As people snap more and more digital photos, being able to organize those photos into useful sets is becoming increasingly important. Facial recognition algorithms are quickly becoming a standard feature in popular photo origination programs (e.g. iPhoto), but people-sorting is only the tip of the “semantic photo search” iceberg. Cloud photo service EverPix is one company that’s currently working to take photo recognition beyond faces. Sarah Perez of TechCrunch writes,
[…] the eventual goal for Everpix is to become the default way people choose to view and share photos. One development which could help it get there is the image analysis technology the company has been developing in-house. As people’s photo collections grow exponentially over the years, it’s something that will become more valuable in time. Using generalized semantic tagging techniques, Everpix is building algorithms that can identify what the photo is of – meaning, whether it’s a person, a night or day shot, a wide or close shot, a city scene, a nature photo, a photo of a baby, or a vehicle, or a photo of food, among many other things.
What’s important here is that the way they’ve built this to scale. After training the system on a minimal amount of photos, Everpix can then look for other photos in a user’s collection that match that signature without reprocessing the entire photo collection.
In the future, we’ll likely be able to search for photos with photos. Looking for a particular photo that you took at a popular tourist landmark? Just show the app a similar photo found online, and voilà, yours appears.
Cloud Photos Service Everpix Exits Beta With New Website & iPad App; Semantic Photo Search Coming Soon [TechCrunch]
Photos and details of Nokia’s upcoming Lumia 920 smartphone leaked earlier this week, revealing that the new flagship Windows phone will feature a 8-megapixel sensor, a 4.5-inch display, 32GB of storage, and wireless charging via a special pad.
Although the camera specs seem rather pedestrian compared to the 41MP 808 PureView, patents published last month reveal that the company is working on some special sensor tech for future devices. More specifically, Nokia is working on developing camera sensors that use layers of graphene — one-atom-thick layers of carbon — for big performance advantages over existing sensors.
Hyperspectral cameras are those that can capture information in the electromagnetic spectrum, far beyond what the human eye — and consumer cameras — can see. American Photo Magazine has a fascinating feature that tells of how researchers around the world are using the cameras to uncover century and millennium-old mysteries:
The historic discoveries are just getting started. No one yet knows how much researchers and scholars will find with this new generation of hyperspectral technology. More than a hundred years ago, in the ancient Egyptian city of Oxyrhynchus, archeologists found piles of illegible papyrus. Recently, University of Oxford researchers found that they contained fragments of a lost tragedy by the ancient author Sophocles, of whose plays only seven were known to have survived. New imaging methods have also found portions of a poem by Archilochus that reveal new details about the genesis of the Trojan War. The research at St. Catherine’s could settle long-standing debates over the origins and foundation of some of the world’s major religions.
Discoveries using hyperspectral photography so far include revisions to the US Declaration of Independence, hidden words in the Dead Sea Scrolls, and a possible Abraham Lincoln fingerprint on a copy of the Gettysburg Address.
Peeling Back the Hidden Pages of History With Hyperspectral Photography [American Photo]
P.S. Last year, a group of scientists was able to create a hyperspectral camera using an ordinary Canon 5D and random off-the-shelf parts.
Image credits: Photographs by Abby Brack Lewis and the Library of Congress
If you think modern day hard drives store a lot of data, get a load of this: researchers at Harvard have succeeded in storing roughly 700 terabytes of data in a single gram of DNA. The strands of DNA are treated much like other storage devices, except instead of using electric charge or magnetism to store information, DNA’s four bases (A,C,G,T) are used.
What if the battery in your camera could be charged in the same amount of time it takes to microwave a cup of instant noodles? It sounds crazy, but that’s what appears to be headed our way.
Researchers at the Ulsan National Institute of Science and Technology in South Korea have figured out a way to drastically cut down the time it takes to recharge a lithium-ion battery — the same kind found in most digital cameras.
Earlier today, we poked fun at a clip from the TV show CSI showing some pseudo-scientific photo enhancing. Many of the comments on YouTube also poked fun at the mention of “corneal imaging”, in which the investigators used to obtain imagery from the reflections seen in an eyeball. Turns out corneal imaging is a real thing…
“Any sufficiently advanced technology is indistinguishable from magic.” That’s the quote by science fiction author Arthur C. Clarke that you’ll find on Cardiio‘s homepage. It’s a quote that is quite appropriate, given what the app can do.
The app is a touch-free heart rate monitor that can accurately tell you your pulse by simply looking at your face through your phone’s camera.
Stuff a few thousand dots per inch into a color print, and you have yourself a pretty high resolution image that most people would approve of. What if you could stuff 100,000 dots into that same inch?
That’s what researchers were able to do recently in creating the highest-resolution photograph ever printed — and one of the smallest, to boot.
Cameras these days are smart enough to recognize the faces found inside photographs and label them with names. What if the same kind of recognition could be done for the locations of photographs? What if, instead of using satellite geodata, the camera could simply recognize where it is by the contents of the photographs?
That’s what research being done at Carnegie Mellon University and INRIA/Ecole Normale Supérieure in Paris may one day lead to. A group of researchers have created a computer program that can identify the distinctive architectural elements of major cities by processing street-level photos.
“Super-Resolution From a Single Image” is an interesting research page by computer scientists over at the Weizmann Institute of Science in Israel. It details the group’s efforts to create sharp enlargements of small photographs, and offers comparisons between their algorithm and other popular ones being used and researched (e.g. nearest neighbor, bi-cubic). The large image of the baby seen above was created from the tiny image on the left. See if you can create something more useable using Photoshop.
Super-Resolution From a Single Image (via MetaFilter)