New Object Recognition Algorithm Learns On the Fly

← Back to Stories (view on slashdot.org)

New Object Recognition Algorithm Learns On the Fly

Posted by samzenpus on Monday January 20, 2014 @07:47AM from the we'll-do-it-live dept.

Zothecula writes "Scientists at Brigham Young University (BYU) have developed an algorithm that can accurately identify objects in images or videos and can learn to recognize new objects on its own. Although other object recognition systems exist, the Evolution-Constructed Features algorithm is notable in that it decides for itself what features of an object are significant for identifying the object and is able to learn new objects without human intervention."

21 of 100 comments (clear)

Min score:

Reason:

Sort:

I could be wrong... by barlevg · 2014-01-20 07:49 · Score: 2, Insightful

...but I don't think an evolutionary algorithm approach to pattern recognition is anything new.
1. Re:I could be wrong... by Anonymous Coward · 2014-01-20 07:57 · Score: 2, Funny
  
  The big news here is that it's being trained to detect bullshit. It's currently 0-10.
2. Re:I could be wrong... by durrr · 2014-01-20 08:30 · Score: 4, Interesting
  
  The way I understand it is that it identifies recurrent features and learns them. Meaning that giving it a huge image library with no labels would mean it can recognize say, roses, but it would call them "object 193131", not "rose".
3. Re:I could be wrong... by fatgraham · 2014-01-20 08:44 · Score: 2
  
  This can't be far off, I read a paper a while ago (still trying to find it, this post is a bit redundant without it) which would "detect" the capital of a country from how often they were found in text together. (Probably pre-loaded with country names, this would just have the image as the needle)
  I'm sure "Object 1387" and "Nyan cat" will soon be matched :)
4. Re:I could be wrong... by Anonymous Coward · 2014-01-20 08:59 · Score: 5, Funny
  
  Well, you know what they say... "a rose by any other name would posess eigenvalues closely matching those of object 193131."
5. Re:I could be wrong... by timeOday · 2014-01-20 09:56 · Score: 3, Insightful
  
  There is no way an image-based unsupervised algorithm can learn to recognize objects. "Shapes that frequently go together," yes. But what we consider "objects" is not an objective reality, it is a mental construct that is largely functionally-determined. It will never figure out all the different forms to which we ascribe the label "chair."
  Sitting on a street, a "bicycle" is an object because it is most like to be operated on as a unit. But to a bicycle mechanic, a bicycle is a collection of objects, such as a frame, a seat.. and so on because they need to decompose the "bicycle" construct to do their job. To somebody on an assembly line putting together bicycle seats, a seat is (at least initially) several different objects.
  So, truly unsupervised algorithms cannot do useful recognition - that is, classify objects the same way people do. (A robot that could experiment with its environment and learn to use "objects" could come closer).
6. Re:I could be wrong... by JanneM · 2014-01-20 10:25 · Score: 2
  
  So, truly unsupervised algorithms cannot do useful recognition - that is, classify objects the same way people do.
  That's an overly narrow defintion of "useful recognition".
  
  --
  Trust the Computer. The Computer is your friend.
7. Re:I could be wrong... by Lamps · 2014-01-20 11:18 · Score: 2
  
  The unsupervised algorithm discussed in the article seems to code some sort of visual input and, I'd infer, to perform clustering, which permits it to assign labels (i.e. let's say, 'tree', 'human', etc.) to objects it has encountered. It can use this schema which it has constructed to assign objects it hasn't seen before to a cluster - that is, it labels novel inputs in accordance with its schema. Thus, the algorithm 'recognizes' classes of objects. I'd imagine if you granularize the detail level of detail to which the algorithm pays attention, it can recognize (categories of one object)/particular instances of a general object category/a particular object.
  
  Sitting on a street, a "bicycle" is an object because it is most like to be operated on as a unit. But to a bicycle mechanic, a bicycle is a collection of objects, such as a frame, a seat.. and so on because they need to decompose the "bicycle" construct to do their job. To somebody on an assembly line putting together bicycle seats, a seat is (at least initially) several different objects.
  That goes way beyond the task of 'classifying objects', which is what the algorithm is intended to do. It's like expecting a mechanic to drive your vehicle for you once he has repaired it.
  
  So, truly unsupervised algorithms cannot do useful recognition - that is, classify objects the same way people do. (A robot that could experiment with its environment and learn to use "objects" could come closer)
  Sure, the algorithm doesn't entail a neurological equivalent of what humans to classify objects, but the effect is the same, no? Is not the task of accurately classifying objects useful in and of itself? For example, how would you build said robot that can manipulate objects in a useful fashion if it cannot recognize the objects in its vicinity?
Enhanced reality by Gaygirlie · 2014-01-20 07:59 · Score: 2

I know it's popular for people to immediately start with all the Terminator-claims and whatnot, but that's not the first thing that comes to my mind when reading stuff like this. Personally, I think of coupling this with something like e.g. Google Glass, so that you can tell the system to identify the item in the center of the view and then ask for it to automatically search for instructions on use or repair or whatnot. Even better if you have a device that covers both of your eyes so that the system can overlay things in your whole visual field, identifying things and showing their connections and whatnot.
1. Re:Enhanced reality by icebike · 2014-01-20 08:15 · Score: 2
  
  Like I've said in the past, mankind simply can't seem to stop itself from building Skynet piecemeal. Too dumb and trusting to think all those interesting things could ever be made into weapons or instruments of control.
  
  --
  Sig Battery depleted. Reverting to safe mode.
Re:Bah ... by K.+S.+Kyosuke · 2014-01-20 08:00 · Score: 2

If not, it will probably be hilarious to see the results.
Let me check...BYU...sex toys...yes, it probably would!

--
Ezekiel 23:20
Re:Evolution at BYU by ComfortablyAmbiguous · 2014-01-20 08:27 · Score: 5, Informative

At least there's one professor at BYU that believes in evolution!
I understand why it might be tempting to put BYU in a basket along with the rest of the evangelical christian universities. However, on the issue of evolution it could not be more different. I graduated from there with a degree in microbiology and my college at least evolution was the coin of the realm, just like it is in any serious biology department. I did not have a single professor that did not see evolution as you might expect a biologist to see it; as the only serious explanation of the data at hand, the only theory that works with what we know and provides valid predictions of future results. Not once did I hear even the smallest bit of credibility being given to creationism or its various variants (intelligent design, etc).
And yes, my professors were all Mormons. You might ask yourself how they square this. It turns out that while there are certainly Mormons that take a very literal reading of the bible on this issue, that is not the official church position, and there are many members that don't see it that way at all. Basically I had several professors that explained it as religion was about how to live life, science was about how life works, and we really have no idea how the two come together. The bible, while providing a lot of information to believers on a moral life, provides no real information on how the world works in any of the scientific fields.
Interestingly, many believe this is on purpose, that God has no interest in proving his existence; it's a matter of faith for a reason. Because of this He stays out of offering scientific explanations. I realize that sounds distinctly like a cope-out, but frankly it leads to a fairly rational place where you can function as a scientist an still be a Mormon. And by function I don't mean some half-way hands over eyes sort of a way, but in a real, go where the evidence takes you sort of a way.
Take it for what it's worth, but that was my experience
On the fly, but.... by fatgraham · 2014-01-20 08:28 · Score: 3, Insightful

Does it work in real time? I can't find any more information than marketing buzz in the article (and the BYU article)...
Is there a paper or anything with a bit more [technical] detail?
1. Re:On the fly, but.... by FriendlyStatistician · 2014-01-20 08:59 · Score: 2
  
  Here's the journal article:
  http://www.sciencedirect.com/science/article/pii/S0031320313002549
Paper? by StripedCow · 2014-01-20 08:41 · Score: 2

Anyone got a link to the actual paper?
I wonder if this can be used for image compression. Because if you know e.g. what a bicycle looks like, you don't have to compress it.

--
If Pandora's box is destined to be opened, *I* want to be the one to open it.
1. Re:Paper? by wagnerrp · 2014-01-20 08:52 · Score: 3, Informative
  
  Data compression is often considered to be a key component of artificial intelligence. There is a competition that gives out prizes for compression of a sample of the Wikipedia database.
Re:Evolution at BYU by DownWithTheMan · 2014-01-20 09:37 · Score: 2

I graduated from the Y too - and while most of my professors were not irrational about science, much of the student body was. I had a professor in a 100 level geology class who would start off most of his lectures by saying, "Now I know for some of you, your testimonies may tell you the earth is only such and such many years old. I'm not here to rock your testimonies or shake your faith, but simply to present scientific evidence as we understand it today."

I laughed every time he had to make a disclaimer to the believers about the validity of his lectures (and then face-palmed myself for going to a school where so much of the student body sticks their heads in the sand).
*Sigh* by Wootery · 2014-01-20 09:53 · Score: 3, Interesting

notable in that it decides for itself what features of an object are significant for identifying the object and is able to learn new objects without human intervention
For Christ's sake. The AdaBoost face-detection algorithm - the one that everyone uses today - does precisely this, and was developed in the the 90's.
PDF or it did not happen by jopet · 2014-01-20 09:56 · Score: 3, Insightful

Why should I get excited about something written by a journalist where there must be something writeen by scientists? Where is the PDF of the scientific paper to download?
actual link to paper by Anonymous Coward · 2014-01-20 14:02 · Score: 3, Informative

team,
fyi: http://contentdm.lib.byu.edu/utils/getfile/collection/ETD/id/3021/filename/503.pdf
-me
1. Re:actual link to paper by pmontra · 2014-01-20 19:57 · Score: 2
  
  This is the paper. Please mod it up.