Slashdot Log In
Searching by Image Instead of Keywords
Posted by
samzenpus
on Wed May 04, 2005 08:00 PM
from the find-me-something-square-and-green dept.
from the find-me-something-square-and-green dept.
Content based image retrieval (CBIR), the technique to search for images not by keywords, but by comparing features of the images themselves has been the focus of much research ever since the web emerged. Consider for instance adding CBIR to Google Images, where you would be able to search for images similar to a query image instead of using keywords. A research project at Penn State University has recently been applied to the biggest aviation photo database in the world with close to 800,000 images. You can search for images similar to a photo already in their database (click "View similar photos") or submit your own query image. Some queries generate better results than others but CBIR is certainly here to stay and will be standard in many image applications of the future.
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Think of the greatness to society! (Score:5, Funny)
Re:Think of the greatness to society! (Score:2, Insightful)
http://www.airliners.net/similarity/index.php?ima
BTW, if you want to post other searches, this URL format seems to work.
Skin Cancer Detection (Score:3, Interesting)
I always felt good about working on projects like this, gives a warm fuzzy feeling.
False positives (Score:3, Funny)
Its almost like telling someone to go to whitehouse.com
Arm jokes... (Score:2, Funny)
Location? (Score:5, Funny)
Old photos (Score:3, Interesting)
Re:Old photos (Score:2)
Re:Old photos (Score:3, Informative)
It's an amazingly scary experience to sit there at night when a large plane is landing.
Re:Old photos (Score:3, Informative)
In fact, there is a bar [sunsetbeachbar.com] located right in the flight path of the runway. I just met a guy who came back from there, and said it's quite interesting to have planes landing so close to you.
Re:Old photos (Score:3, Informative)
"The island is served by many major airlines that bring in large jets, including Boeing 747s, carrying tourists from across the world on a daily basis. This fuels the island's largest revenue source, tourism. The airport is famous
Re:Location? (Score:2)
It says where just below the picture.
Re:Location? (Score:2)
Re:Location? (Score:2)
1) These photos are not digitally edited. This beach and airport is real.
2) It is not an awful beach; it is the holy grail of aircraft spotting, and a place that most aviation enthusiasts (myself included) would like to visit someday
3) If you say 9/11 in relation to this subject, such as, "OMG! it's unsafe there will be terrorisms LOLZ", I will be forced to kill you.
Re:Location? (Score:2)
1) Never thought otherwise.
2) Presumably, the aircraft are the reason you want to visit this location. It's certainly not the sand and water. In short, I stand by my assessment.
3) I didn't say it, but somebody else did in reply to my post.
Girl wearing thong looking at something in the air (Score:2)
Wow (Score:5, Interesting)
It will be interesting if we ever get to a stage where we can just search for a random object (or person) in a database of photos. Then you could take pictures of everything with an always-on camera and if you need to find where you put your car keys, just do a search.
Re:Wow (Score:2)
Re:Wow (Score:2)
Dunno about that. Here's what I get after clicking on a picture of an A-10 Warthog: A Tornado, a 767, a 747, A Fokker F-7 turboprop, a Dassault Falcon business jet, a Luftwaffe A310, a Harrier, an F-18 Hornet, another Tornado, a Lockheed P3 Orion sub hunter, a Sikorsky Super Stallion helicopter, a Concorde... and soforth. No other A-10s. Hard to think of a more diverse crop of aircraft.
Most of these aircraft are airborne but a couple are on the ground. If I cli
Re:Wow (Score:4, Informative)
If you are only interested in searching for images on your own computer, have a look at imgSeek. http://imgseek.python-hosting.com/ [python-hosting.com]
It's been around for some time now. You can not only use an existing image to search, but also do a rough sketch. Check the screenshots: [sourceforge.net]
Nice complement to what has been presented in this article.
Parent
They would need major manpower to maintain this db (Score:3, Funny)
They would need a team of outsource Indian workers to go through each picture one by one!
I am not Indian but...can I apply for the image filtering job?
I said this first, I should get the job
Re:They would need major manpower to maintain this (Score:2)
Porn DOES however, make you spell better!
Top Search (Score:3, Funny)
Re:Top Search (Score:2)
Similar images (Score:2, Funny)
1. Airliners.net
A site with almost 1,000,000 aviation images.
Wow !!! I tested their Sample search [airliners.net] and all the results were aeroplane photos !!! Ok, ok the site only has airplanes but still
On a more serious note the alogorithms seem to look for similatity in the colors and lighting rather than the subjects (for example it shows the interior of a cabin in photos similar to a whole plane in the sky. To really see its effectiveness we need to test in in
And for 'lynx' users... (Score:5, Funny)
Some relevant research papers (Score:5, Informative)
* Finding Naked People [hmc.edu] (Fleck et al, 1996)
* Video google: A text retrieval approach to object matching in videos [ieee.org] (Sivic & Zisserman, 2003): web page demo here [ox.ac.uk]
* Names and Faces in the News [columbia.edu] (Berg et al, 2004)
* FACERET: An Interactive Face Retrieval System Based on Self-Organizing Maps [springerlink.com] (Ruiz-del-Solar et al, 2002)
* Costume: A New Feature for Automatic Video Content Indexing [www.irit.fr] (Jaffre 2005)
One more: automatic film character retrieval (Score:4, Informative)
Automatic Face Recognition for Film Character Retrieval in Feature-Length Films [cam.ac.uk] (Arandjelovic & Zisserman, 2005)
The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).
Parent
Re:Some relevant research papers (Score:2)
http://wwwqbic.almaden.ibm.com/ [ibm.com]
that first one is so pointless (Score:2)
and then we have reverse "Googling" for images.. (Score:5, Interesting)
One has to guess the search word which generated a given set of 20 images in google's image search [robinson.name]
When things are moving forward, we have soomthing to talk about "those good ole days" but frankly the game is interesting initially but later gets boring due to the frequent repetitions..
Re:and then we have reverse "Googling" for images. (Score:2)
http://www.spilth.org/pictures/girls/ceren/jkh-and -babe.jpg [spilth.org]
Impossible!
Is it just colour? (Score:5, Interesting)
What I got was an awful lot of red planes - some of which were actually Qantas planes, but I think more by coincidence (i.e., they're red) than design. Many images had nothing to do with Qantas, or even a red plane - they simply had a lot of red in the image.
This is impressive in some ways, but in others it seems like it's simply looking for similar patches of colour. I haven't done enough testing to see what happens if,say, I gave it a half red half green image.
Interesting, but not ready for public consumption just yet. A bit like A.L.I.C.E. the artifial intelligence system actually - neat, but not practical. Yet!
Great! (Score:5, Funny)
IP Enforcement Nightmare (Score:2, Interesting)
The big problem to me is specifying input. I know the "look" of the Mona Lisa's smile, but even with the best pen input methods I'd never be able
This reminds me of Gibson's Pattern Recognition (Score:3, Interesting)
How does it do that? (Score:3, Funny)
There is a GNU project related to this GIFT (Score:5, Interesting)
The GIFT (the GNU Image-Finding Tool) is a Content Based Image Retrieval System (CBIRS). It enables you to do Query By Example on images, giving you the opportunity to improve query results by relevance feedback. For processing your queries the program relies entirely on the content of the images, freeing you from the need to annotate all images before querying the collection.
GIFT [gnu.org] It worked pretty well for me in the demos they linked too. I have been waiting for this type of application to gain momentum.
Would it work for animated .gifs? (Score:2, Interesting)
It says "multi lock on" and a date, but all Google reports is other forum posts looking for the creator of the image. Apparently, there's a high-res version of it too.
Pretty controllable test (Score:2)
Now, do this for something like Google Images or PBase or collections spanning infinite numbers of subjects and image sizes,
Re:Pretty controllable test (Score:2, Informative)
Look up Bombardier in the forums on airliners.net, they have frequently asked a photog for permission to use their photos (for pay), then later say they elected not to use them (and therefore no payment to photog). But then they use the photos anyways without payment or acknowledge
Is this a joke? (Score:3, Interesting)
Next experiment: I took a picture of a highly distinctive plane, a harrier, climbing at a steep angle and viewed in profile. I got, in return, a list of passenger jets, and even a helicopter. Hardly surprisingly, all of the result pictures had the same bluish white sky as my original image. That was literally the only similarity.
According to the introduction on the search page the heuristics used compares colors, contrast and shapes in the images themselves. I saw no correlation whatsoever between shapes, and any correlation in contrast seems to be to be the result of the search engine simply looking for images that contain the same colors in a similar ratio to the original. In short, nothing to see here, move along.
On the other hand, one of the projects listed under the Penn State University link looks fairly fascinating. The Riemann a-LIP project [psu.edu] (automatic linguistic indexing of pictures) doesn't allow user input of images, unfortunately, but it does show some fairly fascinating attempts at verbally qualifying image data. For example, it describes a blue and orange mandelbrot as pattern agate shimer abstract scene, and a sunset over a lake as Berlin Devon Namibia landscape lake scene. Okay, it may still need some work, but it sure beats the hell out of the "find the same color airplane engine".
Oh, you mean like imgseek? (Score:4, Informative)
Worked on something similar (Score:3, Informative)
I've not RTFA (not had the time), but our approach was to split the images into segments (based on colour and texture) which were assumed to be objects. The segments would then be analyzed for various feature vectors, such as shape, texture, colour etc. These vectors would then be added into a database of numbers, and finally the segments grouped, giving a collection of classified sections which (hopefully) represent similar objects.
From related metadata such as keywords, you could then hope to build up an idea of what keyword matches which section. You could also come up with a relevance between two images, and thus search for similar images.
We didn't have enough time to make it bulletproof by any means, but our limited results were very promising.
Sorry I can't find the paper, but we've got some screenshots of the application here [soton.ac.uk] and here [soton.ac.uk] (you can see false colouring applied to the original image to display the segments)
Re:wtf? (Score:5, Interesting)
Parent
Re:wtf? (Score:2)
I used to do research in CBIR, and in my image library I had 5 photos of a christmas tree. By any efficient metric, one of them was always way far away from the others.
Xcott
Re:wtf? (Score:3, Interesting)
Re:security issues (Score:2)
Re:security issues (Score:2)
On what grounds could the TSA squelch photographers and their right to share their creative works (which is their livelihood)?
Re:security issues (Score:2)
Trainspotting seems to still be around as well, see http://www.railpictures.net/ [railpictures.net].