2009 promises to be a formative year for 3D and Computer Vision. 3D films are getting all the press at the moment (see this excellent blog on 3D Movies), but this year should bring us much more than just a new dimension from Hollywood.

Just today, Apple announced at MacWorld that its new iPhoto program would have facial recognition built in, following Picasa’s lead of a few months back, and bringing yet another computer vision application to the masses.?? Expect visual search to keep blossoming in 2009, with uses you may not have considered before.

In the next weeks and months, I will have many more posts on the innovative technologies that are going to shape our fields for 2009 and the years to come.?? From computer vision research analysis to 3D film reviews to chipset technology, there is so much to write about, I’m having trouble containing myself and not going on for a few thousand words right here.

To begin an exciting 2009, I’ll be heading to CES later this week, so if you want to meet me there for a chat or a beer, just send me an e-mail.?? Alternatively, you can look for me as I wander around; I’ll be the guy standing in front of the 3D displays, drooling.

Happy New Year to all of you!

Constructive 3D Furniture Demo from joshk on Vimeo.

Usability and time-to-learn are two big concerns with any web application.?? For 3D applications, both of these factors have led to the downfall of some pretty innovative sites.

In the video above, I demonstrate how we use the Constructive technology to refurnish our own conference room in 3D without having to learn any new or foreign process. With a few points tagged in two pictures by an operator, Constructive understands the camera position, orientation, and focal length, allowing me to move around the 3D furniture along the floor with the correct perspective.?? And since Constructive understands the relationship between the photos, moving a piece of furniture (or a French maid, as the case may be) in one photo will also move it with the correct perspective in any and all others.

This application also addresses the issue of scalability; by not requiring any highly trained or skilled work to be done, the simple manual tagging process can be cheaply outsourced or put “in the cloud” using Amazon’s Mechanical Turk.

I look forward to seeing innovative retailers using Computer Vision technology like Constructive to add a level personalization that doesn’t exist today.?? Soon, we won’t have to try to imagine what our new room will look like; you will be able to perfect it before ever putting any money down, and even share your ideas with friends and family to get their thoughts too.?? A mother knows best, right?

All 3D models used come from www.Presto3D.com

Unless you are Haley Joel Osment, odds are you possess 5 senses.?? On this blog, we are focused on how computers can interpret one of those senses, vision.?? It’s the field where we have our technical expertise, and where we believe we can make our biggest contribution to technological advancement (see our current R&D project to turn photos to 3D models).?? However, in the same way that computer vision scientists are trying to help machines understand what they see, the researchers over at mufin are trying to teach computers how to hear.

mufin is an automated music recommendation system that takes a different, one could say more technical, approach to helping you find music that you like.?? Services like Pandora and iTunes Genius use human expertise or song meta-data where mufin actually analyzes the audio content.?? This is from the mufin website:

How does mufin work?

mufin knows the musical essence of millions of songs and connects those songs that have a similar essence. This essence consists of sound properties like tempo, instruments, sound density or harmony. Whether the music is well-known or not, which genre it belongs to, when it was released or where in the world it was made, plays no role when you discover music using mufin. What matters is the sound!

Much like those of us in Computer Vision, Computer Audition scientists sit at the meeting point between art and mathematics.?? As effectively as Computer Audition algorithms can objectively break down music into a series of variables, it requires a subjective human to determine which combination of those variables implies a “similar” song.?? It is this subjectivity that keeps both of our fields fascinating.

Though the early reviews of this site seem to be not entirely positive, the folks over at mufin already have my respect for taking a stab at a truly complex problem.?? Whether mufin succeeds or not, I expect to see Computer Audition techniques applied in other music recommendation services in the future, though undoubtedly in combination with other, more manual, techniques rather than in isolation.

Who hasn’t always dreamed of having a $2000 sculpture of their own head??? I know I have.?? And finally, thatsmyface.com will make this dream come true.?? With the upload of 2 photos of your face, one in front view and one in profile, thatsmyface.com will reconstruct a 3D model of your head in a semi-automatic fashion. This is a pretty neat attempt to bring a computer vision & 3D technology to the consumer market.

The technology behind the site is nothing new.?? I can’t say for sure, but I would be willing to bet that thatsmyface.com is using FaceGen technology, which has been around for 10 years.

Similar?

Still, you don’t need cutting edge technology AND an exciting product to make a successful business; one of the two will usually do just fine.?? Thatsmyface.com now just needs to convince people that what they’ve always wanted was random gear with their head as the main feature.?? For the sake of entrepreneurship, good luck to them!

Today I came across a neat computer-vision based installation/game that was presented at the FILE 2008 expo in Brazil.?? The company that put this together, Colmeia, is an interactive production company that creates digital installations for advertising.?? The game involves using one’s silhouette, reprojected as dark blobs, to block out certain parts on a screen.

Tantalus Quest at FILE 2008 from eduardo omine on Vimeo.

We wrote a couple of weeks ago about Float4, a Montreal-based company also working on interactive display installations.?? I am hopeful that what we are observing is the beginning of a trend, and that in the next couple of years we will see a rising number of computer vision applications in advertising.?? This is certainly a trend that we will be following closely on ENLIGHTEN3D.

Spies rejoice!?? Computer vision scientists at UC San Diego have devised a way to create a duplicate of a key using a only one digital photo, apparently taken in normal conditions.

By identifying a few “key” points (lame pun intended) in the photograph, the researchers are able to extract all the information required by a locksmith to make a copy of that key.?? So, to all our loyal readers in the secret agent and espionage professions, send this report to your R&D department today and get this mildly amusing incredibly practical technology out of the labs!

Read the full article here.

The folks over at the Orkut blog announced a few days ago a new filter for their social network that can screen out “sexually suggestive phrases or images”.?? However, no detail has been published (to my knowledge) on exactly how they filter out these images, whether they use text-based clues or somehow incorporate computer vision to detect the content of photos.?? Until they respond to my e-mail I cannot say for sure, but my guess is that they are using only a text-based filter like the one used for Google Images SafeSearch.?? If this is the case, I doubt it will be as effective on a social network where there are far fewer textual clues to put an image in context than there are on, say, a pornography web site.

Regardless of whether Orkut is using it or not, it is only a matter of time before computer vision techniques drive the next wave of “safe content” filtering.?? As we discussed a few weeks ago, VideoSurf, the video search engine, has already introduced an image/video-based filter.?? Once one major player in search adopts computer vision for content filtering, their competitors will have a strong incentive?? to follow or risk being seen as the “unsafe” search engine.?? Whether or not Google started the trend with Orkut this week, it’s only a matter of time until this application of computer vision hits the mainstream.

The New York Times, that is.?? In what can only be perceived as the deepest form of flattery, last week the NY Times wrote a full length article on the “beautification algorithm”; the exact same paper that we wrote about 2 months ago.?? Personally, I was excited to see a major mainstream publication taking an interest in computer vision, and I hope that our field continues to push into the thoughts of those who are not working directly in it.

Most folks that I encounter who aren’t working directly in computer vision or computer science are unfamiliar with the field entirely, and, more importantly, are unaware of the amazing things that can and are being done with computer vision today.?? In my own experience, some of the best ideas come from those who are not the scientists directly doing the research, but who are working on something completely different yet see the potential of the research in their own, seemingly unrelated, application.?? So, New York Times, show the potential of computer vision to the world!?? And any time you need inspiration for an article, we will be flattered if you come check by ENLIGHTEN3D.

In the last month, Josh and I have had the opportunity to meet with several companies on the cutting edge of the computer vision and graphics field. First, we sat down at SIGGRAPH with the team leaders on Intel’s Larrabee project (the topic of a future post). More recently, we talked to Videosurf CTO Eitan Sharon, our pick for top company presenting at the TechCrunch50 conference two weeks ago. Last week, we got to chat with the founders of a local startup, Float4 Interactive, a Montreal start-up, who is turning image processing and computer vision techniques into an interactive art form.

Although Float4???s custom software technology works with cheap cameras (e.g. eyeToy) and regular screens, the effects are most impressive when displayed life-size using a back-projected display and two high-performance cameras. They provide turn-key solutions and even rent the hardware for special events, such as extravagant wedding ceremonies, industry expositions, and advertising installations.

Applications and clients.

Other companies experiment similar technologies — I remember seeing some at SIGGRAPH ??? but Float4 has raised the bar in interactivity, robustness and aesthetic quality.

Here are a couple examples of the applications of their current technology:

• Move your body to create unique animations (such as juggling a soccer ball)
• Experience the joy of flying like an airplane or a bird, by shifting or waving your arms.

Already, the company has attracted attention from notable clients such as the Cirque du Soleil. Despite our best efforts to pry it out of them, the Float4 folks are staying quiet on exactly what kind of display they’re building for the Cirque. Personally, I’m excited to see how this state-of-the-art graphical technology gets integrated into what is already a visually astounding performance.

Visit Float4 Interactive

With 50 startups launching at the TechCrunch50 conference last week, the blogosphere has been abuzz with high tech news. In all that media frenzy, one company stood out and impressed us more than the rest. Videosurf, a video search engine, combines traditional text metadata search with computer vision to provide higher quality search results. After seeing a video of their presentation at TC50, I wanted to learn more, so I arranged an interview with Videosurf CTO and computer vision expert Dr. Eitan Sharon. The following article is based on our discussion.

How Videosurf Works

Videosurf starts by looking through textual tags and dividing video into shots. Unlike other video search engines though, Videosurf goes much further in its analysis. A facial recognition system goes through the films frame-by-frame, collects faces that look alike in different shots, and tries to match them against the appearance of known actors using the cast information. In the beginning, an operator had to assist the system, but now, most of the common actors are easily recognized automatically.

Here’s an example. I put in a search for “Star Trek”. At the top of the page, I am presented with a thumbnail of people that are associated with my search. In this case the list includes William Shatner, Jeri Ryan, Leonard Nimoy, and Patrick Stewart, all actors who have played major characters in a Star Trek TV series. By clicking on one of the thumbnails (Patrick Stewart), I can find all of the Star Trek-related clips in which Patrick Stewart appears.

From the screenshots, you may have noticed that next to each clip there appears to be a storyboard. Appearing simple at first glance, these “video summaries” actually employ a complex computer vision approach in trying to automatically determine the most “important” frames in a clip. According to Dr. Sharon, creating these visual summaries involves a combination of techniques such as determining the uniqueness or similarity of objects across frames, the depth of field, motion in the scenes, etc. If these automatic storyboards work effectively, and from my own testing they seem to do a good job, this should save users time so that they don’t have to wait for a video to finish downloading just to realize that it is not what they were looking for.

Other Features

Perhaps the feature with the most immediate profit potential is their adult content filter. Though we did not get too far into the details, they have employed a type of “safe search” filter that adds computer vision techniques to traditional text search to determine whether content should be filtered. Like Google’s Safe Search, this filter can be toggled on or off. If I was Yahoo’s chief marketing officer, I would immediately license this technology exclusively for a few years. Then I would run an ad campaign about how our search engine is the only safe place for children on the internet. But that’s just me.

One other neat feature lets you share a specific segment from a video, increasing the viral potential of online video beyond where it already is today.

Will it take off?

Saying “Will I use this?” is not really the most unbiased kind of market analysis, but I can say that I will use this (free!) service now. I already have, actually; having “Videosurfed” 3 times in the past 24 hours since receiving my beta invite, and I am confident that I will keep coming back if it keeps giving me quality results.

From a profitability perspective, Videosurf may have an ace in the hole that they haven’t talked about yet: copyright detection. After Google (owner of YouTube) was sued for one billion dollars by Viacom last, it is safe to bet that they and others are interested in being able to better detect whether the material on their sites is copyrighted. Computer vision has finally come to online video search, and we can safely say that it is here to stay.

You can find a list of Dr. Sharon???s computer vision publications on his personal web site: http://www.dam.brown.edu/people/eitans/