Facial recognition is not a new buzzword in the world of technology. Facial recognition enables the identification or verification of a person from a digital image or a video frame from a video source. This technology generally works by comparing selected facial features from a given image with faces within a database. While initially envisioned as a computer application, facial recognition has seen wider uses in recent times on mobile platforms and in other forms of technology, such as robotics and security.
According to the Boston Globe, the earliest usage of facial recognition technology can be traced back to the 1800s, when a poster bore the portrait photograph of Abraham Lincoln’s assassin, John Wilkes Booth. In the 1960’s Woodrow Wilson Bledsoe devised a system for noting key facial landmarks on each picture.
Further research in the 1990s by mathematicians at Brown University and MIT led to a linear algebra-based system called Eigenfaces that was able to plot a human face by focusing on ways it differs from the average. Modern facial recognition, however, has flourished since the September 11 attacks in the United States, spurred by additional funding for national security.
Experts at Technavio estimate that the global surveillance market for video is expected to post compounded growth rates of around 11% between 2018 and 2022. Traditionally associated with the security sector alone, facial recognition technology has been making inroads into the retail, marketing, and health industries.
Fueled by AI and Machine learning, facial recognition has become nearly ubiquitous. From unlocking phones to security clearances to personalized advertisements to healthcare, facial recognition has been impacting our lives in more ways than we can imagine.
[Must Read] – How Is AI Revolutionizing Farming?
The primary sector for which facial recognition was initially envisioned, facial recognition is used in many areas as an intrusion deterrence mechanism and a suspect recognition mechanism.
One key advantage of a facial recognition system that it is able to process mass identification as it does not require the cooperation of the test subject to work. Properly designed systems installed in airports, multiplexes, and other public places can identify individuals among the crowd, without passers-by even being aware of the system.
The U.S. Department of State operates one of the largest face recognition systems in the world with a database of 117 million American adults, with photos typically drawn from driver’s license photos. In January 2001, police in Tampa Bay, Florida used Viisage face recognition software to search for potential criminals and terrorists in attendance at the Super Bowl XXXV. Around19 people with minor criminal records were potentially identified.
Companies like Truface are bringing facial detection to your home. With their facial recognition doorbell called Chui, deep learning and facial recognition come hand in hand to help distinguish a human face from a photograph to avoid misdetection and is now actively being used in many industries like healthcare and banking. Financial institutions worldwide use facial recognition system in their Installations including ATMs and bank branches to identify potential fraudsters and to prevent tampering in the ATM hardware.
Facial recognition promises to be the next disruptive technology in healthcare. Dosing compliance is one field where AiCure, an AI company has been using facial recognition technology and computer vision to improve dosing compliance of medication by end users. Research has shown that higher medication adherence correlates with patients who have two conditions (comorbidities) and a much higher number of prescription medications. AiCure is poised to become increasingly relevant as the healthcare industry continues to integrate technology and AI solutions to improve patient outcomes and dosage acceptance.
Another field of study was done for ePAT around pain management. As the assessment of pain is very patient dependent, patients that cannot describe their pain are at a constant disadvantage. ePAT is a point of care app that uses facial recognition to detect expressions associated with pain. Studies like this and many more showcase facial recognition to be a highly sought-after technology in healthcare.
Marketing and Retail
Facial recognition and AI are vital for the retail industry as they can help retailers understand their customers better and deliver improved customer experiences. Recent advances in AI have significantly improved the accuracy of facial recognition. Although marred with controversy, apps like Facedeals targeted customers that entered a retail area by mapping their faces to their Facebook profiles.
Their like patterns would then generate a customized deal on their phone. Similarly, coffee maker Douwe Egberts integrated facial recognition tech into their marketing campaigns and publicity efforts. Retail major Walmart had also dabbled with face recognition to identify potential shoplifters but had to abandon their efforts after considerable protests.
In September 2009, Coke Zero launched a Facial Profiler app on Facebook that scanned photos for people who looked similar to you. The tagline for this facial recognition project was: “If Coke Zero has Coke’s taste, is it possible someone out there has your face?”
Security, however, remains the major requirement and the driving force behind the current facial recognition market. The main reason for this being the increased security concerns for companies and individuals. Even when marred with great resistance from the advocates of human rights and anti-privacy violation advocacy groups, facial recognition technology will continue to see increased implementation across industries, with certain sectors leading the race when it comes to innovation.