Cornell software identifies bird species from users’ photos

merlin-bird-photo-id

A photo of a Blackburnian warbler, made ready for processing by Merlin Bird Photo ID

While there are already plenty of apps that help birdwatchers identify birds, most of them work by searching a database based on descriptions. Cornell University and the Visipedia research project’s Merlin Bird Photo ID program, however, goes further – it utilizes computer vision tech to identify birds pictured in user-supplied photos.

Users start by uploading a photo that they snapped of the bird in question, drawing a box around the animal to help the software find it, and then clicking on its bill, eye and tail to establish its orientation. They also indicate where and when they saw it.

Merlin Bird Photo ID then uses its artificial intelligence to compare data points in the photo with those from tens of thousands of photos of known species of birds – its database currently includes 400 species that are commonly seen in the US and Canada. It also takes into account the time of year and geographical location at which the photo was taken.

Within a few seconds, the software subsequently presents the user with a short list of the closest matches, including photos and song recordings.

merlin-bird-photo-id-2

 

“Computers can process images much more efficiently than humans,” says Cornell’s Prof. Serge Belongie. “They can organize, index, and match vast constellations of visual information such as the colors of the feathers and shapes of the bill.”

The program currently manages to include the correct species within the top three results about 90 percent of the time, although its accuracy should improve with increased use. That’s because it utilizes machine learning, so it builds upon the knowledge it gains each time it processes a new photo.

Plans call for the technology to be added to the existing free Merlin Bird ID app, once it’s able to reliably identify birds in photos taken with smartphones. In the meantime, you can try it out at the project website.

References:http://www.gizmag.com/

Moky Bluetooth keyboard is also a trackpad

moky

You can both type on Moky, and use it as a trackpad

We’ve seen a number of ideas for making Bluetooth portable keyboards that are compact yet still not frustratingly tiny – these have included devices that project virtual keys, devices that fold, and that can be rolled up. The Moky keyboard, however, takes a different approach. It saves space by allowing its keyboard area to double as a multi-touch trackpad.

According to the Seoul-based Moky company, the device uses “infrared laser sensors” to overlay an invisible trackpad on top of the keyboard. It lets users perform actions such as clicking/dragging, scrolling, swiping, pinching in and zooming out, simply by making the traditional finger movements directly above the keys.

While it isn’t clear exactly how the system works, the principle appears to be the same as that used by Continental’s “infrared curtain” technology for multi-touch displays in cars. In that case, a raised rectangular frame around the display has a series of LEDs along two adjacent sides, and a series of photodiodes along the other two. Each LED emits a beam of infrared light, which is picked up and converted into an electrical signal by the photodiode located in the corresponding spot on the opposite side of the frame.

When the user reaches through the grid of infrared light beams in a given location, their finger blocks some of the beams. Those beams’ photodiodes temporarily stop receiving light, and thus cease sending a signal. By analyzing the combination of affected photodiodes, the system can determine the location of the user’s finger relative to what’s being displayed on the screen, in real time.

moky-10

Some of Moky’s other features include pantograph (i.e: individually spring-loaded) keys, an aluminum body, a folding cover that also serves as a smartphone/tablet stand, and a rechargeable battery that should be good for a claimed three months of use per charge (based on about four hours of use per day). The keyboard utilizes Bluetooth LE, and is compatible with iOS, Android and Windows devices.

Moky is currently the subject of an Indiegogo crowdfunding campaign, where a pledge of US$69 will currently get you one – when and if the keyboard reaches production. You can see it in use, in the pitch video below.

And although Moky may end up being the first true keyboard/trackpad hybrid to make it to market, this certainly isn’t the first time that the concept has been conceived of. Microsoft Research’s prototype Type-Hover-Swipe keyboard uses an array of infrared proximity sensors located between the keys to achieve the same ends, while Apple’s patent for the Fusion keyboard incorporates touch sensors in the surface of the keys.

Reference:http://www.gizmag.com/

Coating condensers with graphene could increase power plant efficiency

mit-graphene-power-plant-efficiency

Coating condenser tubes in graphene (right) significantly improves efficiency over existing methods (left)

Research conducted by a team of MIT scientists suggests that applying a layer of graphene to power plant condensers could significantly improve efficiency. Early testing indicates that use of the material is vastly superior to current methods, and its application could lead to huge monetary savings, as well as a positive impact on the climate.

The majority of power plants generate electricity by using steam to turn a turbine, with that steam then turned back into water to allow the process to start again. The MIT scientists believe that they’ve found a method of improving the efficiency of the condensers that collect the steam, and it could make a big difference to overall power plant efficiency.

The research focuses on improving condensers that collect water in thin sheets, covering their surfaces. Looking at how that film of liquid impedes heat transfer, the team decided to search for a way of improving water droplet formation on the surface of the condensers, thereby improving efficiency. Water-repellent polymer coatings are often used for this purpose, but they’re far from an ideal solution, often degrading quickly in the humid conditions of the plant.

To find a better alternative, the team turned to graphene – a very strong, conductive material that’s known to be hydrophobic. Both the ability of the material to shed water and its durability were tested in an environment of pure water vapor at 100 ºC (212 ºF) – the exact conditions you’d find in an active power plant.

The results showed that the graphene coating improved the rate of heat transfer by a factor of four, and further calculations indicated that optimization could lead to improvements of five to seven times that of existing methods. Furthermore, after two full weeks of testing, there were no signs of degradation.

Improvements to large scale chemical vapor deposition (CVP) graphene production, such as that recently unveiled by MIT, will be instrumental in the potential use of graphene in power plants. In fact, the team believes that the new method could be ready for real world testing in as little as a year.

It’s thought that the condenser improvements could lead to an overall power planet efficiency bump of 2 to 3 percent, translating to millions of dollars per power plant per year. Given the vast number of power plants that make use of condensers, that could translate into a big positive impact on global carbon emissions.

References:http://www.gizmag.com/

Could “brainprints” replace passwords, fingerprints and retinal scans?

brainprint-security

The brain waves that result in response to certain words could be used to verify a person’s identity

Passwords are the bane of many a computer user’s existence. Experts recommend long strings of characters containing a mix of upper and lowercase letters, numbers and symbols that may be difficult to crack, but can also be difficult to remember. Despite there being simple techniques for creating difficult-to-crack passwords that are easy to remember and horror stories of identify theft abound, the top two most common passwords remain “12345” and “password”. But a study out of Binghampton University (BU) in New York suggests brainwaves could be a promising alternative to verify a user’s identity.

Researchers at BU read a list of 75 acronyms, such as FBI and DVD, to 45 volunteers and observed the brainwaves that resulted from each group of letters, focusing on the part of the brain associated with reading and recognizing words. This was done with the placement of just three electrodes on the scalp, which is the minimum number that can be used and still obtain a clean reading.

While each respondent’s brainwaves exhibited identifiable features that were consistent in response to a given acronym, the reactions – or “brainprints” – were different enough between respondents to allow a computer system to identify each volunteer with an accuracy of 94 percent. These results were also stable over time, with identification possible after a lag of up to six months.

Sarah Laszlo, assistant professor of psychology and linguistics at BU and study co-author, says that brain biometrics offer a number of advantages over other physical characteristics used for biometrics, such as fingerprints or retinas. For example, both of these can be stolen by malicious means, rendering them unusable by the user since they can’t be replaced.

“If someone’s fingerprint is stolen, that person can’t just grow a new finger to replace the compromised fingerprint – the fingerprint for that person is compromised forever,” points out Laszlo. “Fingerprints are ‘non-cancellable.’ Brainprints, on the other hand, are potentially cancellable. So, in the unlikely event that attackers were actually able to steal a brainprint from an authorized user, the authorized user could then ‘reset’ their brainprint.”

While the researchers don’t see brainprints as a potential replacement for passwords for low security applications in the near future – after all, who wants to hook themselves up to an electroencephalograph (EEG) just to log into their email – they do see the technology having potential in high security environments.

“We tend to see the applications of this system as being more along the lines of high-security physical locations, like the Pentagon or Air Force Labs, where there aren’t that many users that are authorized to enter, and those users don’t need to constantly be authorizing the way that a consumer might need to authorize into their phone or computer,” says Zhanpeng Jin, assistant professor at Binghamton University’s departments of Electrical and Computer Engineering, and Biomedical Engineering.

The team’s study appears in the journal Neurocomputing.

References:http://www.gizmag.com/