Wednesday, December 28, 2011

Future vision

The end of one year and beginning of the next is traditionally a time to take stock. Magazines, TV shows and yes, even blogs like this, are full of such articles. But as I’m too pushed for time to compose my own, (yes, that’s code for “lazy”,) I’m going to link to and critique a great article of the looking forwards genre, and that’s “Machine Vision: The Future of Machine Vision” written by Ben Dawson and published on the Vision & Sensors site, November 28th, 2011.

Ben makes some great points, most of which I fully endorse. I especially agree with his plea for kinder and gentler algorithms, because I believe it’s lack of ease-of-use that’s holding back the industry. But to expand on Ben’s points, what I’d really like are software tools that seamlessly account for or tolerate changes in lighting. I want the software to understand the difference between an edge and a shadow, and I want it to deal with lighting that changes when someone opens an enclosure door.

Readers might point to PatMax from Cognex as such a tool, but I’m not convinced. Yes it does some of what I want, but I’m looking for it to be invisible to the user. I want the vision system to just understand the difference between a part and its shadow. Is that too much to ask?

One area missing from Ben’s paper is optics. I would love to see smarter optics. I want a machine vision system that can automatically focus on what I put in front of it, and can stay focused even if the working distance changes. My feeling is that liquid lenses will give us this ability within a year or two. It can’t happen soon enough!

Last, Ben has a great product idea. He discusses a room painting app – just snap a picture of your room or house and then recolor it in a paint of your choosing. I’ve actually tried this myself using Photoshop so I think it’s a great idea. What it needs though is a database of the reflective properties of every surface in the image. It also needs to identify what each surface is, and apply those properties. Then it has to determine the light source and model how that light will scatter from the surfaces and how much will reach the camera.

It’s all do-able, it just needs programming. Cut me in for 10% please Ben!

Yogi Berra once said, “It’s tough to make predictions, especially about the future,” and I’m sure Ben’s list, with additions by me, will prove that true. Maybe, just maybe, there’s some game-changing idea lurking around the corner that will shake things up in ways we can’t even imagine.

1 comment:

Anonymous said...

I'm commenting a bit late but there is a system that has Hybrid logic (fuzzy neural) that is made from Italian company VEA: VEDO. maybe you could give it a try, they did a demo to us and it was quite impressive.