Researchers create ‘X-ray’ camera that reveals vein patterns
Researchers at the University of Washington and Microsoft Research have developed a camera that uses hyperspectral imaging to capture images at visible and invisible wavelengths, before combining them together to reveal otherwise-hidden details like veins under skin. As far as I know, it can’t see though close but it can tell if melons are ripe.
The HyperCam makes use of a technology called hyperspectral imaging, which involves scanning 17 wavelengths of visible and invisible near-infrared light from across the electromagnetic spectrum to capture unseen details.
This type of camera is typically used in industrial applications and can cost between several thousand to tens of thousands of dollars.
When put to the test with 10 different fruit, the HyperCam could predict the ripeness of the fruit with 94 percent accuracy, way better than the 62 percent accuracy of a regular camera. The researchers want to bring the tech to consumer smartphones so that it can be used in everything from food safety to biometrics and gesture recognition.
The Hypercam could also be used as a biometric tool for security systems. “It is like having a food safety app in your pocket”, said professor Shwetak Patel from Washington University.
But the HyperCam uses 17 different wavelengths, including near-infrared, which would flash in sequence when shoppers point it at a piece of fruit in the supermarket.
After what looks like a mini-disco party for your subject, you’re left with a handful of pictures that range from pretty normal looking to what-even-is-that territory. “You can say, ‘Oh, that’s a pair of blue trousers, ‘” lead author Mayank Goel said in a statement.
A typical camera divides visible light into three bands-red, green, and blue-and generates images using different combinations of those colors. “You can see the difference between blue denim and blue cotton”. The new software analyzes the images and finds ones that are most different from what the naked eye sees, essentially zeroing in on ones that the user is likely to find most revealing.
At the moment, the technology does not work very well in bright light, something the researchers are working on as well as creating a prototype of the Hypercam small enough to clip on to a smartphone. Microsoft Research has funded the project which is based on hyperspectral imaging.