New Camera Unveils Details Invisible to the Human Eye

October 22, 2015 | Kelly Tatera

Veins in a human hand, revealed by the HyperCam
Photo credit: University of Washington. Image has been cropped

Is that avocado in the grocery store ripe? This affordable camera will let you see beneath the surface of its skin.

Grocery shopping can be stressful. On top of trying to make sure we remember every item on the list we forgot at home, how are we supposed to look into a bin and magically distinguish a perfectly ripe peach from ones on the brink of going bad? Thanks to scientists at Microsoft Research and the University of Washington, the Hypercam is an affordable camera that will act as a “food safety app in your pocket.”

HyperCam uses both visible and near-infrared light to capture the details that are invisible to the naked eye. This type of camera is usually used in industrial applications, like satellite imaging, energy monitoring, and infrastructure and food safety inspections, but the technology costs several thousands of dollars.

SEE ALSO: This Scanning Device Exposes What's Really in Your Food

Fortunately, the researchers created a hardware solution that will cost roughly $800, and for those of us who don’t have close to a grand to drop on a new camera, don’t fear — the team estimates it will potentially cost as low as $50 to add the software onto a mobile phone camera.

While normal cameras only work with the red, green, blue (RBG) bands of visible light, the HyperCam emits and images an amazing 17 different wavelengths of light. The smart technology then compares the hyper-lit images to a regular RGB image to determine which elements of the photograph are hidden to the human eye.

In a preliminary test, the scientists took images of 10 different fruits — strawberries, mangoes, avocados, and more — over the course of a week. Amazingly, the HyperCam images predicted the ripeness of the fruits with a 94 percent accuracy. For reference, typical cameras only performed at a 62 percent success rate.

“With this kind of camera, you could go to the grocery store and know what produce to pick by looking underneath the skin and seeing if there’s anything wrong inside. It’s like having a food safety app in your pocket,” Shwetak Patel, professor of computer science and engineering at the University of Washington, said in a press release.

The HyperCam’s potential applications don’t stop at helping distinguish good foods from rotting ones — it could show veins beneath the skin or detailed skin texture patterns that are unique to an individual. The device could be used in biometrics, or technologies that analyze human body characteristics like DNA, fingerprints, irises, and more. In a test of 25 users, the HyperCam system successfully differentiated between individual hand images with 99 percent accuracy.

Further potential applications include using the near-infrared camera to make sure that crops are healthy or determine whether a work of art is genuine, the press release states. Essentially, the HyperCam can perform what many of the expensive, high-tech industrial cameras are doing today, but for a much cheaper price.

"Existing systems are costly and hard to use, so we decided to create an inexpensive hyperspectral camera and explore these uses ourselves," Neel Joshi, a Microsoft researcher who collaborated on the project, said in a statement. "After building the camera we just started pointing it at everyday objects — really anything we could find in our homes and offices — and we were amazed at all the hidden information it revealed."

Check out a video about HyperCam below:



Hot Topics

Facebook comments