Slashdot Mirror
Searching by Image Instead of Keywords
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.
I can't wait to put a nipple into it!
(\_/)
(O.o) This is Bunny. (> <)
and set for goatse!
--
"Outlook not so good." That magic 8-ball knows everything! I'll ask about Exchange Server next.
What an awful beach.
After all, I am strangely colored.
I was just thinking about this the other day. I think content-based image search is one of the Next Big Things. Cameras are so ubquitous now (for better or worse), but having to rely on metadata to give meaning to images requires lots of effort up front.
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.
This is just asking for trouble. As most of you would probably imagine, some self-proclaim "comdeian" would post either porn pictures, or pictures that resembles porn body position.
;)
.
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
Because it still has problems - you'll note that the pictures seem to be compared simply based on color similarity. That's the same thing imgSeek does (a great program for sorting and searching your photos) on photo searches. It works wonderfully if you're searching a very limited picture subset (say, airplanes), but if you search a wide variety of pictures, the results can be quite amusing.
It's a Cyrillic alphabet. It's like all those keys you never push on a calculator.
Something with two circles and dots in the middle of each circle.
(\_/)
(O.o) This is Bunny. Add Bunny to your signature
(> <) to help him achieve world domination.
Some Applications of Our Research
..:)
... now you should be able get similar pr0n (^H^H^H^H I mean art) with these algorithms
1. Airliners.net
A site with almost 1,000,000 aviation images.
Wow !!! I tested their Sample search 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 the real world (google images) . The 'artisticly revealing' photo you always liked
Those must be old photos. There is no way that beach would be open to the public in the post 9/11 world.
... the search engine will support ASCII art image searches.
Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
There's a bunch of interesting papers out there on content-based image analysis and retrieval. Below is a sampling from my bibtex file. Does anyone else have others they'd like to share?
* Finding Naked People (Fleck et al, 1996)
* Video google: A text retrieval approach to object matching in videos (Sivic & Zisserman, 2003): web page demo here
* Names and Faces in the News (Berg et al, 2004)
* FACERET: An Interactive Face Retrieval System Based on Self-Organizing Maps (Ruiz-del-Solar et al, 2002)
* Costume: A New Feature for Automatic Video Content Indexing (Jaffre 2005)
I forgot one more, where specific faces were automatically retrieved from feature-length movies and Fawlty Towers:
Automatic Face Recognition for Film Character Retrieval in Feature-Length Films (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%).
Talking about greatness to society and a little bit of skin. At university one of my projects was a system that used CBIR to try and diagnose skin cancer. The doctor would take an image of the suspect area it then would be compared against a database of cancers. It would then return a suggested likelyhood of being cancer. It also allowed the doctor to build a history of images allowing easy comparision over time.
I always felt good about working on projects like this, gives a warm fuzzy feeling.
One has to guess the search word which generated a given set of 20 images in google's image search
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..
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!
Physicist, consultant, science communicator
Now I can find all the other naked pictures of Bea Arthur on the web!
Pattern Rcognition is a novel by William Gibson, basically set in the present day or very near future. Image based search plays a central role in the plot. It's a very good read.
Did you mount a military-grade, variable-focus MASER on an unlicensed artificial intelligence?
I was looking at a picture of a plane on that web site and there was a link that said "Click for similar images". And what do you know? It brought up more pictures of planes. This is amazing stuff. How did it understand that I was looking at a picture of a plane?
Doesn't it make you feel good to know that our freedoms are protected by politicans, lawyers and journalists.
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 It worked pretty well for me in the demos they linked too. I have been waiting for this type of application to gain momentum.
Wax on, wax off baby!
'Coz I'm looking for more information on this image.
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.
Actually, it will be hillarious what will happen when grandma puts in a picture of her grandson taking a drink from the hose in the backyard.
Its almost like telling someone to go to whitehouse.com
Google actually did take this technology and try it. The first version of their image search had a "find similar" link next to every image. These tended to work okay at first (they weren't great, but you usually got enough photos back that you could visually scan them and find something of interest that was related to the original image). After a few months, for some reason, the "find similar" links started returning increasingly nonsensical results. After it degenerated to the point of near uselessness, they took the "find similar" link away from the image search results. I expected it to turn up again once they got the kinks worked out, but apparently they just decided to stop working on it.
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 acknowledgement to the photographer.
So these spotters trawl the web looking for aircraft photos to 'vet' to see if they are stolen from an a.net photographer and band together to stamp out the piracy (sound familiar??????)
I've tried two different images of airplanes; one of a bright red flying car on bright green grass and one of SpaceShip One against a deep blue sky. Both times, the results looked surprisingly like my query images in color composition only. Red planes on grass and white planes against a blue sky. Inauspicious start.
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 (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".
I want the fire back.
Oh, you mean like imgseek?
Purdue also has a 3D shape search. More can be found at Here .
I'm pretty sure altavista had this feature several years ago, but removed it. I remember that it worked fairly well. Does anyone know what happened to it?
I'm sorry. The number you have reached is imaginary. Please rotate your phone 90 degrees and try again.
About a year or so ago, I and three other Masters students worked on a similar project at the University of Southampton.
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 and here (you can see false colouring applied to the original image to display the segments)
We Build Beautiful Websites