Heuristic” regarding the number of pixels necessary to find a flaw.

Well it turns out that Paul Whelan of Dublin City University has beaten me to the punch with a compendium of “Machine Vision Proverbs, Opinions And Folklore,” and I have to say that he’s done a pretty darned good job of it.

Now I want to say that while his list may be funny, it’s also very useful because it’s based, like all heuristics, on actual lessons learned. So if you’re serious about a career in machine vision I encourage you to print it out and paste it somewhere over your workbench. Then, when your customer or boss asks, tell him it’s a set of heuristics. I’ll wager he’ll be impressed enough to leave you alone for the rest of that day.