Oosto’s deep learning enhances facial recognition accuracy and expands uses

Download PDF version Contact company

Newer facial recognition systems are scalable and provide more accurate results, and the end-user selects the parameters of system performance to suit their own application needs.

“We have developed algorithms that can be optimised in various compute environments, whether in a small chip inside an edge device or on a large server device,” says Ido Amidi, Oosto’s Vice President of Products and Business Development. “It all depends on client needs. We can do it all without giving up performance. There is no significant loss in performance across various platforms.” The system’s “containerised environment” operates efficiently in a customer’s IT architecture.

Facial recognition implementation

Oosto, formerly AnyVision, was founded in 2016 based on deep learning research into facial recognition. The focus has been on how to use face recognition to identify people in real-world scenarios. Products began coming to market in 2017, targeting verticals that involve a need to identify “bad actors” or very important people (VIPs).

The implementation of the technology involves the software operating in an on-premise appliance or server

The most common implementation of the technology currently involves the software operating in an on-premise appliance or server, with inputs coming from cameras at the edge and outputs going to a network video recorder or access control system. As concepts of the Internet of Things (IoT) trickle down into the security marketplace, edge-based deployments will become more common, supplying real-time actionable information, and avoiding a flood of unstructured video data.

Ethical recognition

Oosto helps users deploy, set up, and calibrate the system; then, it is managed by the customer based on their needs. Privacy features are built into the system, part of the company’s commitment to “ethical” facial recognition.

The technology, in general, has changed a lot since early implementations a decade or so ago failed to perform as promised. Expanded capabilities are fueled by developments in deep learning.

Privacy features

Facial recognition can help end-users identify people of interest but is specifically designed not to violate anyone’s privacy.

There are no databases or watch lists involved; the user typically compiles their selection of “bad actors” against which facial recognition algorithms can be compared. While Oosto provides a valuable tool, the end-user customer decides how to deploy that tool in their business, says Amidi.

Oosto's “liveness detection” deploys algorithms to analyse images from video and/or 3-D cameras

Liveness detection

Recently, Oosto has adapted the approach to provide access control; too, including “liveness detection” that deploys algorithms to analyse images from video and/or 3-D cameras to ensure a presented face is not a printed image or mask.

Their latest software release is a single platform aimed at recognising and providing insights into how people behave in physical spaces. New functionality includes the ability to detect unknown individuals entering restricted areas.

Neural net algorithm

Improved facial recognition functions well even for those wearing masks. A new neural net algorithm improves accuracy when identifying those wearing masks and the system can alert if a person is not wearing a mask (to aid compliance).

Expanded video forensics features, designed to expedite investigations, include an ability to do in-depth searches on captured video related to body attributes, colour of clothing, etc.

Recognition algorithms

How well can Oosto recognise a face among 20 different people on a casino floor? It all depends on variables, such as the number of people, lighting, and angle of view, image quality, and even networking issues. Recognition algorithms are “trained” using data collected from real-world use cases; training takes place in the lab environment.

The system can adapt to various lighting conditions, such as in a glass-enclosed lobby in the morning versus in the afternoon. As people enter an area, they may be looking down at their smartphones, for instance, which would mean some of their faces would not be in view. Such variables impact accuracy.

Test requirements of a system apply to each specific customer and can be adjusted and tweaked as needed

Customisable system

Each customer must decide their parameters regarding how to best use the system, with the fewest acceptable number of false alerts, in real-time, and using existing infrastructure.

Test requirements of a system apply to each specific customer and the system’s sensitivity and other operational factors can be adjusted and tweaked as needed, including at any time after a system has been installed.

Meeting specified application

“No customer is alike, so the needs of each customer’s system are unique,” says Amidi. For example, some situations might have a higher tolerance for false alarms, such as when there is an operator available who can make the final decision on whether a face matches. In other situations, such as when there is a missing child, false alerts are a bigger problem, and rapid response is especially of the essence.

“What we give customers out of the box applies to any scenario, and customers can tweak the system with the click of a button to meet a specific application,” says Amidi. “We empower our customers to understand the pros and cons so they can react in real-time.”

Identity management

Oosto can help to enhance the customer experience by identifying important customers

Oosto sells through systems integrators and has a partnership program with more than 150 integrators worldwide certified to manage and install systems. Oosto targets Fortune 500-size companies in financial services, gaming, and retail. The system helps to create a safe environment that is devoid of any “bad actors.”

Alternatively, Oosto can help to enhance the customer experience by identifying important customers that warrant special treatment. The system also can provide an alert if any unauthorised person enters a restricted zone; that is, anyone who is not an employee, a registered visitor, or a contractor.

Understanding technology

In many parts of the world, facial recognition is widely accepted and used for applications such as payment and access control. Anxiety about technology, especially in the United States, is based on a lack of understanding.

The public needs to “be better educated” on the subject, and Amidi expects the technology to become more socially accepted over time. “It’s a tool, and it needs to be supervised,” says Amidi. “From a technology perspective, we trust the accuracy. It just needs to be better explained.”

Download PDF version Download PDF version

Author profile

Larry Anderson Editor, SecurityInformed.com & SourceSecurity.com

An experienced journalist and long-time presence in the US security industry, Larry is SourceSecurity.com's eyes and ears in the fast-changing security marketplace, attending industry and corporate events, interviewing security leaders and contributing original editorial content to the site. He leads SourceSecurity.com's team of dedicated editorial and content professionals, guiding the "editorial roadmap" to ensure the site provides the most relevant content for security professionals.

People mentioned in this article

Ido Amidi Oosto

Related companies
Oosto

View all news from
Oosto

In case you missed it

What change would you like to see in security in 2022?

Here’s a news flash: 2022 will be a pivotal year for the security industry. As we enter the new year, continuing change is a safe prediction for any fast-moving, technology-driven marketplace. Recent history confirms the ability of the security industry to shift and adapt to changing conditions and to provide an ever-expanding menu of technology solutions to make the world a safer place. Given that the new year will bring change, what will that change encompass? More to the point, what should it encompass? We asked this week’s Expert Panel Roundtable: What is the biggest change you would like to see within the security industry in 2022?

2021’s most popular expert panel roundtable discussions

Topics that dominated our website’s Expert Panel Roundtable articles in 2021 included the effects of COVID-19, the benefits of mobile access, the upcoming potential of deep learning, and the future of access control cards. Our website’s Expert Panel Roundtable discussions in 2021 reflected some of the most timely and important topics in the industry. The very most clicked-on Expert Panel Roundtable discussion in 2021 considered the positive and negative effects of COVID-19. The second most popular was trends in perimeter security technology. Smart video solutions Here is a roundup of the Top 10 Expert Panel Roundtable discussions posted in 2021, along with a ‘sound bite’ from each discussion and links back to the full articles. Thanks to everyone who contributed to Expert Panel Roundtable in 2021 (including the quotable panelists named and linked below). The pandemic has impacted security in many ways, some we are just now realising" What are the positive and negative effects of COVID-19 to security? “The pandemic has impacted security in many ways, some we are just now realising. On the negative side, integrators were limited in their ability to access customer locations, posing significant challenges to supporting customers. Innovation was also halted in many sectors – such as AI and edge computing in healthcare. However, the pandemic increased awareness regarding the need for smart solutions that can aid in these types of crises. Smart video solutions have been identified repeatedly in the media as a potential pathway to better customer experience and increased safety.” – Alexander Harlass. Reducing false alarms What are the latest trends in perimeter security technology? “What’s really important in perimeter security is the minimisation of false alarms, not simply the potential detection of what might be an unauthorised person or object. In light of that, many systems now include alarm validation that can confirm an alarm event using a camera. The utilisation of AI-based technologies can further validate the accuracy of the alarm, making it as accurate and precise as possible. I anticipate seeing more cross-technological integrations to reduce false alarms, so that personnel in an alarm center spend as little time as possible in validating an alarm.” – Leo Levit. What will be the biggest security trends in 2021? “2021 will see artificial intelligence (AI) become more mainstream. There will be increased deployment in edge devices, including cameras, thermographic cameras, radar and LIDAR sensors, entry point readers, etc. Additional algorithms will be developed, greatly expanding the use and function as video surveillance transitions from a forensic tool to real-time analytics. This increases the value of these systems and helps create ROI cases for their deployment.” – Tim Brooks. Access control solutions Investments in tools and platforms to drive digital interactions have accelerated" What will be the security industry’s biggest challenge in 2021? “The security industry is traditional in the sense that it relies heavily on face-to-face interaction to do business with customers and partners alike. COVID-19 has put a hold on in-person meetings, trade shows, etc., and this trend is likely to extend throughout 2021. Virtually recreating these personal touchpoints, while cultivating and strengthening internal and external relationships, will continue to be both a challenge and opportunity for the security industry. Investments in tools and platforms to drive digital interactions have accelerated.” – Robert Moore. What are the challenges and benefits of mobile access control? “Mobile access control solutions are an exciting innovation in a market where the day-to-day user experience hasn’t changed much in the last 20 years. One area that has clear benefits and challenges is in improving the user experience. On one hand, physical credentials are expensive and a hassle to administer; however, they work reliably, quickly, and predictably. Mobile credentials are convenient in that everyone already has a smartphone, and you don’t have to admin or carry cards; however, when you’re actually standing at the door they need to work as well or better than physical credentials, or the benefits are lost.” – Brian Lohse. Attacking critical infrastructure What are the security challenges of protecting critical infrastructure? “It seems so often we hear about a new threat or cyber-attack in the news. Because of the rapid growth in technology over the last few years, cybercriminals are getting bolder and discovering new ways to attack critical infrastructure. One of the biggest challenges boils down to the capabilities of the operating security system and whether the organisation is aware of the current risks they face. Because there are so many points of entry for cybercriminals to target within critical infrastructure, it is vital that the security solution be prepared for attacks at every level.” – Charles (Chuck) O’Leary. They are more aware when they make physical contact with doors and interfaces" Which security technologies will be useful in a post-pandemic world? “People have become more sensitised to crowds and personal space. They are more aware when they make physical contact with doors and interfaces. As the pandemic subsides, these habits will likely remain for a majority of people." "Utilising AI-based cameras to accurately monitor the number of people in a room or in a queue will enable staff to take action to improve the customer experience. For example, AI-based analytics can quickly notify security or operations when people are waiting at a door and initiate 2-way audio for touchless access.” – Aaron Saks. Central monitoring station What is the potential of deep learning in physical security and surveillance? “Deep learning, a subset of artificial intelligence, enables networks to train themselves to perform speech, voice, and image recognition tasks." In video surveillance, these networks learn to make predictions through highly repetitive exposure" "In video surveillance, these networks learn to make predictions through highly repetitive exposure to images of humans and vehicles from a camera feed. That ability is ideal for use with drones patrolling perimeters seeking anomalies or in software that significantly reduces the number of false alarms reported to central monitoring station operators. Through use, the software continues improving its accuracy.” – Brian Baker. Valuable audit trail How soon will access control cards become extinct and why? “Access control cards will go the way of the dinosaur, but they still have some life left in them. For the short term, they have plenty of utility in minimum security use cases and leave a valuable audit trail. But for companies that are more technology-centric, particularly those with high value assets, we’re seeing demand for next-generation access control, which includes increased integration with video surveillance systems and professional monitoring services.” – Sean Foley. Which security markets are embracing touchless and contactless systems? “Touchless technology is not a new trend, but contactless systems and transactions have surged since the COVID-19 pandemic. Even after the pandemic is over, it is likely public perception of what is hygienic and acceptable in public spaces will have changed. [We are] seeing an uptick in touchless access control systems in the education and flexible office space markets.” – Brooke Grigsby.

Identity and access management in 2022 - what will the future look like?

As we enter into 2022, there is still a level of uncertainty in place. It’s unclear what the future holds, as companies around the world still contend with the COVID-19 pandemic. Remote working has been encouraged by most organisations and the move to a hybrid working system has become ‘business as usual’, for the majority of businesses. Some have reduced their office space or done away with their locations altogether. Following best security practices With all this change in place, there are problems to deal with. According to research, 32.7% of IT admins say they are concerned about employees using unsecured networks to carry out that work. Alongside this, 74% of IT admins thought that remote work makes it harder for employees to follow best security practices. This need to manage security around remote work is no longer temporary. Instead, companies have to build permanent strategies around remote work and security. The coming year will also create a different landscape for small and mid-sized businesses (SMBs). Here are some key predictions for next year and what to start preparing for in 2022: The reality of SMB spending around security will hit home SMBs had to undertake significant investments to adapt to remote working SMBs had to undertake significant investments to adapt to remote working, especially in comparison to their size. They had to undertake significant digital transformation projects that made it possible to deliver services remotely, during the COVID-19 pandemic. We’ve seen a shift in mindset for these companies, which are now more tech-focused in their approach to problem solving. According to our research, 45% of SMBs plan to increase their spending towards IT services in 2022. Around half of all organisations think their IT budgets are adequate for their needs, while 14.5% of those surveyed believe they will need more, to cover all that needs to be done. Identity management spending to support remote work For others, the COVID-19 pandemic led to over-spending, just to get ahead of things and they will spend in 2022, looking at what they should keep and what they can reduce their spending on. Areas like identity management will stay in place, as companies struggle to support remote work and security, without this in place. However, on-premise IT spending will be reduced or cut, as those solutions are not relevant for the new work model. Services that rely on on-premise IT will be cut or replaced. The device will lead the way for security We rely on our phones to work and to communicate. In 2022, they will become central to how we manage access, to all our assets and locations, IT and physical. When employees can use company devices and their own phones for work, security is more difficult. IT teams have to ensure that they’re prepared for this, by making sure that these devices can be trusted. Wide use of digital certificates and strong MFA factors Rather than requiring a separate smart card or fingerprint reader, devices can be used for access using push authentication There are multiple ways that companies can achieve this, for example - By using digital certificates to identify company devices as trusted, an agent, or strong MFA factors, like a FIDO security key or mobile push authentication. Whichever approach you choose, this can prevent unauthorised access to IT assets and applications, and these same devices can be used for authentication into physical locations too. Rather than requiring a separate smart card or fingerprint reader, devices can be used for access using push authentication. Understanding human behaviour Alongside this, it is important to understand human behaviour. Anything that introduces an extra step for authentication can lead to employees taking workarounds. To stop this, it is important to put an employee education process in place, in order to emphasize on the importance of security. The next step is to think about adopting passwordless security, to further reduce friction and increase adoption. Lastly, as devices become the starting point for security and trust, remote device management will be needed too. More companies will need to manage devices remotely, from wiping an asset remotely if it gets lost or stolen, through to de-provisioning users easily and removing their access rights, when they leave the company. Identity will be a layer cake Zero Trust approaches to security Identity management relies on being able to trust that someone is who they say they are. Zero Trust approaches to security can support this effectively, particularly when aligned with least privilege access models. In order to turn theory into practical easy-to-deploy steps, companies need to use contextual access, as part of their identity management strategy. This involves looking at the context that employees will work in and putting together the right management approach for those circumstances. For typical employee behaviour, using two factor authentication might be enough to help them work, without security getting in the way. How enterprises manage, access and store identity data There will also be a shift in how enterprises manage, access, and store that identity data over time For areas where security is more important, additional security policies can be put over the top, to ensure that only the right people have access. A step-up in authentication can be added, based on the sensitivity of resources or risk-based adaptive authentication policies might be needed. There will also be a shift in how enterprises manage, access, and store that identity data over time, so that it aligns more closely with those use cases. Identity management critical to secure assets in 2022 There are bigger conversations taking place around digital identity for citizenship, as more services move online as well. Any moves that take place in this arena will affect how businesses think about their identity management processes too, encouraging them to look at their requirements in more detail. Overall, 2022 will be the year when identity will be critical to how companies keep their assets secure and their employees productive. With employees working remotely and businesses becoming decentralised, identity strategies will have to take the same approach. This will put the emphasis on strong identity management as the starting point for all security planning.