New low light camera tech will improve AR apps, facial recognition in smartphones

A new technique called Light Invariant Video Imaging, developed by Ben-Gurion University, could help create better security cameras, facial recognition logins, and more.

Take professional photos with a smartphone: 4 tips
Building a slide deck, pitch, or presentation? Here are the big takeaways:
  • A new low light imaging technique could vastly improve smartphone cameras, security cameras, and facial recognition systems.
  • BGU's Light Invariant Video Imaging eliminates background issues to deliver clear, shadow-free images.

A new imaging software developed at Ben-Gurion University of the Negev (BGU) in Israel could help improve facial recognition systems and augmented reality (AR) apps on smartphones. The technique, dubbed Light Invariant Video Imaging (LIVI), improves the clarity of pictures in low light situations and makes objects more easily recognizable.

The software uses amplitude-modulated (AM) light separation to take out the distorting effects of background lighting and dynamic lighting, so images can be presented without shadows, with better contrast, and with stronger color, according to a BGU press release. Basically, it eliminates the impact of bad lighting conditions so an image can be clearer.

"Strong background light creates shadows, for example when people walk into buildings, interfering with the ability of our eyes and cameras to recognize faces," BGU professor Hugo Guterman said in the release. "Our invention produces a 'flash' effect that clears the backlight, removes shadows and improves contrast, making all captured frames much clearer."

SEE: Mobile device computing policy (Tech Pro Research)

According to BGU Ph.D. student Amir Kolaman, the system will filter backlight out for each individual pixel. It does this by turning each pixel into an "AM receiver" of sorts, Kolaman said, that tunes itself to the flash light, thereby filtering out any background light that may be present.

This new technique could lead to clearer images on smartphone apps, which could improve facial recognition for authentication, the release said. This could also improve the quality of AR applications that mix virtual images overtop of real-world ones. If properly integrated, it could possibly even lead to more effective security cameras as well.

According to a March 2017 IDC report, the worldwide smartphone market reached roughly 1.53 billion units in 2017. This is a huge opportunity for BGU to develop a wide-reaching product that could impact many users, as the technology will work on existing smartphone camera apps.

Low light camera technology is on display in the new Samsung Galaxy S9 and S9 Plus as well. As smartphone images become a more integral part of professional life, other manufacturers may follow suit with such tools.

BGU's breakthrough is one example of the growth of tech in Israel. TechRepublic is in Israel this week doing a tech tour with Israeli startups, entrepreneurs, and researchers, and will have videos of some of the most interesting breakthroughs we learn about.

Also see

Image: iStockphoto/Rohappy