New Algorithms Improve Image Search 111
bc90021 writes "Electrical engineers from UC San Diego are making progress on an image search engine that analyzes the images themselves. At the core of this Supervised Multiclass Labeling system is a set of simple yet powerful algorithms developed at UCSD. Once you train the system (the 'supervised' part), you can set it loose on a database of unlabeled images. The system calculates the probability that various objects it has been trained to recognize are present, and labels the images accordingly. After labeling, images can be retrieved via keyword searches. Accuracy of the UCSD system has outpaced that of other content-based image labeling and retrieval systems in the literature. One of the co-authors works at Google, where the researchers have access to image collections at the largest of scales."
Cool! (Score:4, Interesting)
Snarkiness aside, this is pretty cool stuff. I hope to see usable OSS code in a few years. Imagine how cool it would be to query "show me all pics with my daughter and her rabbits" and have it week through the 1000's of digital family photos.
Probability (Score:4, Interesting)
The probability is either zero or one, because whether or not the feature being sought is present is a state of nature. It would be more helpful to call this number the confidence that the feature is present.
A military system I saw on a TV program ... (Score:5, Interesting)
Then they introduced it to a new batch of images and it fell apart.
Turns out that the initial set of images had all the tanks shot on a sunny day and all the tankless images shot on a cloudy day (or vice versa). It had learned to tell a sunny day from a cloudy day.
Ha ha.
Re:Cool! (Score:2, Interesting)
(Even if it is, I don't want to trivialize the road from theory to practice, I just want to know what's different.)
I did something a little while ago where I had a program search through text, and for all occurrences of all n-character strings (where you choose n) appearing, it would gather the information about how often each other character comes after each string appearing in the text. Then you'd give it an n-character string and it would use those probabilities to generate a new body of text. It was cool, even if it generated complete garbage except for large n.
I hope to see usable OSS code in a few years.
You mean for this algorithm, or at all?
Re:Probability (Score:2, Interesting)
So in Schroedinger's cat, in one universe the cat is alive and in one it is dead, and by observing the cat you only find out which universe you are in?
Couldn't we therefore just say the probability is 1 that the object exists in some universe?
Re:when I was your age (Score:2, Interesting)
Skin detection.....5.5 million hits on Google.
Once you can do this accurately, companies like McAffee and Norton can scan the internet and database pr0n sites for the whole web. Keep in mind that there's a subscription service that allows a Norton database to filter websites for them.
Parents...
Parent not just funny (Score:5, Interesting)
Re:Probability (Score:5, Interesting)
For instance, the set of pictures for which the statement "is this a picture of a chair" is true. There is no objective criteria for this. So imagine you have a bunch of pictures and show each one to a thousand people. Sometimes you might get 0 or 1000 "yes" responses, but often you'll get some number in between (because there are chairs, but barely visible, the picture includes a kids booster seat, or a rock big enough to sit on). This could be interpreted as a probability that somebody will consider a picture to be of a chair.
Re:Cool! (Score:3, Interesting)
Hotness = BeautyFactor * SexyFactor * AgeHotnesseAdjustment
AgeHotnessAdjustment = cos(2*(Age-18)/3.14159)
Gives you maximum hotness at 18, falling slowly in the 20's, dropping rapidly after that.
Also, some hotness under 18 (lets be realistic!) , but not too far under 18
Re:Cool! (Score:2, Interesting)
Try something like this
if age<18: AgeHotnessAdjustment = 0
else: AgeHotnessAdjustment = 1/exp((Age-18)/20)