Facedapter is a multi-modal facial recognition company, founded in February 2020. Being the first of its kind in cross-matching facial recognition, this software uses biometric authentication to bridge the gap between sensing technologies and everyday forms of identification.
In 2019 Founder and CEO, Praveen Gajjala decided to develop a single software system that works to match 3D faces to pre-existing 2D images, like passports and government-issued IDs. Using 4 different cameras, Facedapter cross matches all the images captured by each camera to ensure its accuracy.
This eliminates the issue of identifying people that look alike and enables cameras to recognize people, even in the dark; The cameras in use are 2D, 3D, Short Wave Infrared, and Thermal cameras.
Even with technology advancing at the rate that it is, there is not a single universal facial recognition system. This means that there is not a system that can accurately identify individuals of different ethnicities, and genders without creating synthetic data. This is highly problematic as it can result in poor identification of criminals leading to inaccurate arrests of civilians, and higher cases of identity fraud.
Facedapter recognizes this as one of the biggest issues surrounding facial recognition software today and has created software that adapts to its demographic. This means that it can be used in both homogenous countries like China and India as well as heterogeneous countries like the US and the UK.
“We educate machines the way we know, so when we have discriminatory biases so do the tools we create. This is why when we were creating Facedapter, I got to thinking about how we can accurately recognize all the different people using different types of devices and cameras and eliminate these biases…I understood that a bridge was necessary to match any kind of source image captured by any device, and then match it to an ID or a passport [for any given demographic]” said Praveen.
Facedapter is on a mission to help enterprises and governments reuse their existing face database used to store RBG images of IDs, passports, or Driving licenses, with its proprietary algorithm. An algorithm that can enable identity verification using any camera on the planet.
This software is faster, more cost-effective, and smarter than any other software on the market. With multiple cameras, it can capture and crossmatch up to 5 images per second, and because there is no storage of biometric data to maintain, it is comparatively more affordable.
Where other facial recognition software takes the faces of two individuals and combines that data to create a synthetic face, Facedapter’s software adapts to any given demographic without the use of synthetic data. This makes it smarter and less likely to incorrectly match two different people.
This September marks a year and a half since the founding of Facedapter, and right in the middle of the Covid-19 pandemic. If there is one piece of advice Praveen would give to anyone struggling on the journey of entrepreneurship it would be to, “Never give up – it may sound a little cliché but it is the truth. Strength comes from your beliefs, you have to stay resilient in the face of obstacles, remember what you’re trying to achieve, don’t listen to people who tell you to give up”
“So start now, and if you fail then you will know how to do it the next time, so you never really lose, you just learn”.
Comments