The evolution of facial recognition: from bodycams to video surveillance

Download PDF version

Facial recognition has a long history dating back to the 1800s. To track down criminals, such as infamous bandits Jesse Woodson James and Billy the Kid, law enforcement would place “Wanted Alive or Dead” posters advertising bounties and soliciting public cooperation to help locate and even apprehend the alleged criminals. In addition to the bounty, these posters would include a photo and brief description of the crime, which would then be circulated to law enforcement agencies around the country and displayed in every US Post Office to speed up apprehension.

Facial Recognition

Advancements in artificial intelligence and biometric technology have led to the widespread use of computerised facial recognitionToday, technology such as social media, television and other more specialized communication networks play a more influential role in the recognition process. Advancements in artificial intelligence and biometric technology, including the development of Machine Learning capabilities, have led to increased accuracy, accessibility and the widespread use of computerized facial recognition. The significance of this means that facial recognition can occur on an even larger scale and in more challenging environments.

This article will explore key milestones and technological advances that have resulted in the modern incarnation of facial recognition, before discussing the capabilities of cutting-edge “one-to-many” technology which is increasingly being used by counter-terror defense, police and security forces around the world.

Technology Inception And Developments

The technology was able to match 40 faces an hour, which was considered very impressive at the time

The 1960s marked the start of computerized facial recognition, when Woodrow Wilson (Woody) Bledsoe developed a way to classify faces using gridlines. Bledsoe’s facial recognition still required a large amount of human involvement because a person had to extract the co-ordinates of the face’s features from a photograph and enter this information into a computer. The technology was able to match 40 faces an hour (each face took approximately 90 seconds to be matched) which was considered very impressive at the time.

By the end of the 1960s, facial recognition had seen further development at the Stanford Research Institute where the technology proved to outperform humans in terms of accuracy of recognition (humans are notoriously bad at recognizing people they don’t know). By the end of the century, the leading player in the field was a solution that came out of the University of Bochum in Germany – and the accuracy of this technology was such that it was even sold on to bank and airport customers.

From this stage on, the facial recognition market began to blossom, with error rates of automatic facial recognition systems decreasing by a factor of 272 from 1993 to 2010 according to US Government-sponsored evaluations.

The safety and security market requires near instant feedback on who a person matched against a watchlist is

The aim for facial technology is to achieve successful and accurate recognition on commonly available hardware like live CCTV feeds and standard computing hardware

Modern Usage Of Facial Recognition

Fast-forward to the modern day and facial recognition has become a familiar technology when using applications such as the iPhone X’s Face ID capability or MasterCard Identity Check, passport e-gates at airports and other security and access control points. These solutions implement a consensual form of identity verification, as the user has a vested interest in being identified.

This is a “one-to-one” facial recognition event, one person in front of the camera being compared to one identity either on a passport or the app. In these scenarios, the hardware is specifically developed for the application at hand, therefore technically much easier to accomplish.

Facial recognition can now be used in a variety of governmental and commercial environments The safety and security world brings a much more complex problem to solve – how to pick out a face in a moving and changing environment and compare it to several faces of interest. “One-to-many” facial recognition is a much harder problem to solve.

It’s even more challenging when the aim is to achieve successful and accurate recognition on commonly available hardware like live CCTV feeds and standard computing hardware. And unlike in the 1960’s where identifying a face every 90 seconds was acceptable; the safety and security market requires near instant feedback on who a person matched against a watchlist is.

Security And Safety Applications

The idea behind all facial recognition technologies is broadly the same: you start with an image of a person’s face (ideally a high quality one, although machine learning means that to a point we can now even use video without reducing accuracy). A fully front facing image is best, think a passport photo, but machine learning and new software has made this more flexible.

An algorithm converts this image into a numeric template, which cannot be converted back to an image and so represents a secure one way system. Every numeric template is different, even if it started out as an image of the same person, although templates from the same person are more similar than templates from different people.

The accuracy of facial recognition continues to increase alongside deployments in more challenging and complex environments What happens next sounds simple although the technology is extremely complex: templates of people’s faces are taken in real time and compared to those in the database. The technology identifies individuals by matching the numeric template of their face with all the templates saved in a database in a matter of seconds or milliseconds. To put this into perspective, imagine you are at the turnstiles of a busy train station looking for a person on the run.

Today’s facial recognition technology would be able to identify that person should they pass in view of a CCTV camera, as well as notify the police of any additional persons of interest, whether they are a known terrorist or missing vulnerable person on an entirely separate watch list.

Because of technical progression, facial recognition can now be used in a variety of governmental and commercial environments, from identifying barred hooligans attempting entry at a football stadium or helping self-excluded gamblers at casino to overcome addiction.

Real-Time Assessments

The latest evolution of facial recognition pits the technology against an even more challenging application – directly matching individuals from body worn cameras for real time recognition for police officers on the beat. This capability equips first responders with the ability to detect a person from a photo and verify their identity with assurance.

The broader implication for this means that every interaction, such as stop and search or arrest, can be supported by real-time facial recognition which will see cases of mistaken identity driven down on the streets. First responders can now for the first time be deployed and furnished with the ability to identify wider groups of people of interest with a degree of accuracy that previously relied only on the fallible human memory.

As the accuracy of the technology continues to increase alongside deployments in more challenging and complex environments, its ability to support government initiatives and law enforcement means the debate about the lawful and appropriate use of facial recognition must be addressed. Facial recognition should not be everywhere looking for everyone, but when used properly it has the potential to improve public safety and we should make the most of its potential.

Download PDF version

Author profile

Fernande van Schelle Product Manager, Digital Barriers

Related companies
Digital Barriers

Related links
Face Recognition Software Access control software
Articles by Fernande van Schelle

View all news from
Digital Barriers

In case you missed it

What Was The Big News At ISC West 2019?

ISC West 2019 is in the industry’s rear-view mirror, and what a show it was! The busy three days in April offered a preview of exciting technologies and industry trends for the coming year. We asked this week’s Expert Panel Roundtable: What was the big news at ISC West 2019?

Cybersecurity: Why It Matters Now And Forever

Cybersecurity has become a major element – and a major source of discussion – in the physical security marketplace as a result of the rise in networked systems. And we may still not be talking enough about cybersecurity. Here is part one of our Cybersecurity series. “Cybersecurity requires everyone in the security industry to be playing offense and defense at the same time, every single day,” says Bill Bozeman, President and CEO of PSA Security Network. “It needs to just become part of the standard conversation when we are talking about physical security because they are so intertwined.” Creating New Industry Leaders Cybersecurity and physical security can be seen as two parts of a single entity, and increasingly the two will be combined at the enterprise level over the next several years. “This convergence of physical security and cybersecurity will create new industry leaders that will emerge to lead a new segment of the combined market through strong investment and leadership,” says Rob Lydic of ISONAS, now part of Allegion. Data capture form to appear here! Cybersecurity issues dominate almost every discussion in today’s physical security industry, and the clear message is that “manufacturers and integrators must continue to create robust and scalable cybersecurity offerings to protect customer data and facilities,” says Lydic. He contends that cloud services providers (such as ISONAS) are more cybersecure and reliable ‘by orders of magnitude’ than non-cloud solutions. Cybersecurity is linked to cloud-based systems and managed security service provider models Cloud-Based Services The Security Industry Association (SIA) has listed cybersecurity as one of 2019’s ‘Top Megatrends’ in the physical security market. SIA says it is important to prioritize cybersecurity among security businesses, for customers’ businesses, and for vendors. The trend calls for continual process improvement and investment. Bill Bozeman of PSA Security Network agrees: “Cybersecurity has definitely taken a strong foothold in the industry.” With the continued expansion of cloud-based services, cybersecurity will be more important than ever to integrators, manufacturers and end users alike, he says. Notably, cybersecurity is directly linked to two other important industry trends listed by Bozeman: cloud-based systems and the rise in recurring monthly revenue (RMR) and managed security service provider (MSSP) models, whose focus will include cybersecurity. Loss Prevention Executives The days when cybersecurity was exclusively the domain of the information technology (IT) department are gone. “Cybercrime is one of the biggest threats organizations of all sizes and types face today,” says Michael Malone, CEO of ADT Cybersecurity (formerly known as Datashield). “Considering the magnitude of these crimes, it now falls on the entire organization, including the traditional security or loss prevention executives, to band together to combat these threats.” Cybercrime is one of the biggest threats organizations of all sizes and types face today Malone favors (and his company offers) a managed detection and response (MDR) service, which combines advanced technology and human analysis. Using packet capture on the network, an MDR analyst can ‘replay’ a cyber security event and dig deeper into the incident and determine remediation steps. It’s an approach that significantly cuts through false positive ‘noise’ so security teams can focus on what matters. Helping Security Officers Interestingly, cybersecurity is poised to benefit from another major trend in the physical security market – the rise of artificial intelligence. Specifically, machine learning applications for cybersecurity include: detecting malicious activity, helping security officers determine what tasks they need to complete in an investigation process, analyzing mobile endpoints, decreasing the number of false positive threats, automating repetitive tasks like interrupting ransomware, and potentially closing some zero-day vulnerabilities. But AI in this case is not a panacea. Christopher McDaniels of Mosaic451 recommends pairing human intellect with machine technology to sort through data faster and catch hackers before they do much damage. Part two of our Cybersecurity series coming soon.

ISC West 2019 Wrapup: An Ecosystem Of Apps, Chips And Systems To Come

The excitement of ISC West 2019 continued until the very end – almost. Exhilarated by the first two busy days of the show, attendees and exhibitors seemed to welcome a slower third day. There were no complaints about booth traffic, and still plenty of thoughtful conversations taking place, everyone determined to maximize the value of face time with customers until the last second. Building An IoT Ecosystem In SAST At a show lacking in high-profile new technology announcements, the biggest news is perhaps the possible long-term impact of first-time exhibitor Security and Safety Things (SAST), a Bosch startup. SAST is building a new Internet of Things (IoT) ecosystem for the security and safety industry, including an app store, an open and secure camera operating system, a software developer environment, and a portal for integrators. SOCs (system-on-chips inside cameras) are becoming much more capable" Their 1,800-square-foot booth was big for a first-time exhibitor, and the American football theme was well received, as was the substance of the company’s effort to drive innovation in a highly fragmented industry. Seeing actual cameras and apps on display at the ISC West booth is “more real than PowerPoint,” says Hartmut Schaper, CEO of Security and Safety Things (SAST). “For us, seeing is believing,” says Schaper. “It was important for us to show cameras and apps for the first time. People are surprised at how far down the road we are.” “This dynamic will change in the industry,” says Schaper. “SOCs (system-on-chips inside cameras) are becoming much more capable. Soon there will be more processing power on the edge. People will find a way to use the extra processing power.” “Seeing is believing” at the SAST booth at ISC West 2019, where CEO Hartmut Schaper showed several manufacturers’ cameras whose functionality can be expanded using Android apps Developing More Apps Several large manufacturers are already involved in the initiative, but there are some holdouts. “We are having ongoing talks with everyone to convince them to join,” Schaper says. “Some of the bigger ones will come around. We are not a camera manufacturer, and not a threat. We are owned by Bosch but are managed completely separately. There will be more and more apps developed, and momentum will increase.” “A year from now we will have successful customers we can talk about, and more camera manufacturers on board,” he says. “This year we are taxiing on the runway, but next year we will have cleared the tarmac and be climbing.” If the approach succeeds, their first appearance at ISC West will be remembered as historic. Future Of Surveillance Cameras Off the show floor, in a nearby meeting room, chip maker Ambarella demonstrated technologies that will be driving the future of video surveillance cameras, including more intelligence at the edge. “People have been using more traditional video analytics approaches, though most of them have been disappointing,” says Chris Day, Ambarella VP of Marketing and Business Development. “What is ground-breaking now is the use of neural networks and real artificial intelligence, which has increased capabilities 100x. "You will see camera products coming out over the next year that are massively better than before. It’s not just incrementally getting better. Cameras will be coming out later this year with analytics that are absolutely amazing based on [the new chips.]” Larry Anderson, editor-in-chief of SecurityInformed.com, talks about Ambarella HDR and Low Light Solutions with Jerome Gigot, Senior Director of Marketing for Ambarella. (Source: Ambarella) New Systems-on-Chips Ambarella has introduced four new systems-on-chips (SoCs) in the last year, with emphasis on computer vision (video analytics). The newest is the S6LM Camera SoC with 4K imaging technology, unveiled at ISC West. The S6LM includes Ambarella's latest high dynamic range (HDR) and low-light processing technology, highly efficient 4K H.264 and H.265 encoding, multi-streaming, on-chip 360-degree de-warping, cyber-security features, and a quad-core CPU. People shouldn’t forget what a good camera is, and there doesn’t have to be a tradeoff" “With so much focus on AI and computer vision, I’m concerned the industry has taken focus away from low light imaging, wide dynamic range and image quality,” says Day. “You have to see the details in an image. People shouldn’t forget what a good camera is, and there doesn’t have to be a tradeoff, it’s all included in one chip.” From Products To Systems With a new general manager on board (Daniel Gundlach, formerly of Bosch), FLIR Systems Security Division is continuing its transition from a product company to a solutions provider, removing internal silos to clear the path. FLIR offers a strong end-to-end portfolio for Smart Cities applications, including the TruWITNESS line of body worn cameras and newly acquired Aeryon drones. FLIR’s historical strength as the top thermal imaging provider continues, but today they are much more than a thermal imaging company, offering visible day/night cameras, infrared pan-tilt-zoom cameras, video management systems and other technologies to provide a broader platform. FLIR's Saros security cameras combine multiple security technologies, including thermal sensors, high-resolution visible imaging, IR and visible LED illuminators, onboard analytics and two-way audio and digital input/outputs. Products In Critical Infrastructure Applications In addition to Safe Cities, FLIR installs a range of products in critical infrastructure applications, such as oil and gas and electric utilities. Ports also tend to combine traditional security with an emphasis on perimeter protection, a FLIR strength. Existing perimeter protection applications can open opportunities for the broader platform. For example, installing a complete system in an airport that already uses FLIR’s thermal technology represents “low-hanging fruit” for the company, says Fredrik Wallberg, FLIR Director of Marketing – Security and Intelligent Transportation Systems. Ambarella demonstrates its latest imaging technology for video security during ISC West 2019 (Source: Ambarella) Integrated Solutions Bosch's Focus At the Bosch booth, there was an emphasis on integrated solutions and the customer experience. A mock retail store setup demonstrated systems such as overhead cameras for people counting and alarm communication to provide an alert if a refrigerator door is left ajar. A wireless panic button generates a silent alarm, communicates with a 2-way radio, and triggers a camera to focus on the area. An AVIOTEK IP camera alarms if there is a fire, based on observing actual flames rather than smoke. A new Bosch fixed dome camera series offers wireless remote commissioning capabilities that reduce installation and set-up time by up to 75 percent. Set-up only takes three steps: install the mounting bracket, connect the cables, and attach the camera module. Commissioning can be done wirelessly or remotely with no need for ladders or lifts. Dahua Marks Five Years In The States An IR illuminator is attached to each lens module to ensure there is always illumination in the field of view Time flies in the security industry, and it has already been five years since the Dahua brand entered the U.S. market. Today the company offers products through ADI and some 20 distributors, and has more than 30 technical consultants and technical support employees and 50 or 60 sales people in the field (including independent rep firms). “We are growing,” says Tim Shen, Director of Marketing at Dahua Technology USA. “It’s exciting for the company.” At ISC West, Dahua introduced a line of Multi-Flex panoramic cameras with lens modules that can be repositioned along an internal track for 180-, 270- or 360-degree views, providing flexibility for integrators. An IR illuminator is attached to each lens module to ensure there is always illumination in the field of view. Cost savings come from ease of installation (one camera instead of four) and only one VMS license (instead of four). AI And Night Color Cameras Dahua is also emphasising its Night Color cameras that remain in full color mode regardless of how dark it gets. There is no IR illumination or IR cut filter – the camera stays in color mode and displays any visible image in colour with as little as 1 lux of illumination. The 2 megapixel version is on display at ISC West, and a 4 megapixel version will come in the fall. A year ago at ISC West, Dahua emphasised its initiatives in artificial intelligence (AI) in order to position the company as a technology leader. This year, the message was more general – ‘Power Through Technology.’ The range of Dahua technologies includes AI, Night Color, Starlight low-light imaging, fifth-generation HDCVI, and e-POE (Enhanced Power over Ethernet). Dahua USA's Director of Marketing says "the market itself likes AI", and expects more AI applications to follow (Source: Dahua USA's LinkedIn) “When we present AI to customers, they are happy, but when it comes to the budget they don’t have it,” says Shen. “The market itself likes AI, and it’s very much a buzzword. But we still need a proof of concept that it can do something good for end users. We need time to develop broader applications. The ‘smart retail’ market and education are good places to start.” he says. “AI is for project business,” adds Jennifer Hackenburg, Dahua’s Senior Product Marketing Manager. “Projects that are looking at AI haven’t come to fruition yet; they are still in the pipeline. It’s not for your everyday business. They are implementing it, but not as fast.” Access Control Beyond Doors Access control should extend beyond doors. That’s the message I heard at the ASSA ABLOY booth, which displayed a variety of physical locks and intelligent access systems. An example is traffic cabinets, those metal boxes in public locations that could potentially be accessed to invade an internal network. ASSA ABLOY emphasises the need to secure the variety of enclosures, cabinets, drawers and small spaces ASSA ABLOY emphasizes the need to secure the variety of enclosures, cabinets, drawers and small spaces throughout an enterprise. The company’s ‘security continuum’ message draws attention to the need for the right level of security for the right opening, using existing infrastructure as well as new electronic technologies. “Customers face a combination of non-traditional access control and questions on how they can secure things that are not doors,” says David Corbin, ASSA ABLOY Director of Access Control Accessories. The security message is resonating beyond the traditional security department to involve other stakeholders in an enterprise, including IT directors. There is new awareness of vulnerabilities that have been there forever, such as traffic cabinets that can be opened with a key purchased on eBay.