Slashdot Mirror
Digital Camera Could Help Sort Fish, Save Stocks
MountainSplash writes "PlanetArk.com is carrying a story about a new camera that "takes a digital photograph of the catch which is then divided into a grid, allowing a computer to measure the shape and color of each fish in the grid. It needs one tenth of a second and identifies 98 percent of fish correctly." The claim is that fish can then be culled quicker possibly increasing the likelyhood of survival for the incidental catch in the net. Testing is being done by Norway's Institute of Marine Research and Norwegian marine electronics maker Scantrol. Onboard testing has proven highly successful, but underwater attempts still need more work. With everything we have all been seeing computers do the last few years, I personally found this to be one of the more interesting of late."
And i first read it would recognize socks - would be a great invention if built-in in laundrys: Never loose a second sock or try to find the one you are missing !
Spelling mistakes: My is english spoken not tongue of mother.
I'd be forced to add cartoon drawings of 'charlie' from starkist into the 'endangered' database
Somehow I doubt that there will be much of a migration into any kind of system such as this. A large proportion of the fishing industry uses as little technology as possible as break-downs cannot be repaired until the ship returns to port, maybe not until after then. That would mean a large amount of losses for a fishing company. There is no point over complicating things that can be achieved simpily.
The story fails to mention when and how the picture is taken. I believe for this to be effective, no two fishes must be too close nor on top of each other. Anyone has more technical details on the process?
DrkBr
...but I seriously doubt that the fishing industry will adopt this without legislative mandate. What happens now is that when fisherman haul in a catch, they sort out all prohibited/undersireable fish. They throw overboard that bycatch regardless is the fish are alive or dead. There is no record of what their bycatch was and they suffer no consequences for this bycatch. With this system, there is now a record of the bycatch and it will provide empirical proof of the bycatch problem and therefore ammo to those looking to clean up the fishing industry.
Who are you? The new #2 Who is #1? You are #617565. I am not a number, I am a free man! Muhahaha.
If only the system could help sort trolls on Slashdot. *Sigh*
This is just one example of the increased power of automated pattern recognition. Once computers reach a level of vision close to humans, we will se an explosion in automated tasks. Other examples include Sony Aibos vision, lip-reading software that helps in speech recognition, 'robot scientists' and the next generation of speech recognition with the potential to revolutionize human computer interaction. HAL, is that you?
Is the real problem that we're killing too many of the fishes we didn't intend to catch? Or is it that we're catching too many fish?
Don't forget that quick sorting is only part of the problem, not the whole thing. Another important factor is that fish are wounded/damaged by the nets even if they are smaller than the holes, they lose scales and the wounds get infected (hence they end up dying anyway). This has been somewhat improved with modern nets but still needs work.
Anyway, props to them with this new system. Despite what the tree-huggers may say, we need the fishing industry to feed ourselves, and the better we can catch the appropiate fish while leaving the rest undisturbed, the better.
---- Take the Space Quiz!
Gee, I wonder what kind of pattern matching/classification algorithm it is using. 98% is pretty damn high. Really high. That is a very robust algorithm indeed.
If it can be applied to fish, it can be applied to nearly any kind of object that needs to be identified. I would really like more technical details, as I am very sceptical of this 98% business.
Searching for 'automatic "fish classification"' doesn't turn up much...
I'm guessing it's a neural network or some other sort of classifier that has been trained with existing pictures of fish.
The Official Steve Ballmer Webpage
IAACVPS (I Am A Computer Vision Ph.D. Student), and I'd like to add some general remarks concerning this application, and concerning computer vision in general.
Although the article mentions a nice application of computer vision, it is shockingly sparse in details. This in itself is not so strange for a news-site, but the fact that they didn't include a link to a more detailed description is a pity.
Some ideas:
First, the article doesn't make sufficiently clear whether one looks at the net, full of fish, or that one looks at the fish all spread out on a flat surface. If one looks at a full net, one can only see the fish on the outside, i.e., only a small fraction: that doesn't provide any information on the fish on the inside. If one looks at the fish spread out on a flat surface, one can see all the fish, but there are a number of issues here:
Given the speed at which they process, it's most likely that they determine fish-size based on general statistical properties in different regions of the image. In that case, the 90-something% accuracy really doesn't mean that much, because in all honesty, I don't see how they can either measure or guarantee that. Looks like marketing optimism to me.
Now, on the general state of computer vision: If you're expecting terminator-like all-seeing computer in the near future, don't hold your breath! It might take some time:
At the moment, some object classes that don't vary too much in structure within the class (e.g., faces, cars, people), can be found reasonably quickly and moderately reliably in an image. To give an example, the detection of human faces in 800x600 images can be done in about a second, with about a 90-95% detection rate, but with about 1-10 false positive detections per image. That effectively means that if you find a face, there still is only a 30% change that it's actually a face.
In order to understand what you see, you rely on high-level semantics. These include the geometrical arrangement of objects (e.g., your head stands on top of your body, there is a hierarchy body->limbs->extremities, etc.) and general relations (e.g. finding faces at eye-level, so e.g. near the horizon). Research on these higher-level semantics is really in its infancy: the main problem is that it's very hard to get enough "world-knowledge" into the computer for it to make all the relations.
I can put a nice multiple-frame face-detection demo here, but that would destroy my research group's net-connection. If someone can offer a high-bandwidth spot, mail me: I'll then make a movie available.
Support a Europe-related section on Slashdot!
so we can recognize fish but not faces? this is the same technology that so miserably fails to recognize faces in real life but works so marvelously in marketting demonstrations.
stop being so fucking greedy with your satellite fish finders and 5 mile fishing nets
i have absolutely no sympathy for industries that through only their own greed and short term stupidity put themselves out of buisness, fishing had survived for thousands of years till fish finders,5 mile nets, 10000 ton ships etc etc, you don't have to be a fucking genius to work out their real problems are, and they think taking pictures will help them
the phrase "did they really think it would last forever"
comes to mind
of course greed is the behaviour mankind will realise is wrong after we have pissed away all earths natural resources and we are left sitting on a dust ball wondering what happened
A>S
The company I worked for a couple years back was a seafood company. I worked at a clam processing plant and they used digital camera's and computer software to take a picture of each clam as it went along the conveyor belt. The computer then graded the clam depending on size and colour. They have been using this process for atleast 4 to 5 years now.
The Good Life