One of the major justifications for implementing machine vision inspection is that computers are much better than people at performing inspection. The human mind tends to wander, which is why parts with glaring errors or defects still get past end-of-line inspection.
And this is why, with a nod towards topical matters, I was interested in this article on the BBC web site, “Would you trust the human eye to spot a bomb?”
The point writer Chris Yates makes is that security screening equipment is only as good as the people who look at the images. You could have the best explosive detector in the world, but if the guy looking at the screen has been on duty six hours what are the chances of him catching a positive indication? More than likely, his eyes will have glazed over and he’ll scarcely know what’s being displayed.
Inspection is a crappy job for a human to do, because we are not able to maintain constant vigilance. This is why I’d be happier if the scanner images were analyzed by software, with suspicious indicators being flagged for human review.
A few false positives are preferable to one false negative.
Showing posts with label inspection. Show all posts
Showing posts with label inspection. Show all posts
Tuesday, January 5, 2010
Monday, April 20, 2009
Machine vision success story
Machine vision is not new, yet I’m still surprised by how many people in manufacturing treat it with a suspicion usually reserved for politicians and emails from Nigeria.
News flash folks!! Machine vision is a proven technology. It works!
That message should be reinforced by this case study culled from Quality Magazine (March 30th, 2009.) In “Quality at 400 Blades per Minute” Managing Editor Maggie McFadden describes a factory that has made vision part of its standard equipment.
The part that really caught my eye was this: “… with 10 million [razor] blades made at the plant daily, it’s impossible to rely on the human eye for inspection.” The article then goes on to list some of the machine vision applications to be seen in the plant.
Notice how people at the plant dismiss human inspection. Although the justification is not spelt out, I think it’s safe to assume that:
(a) An awful lot of inspectors would be needed to 100% inspect 10 million blades per day. And at a fully loaded cost of say $20 per hour, (the plant is in the US,) that would make the product just too expensive for the market, and
(b) If we accept the oft-quoted figure of human inspection being only 80% effective, there would be the potential for a lot of poor quality blades to reach retailer’s shelves (and perhaps my chin.)
So the smart people at the plant just put machine vision to work. And I’m willing to bet that the more systems they install, the easier it becomes. It’s just a learning curve thing; give it a go, you might like it.
News flash folks!! Machine vision is a proven technology. It works!
That message should be reinforced by this case study culled from Quality Magazine (March 30th, 2009.) In “Quality at 400 Blades per Minute” Managing Editor Maggie McFadden describes a factory that has made vision part of its standard equipment.
The part that really caught my eye was this: “… with 10 million [razor] blades made at the plant daily, it’s impossible to rely on the human eye for inspection.” The article then goes on to list some of the machine vision applications to be seen in the plant.
Notice how people at the plant dismiss human inspection. Although the justification is not spelt out, I think it’s safe to assume that:
(a) An awful lot of inspectors would be needed to 100% inspect 10 million blades per day. And at a fully loaded cost of say $20 per hour, (the plant is in the US,) that would make the product just too expensive for the market, and
(b) If we accept the oft-quoted figure of human inspection being only 80% effective, there would be the potential for a lot of poor quality blades to reach retailer’s shelves (and perhaps my chin.)
So the smart people at the plant just put machine vision to work. And I’m willing to bet that the more systems they install, the easier it becomes. It’s just a learning curve thing; give it a go, you might like it.
Sunday, June 22, 2008
Aiding human visual inspection
I hear two reasons for replacing end-of-line inspectors, (those cheerful ladies usually found in pairs at the end of the production line.) The first is that they cost too much and don’t add value, (although I think avoiding shipping bad product might have some value to the business.) The second is that they make mistakes, which is true. They are, after all, only human.
But as I have discussed previously, replacing those jolly souls with vision systems is very, very difficult, not to mention expensive. So let me suggest an alternative: give your inspectors the tools to do a better job.
The first tool they need is good lighting rather than the gloom so often found in manufacturing plants. Make sure they can see what they’re looking at. If you own a light meter, aim for 500 Lux.
The second tool is magnification. Typically we want to find flaws as small as 0.3mm (about 0.012”) and that’s a stretch for the human eye. But the old fashioned magnifying glass too slow and cumbersome. Instead, why not use a video system like the one shown below?
For $3,000 you get a clear, magnified image that allows the inspector to actually see what they are looking for. No, it doesn’t have automatic defect recognition (ADR) capability, but neither does it need a 6 axis robot to manipulate the part or five months of development effort. Think of it as Pareto Vision – for 20% of the cost of a vision system you get 80% of the benefit. Contact Aegis Electronic Group for details.
But as I have discussed previously, replacing those jolly souls with vision systems is very, very difficult, not to mention expensive. So let me suggest an alternative: give your inspectors the tools to do a better job.
The first tool they need is good lighting rather than the gloom so often found in manufacturing plants. Make sure they can see what they’re looking at. If you own a light meter, aim for 500 Lux.
The second tool is magnification. Typically we want to find flaws as small as 0.3mm (about 0.012”) and that’s a stretch for the human eye. But the old fashioned magnifying glass too slow and cumbersome. Instead, why not use a video system like the one shown below?
For $3,000 you get a clear, magnified image that allows the inspector to actually see what they are looking for. No, it doesn’t have automatic defect recognition (ADR) capability, but neither does it need a 6 axis robot to manipulate the part or five months of development effort. Think of it as Pareto Vision – for 20% of the cost of a vision system you get 80% of the benefit. Contact Aegis Electronic Group for details.
Subscribe to:
Posts (Atom)
Posts
