Using Deep Learning Algorithms to Recognize Individual Faces

Finding a particular face in a crowd is something human minds have difficulty doing in settings much larger than a café. We are able to use context clues in such a setting, like a friend waving their arm or a table with just one person sitting at it. But in something more akin to a major league sports event with 40 thousand people such a task is impossible. Technology which can “fast-track” through massive amounts of data (hours of surveillance video with changing lighting and moving crowds) is now increasingly in demand. Facial recognition allows alerts to be sent out when a specific individual(s) enters a location and helps in post-event investigations as it can identify and track the movements of an individual.

As we have investigated previously, Deep Learning algorithms are the go to solution for these types of tasks. These are the same algorithms used in everything from predictive advertising, crime prediction, and chess/game playing software. Yet facial recognition is uniquely complex and comes with its own host of challenges. Pouring through vast amounts of data or trying to connect old images to the current appearance of an individual is just the beginning, but can still paralyze standard surveillance systems unable to make sense of the information. System hardware is simply too slowed down with the sheer volume of data necessary to perform the tasks needed. Furthermore, traditional “intelligent video” needs a consistent and stable background. It is for these reasons and more that this new, smarter breed of facial recognition is the future of video surveillance.

Something we have not looked at before in our “Security News” section are the two key steps of facial recognition algorithms; “Feature Extraction” and “Classification Learning”, defined briefly below.


Classification Learning makes use of so-called “shallow” learning and analysis; the kind used in old intelligent video solutions.

Feature Extraction sets the new technology apart from the old. This is where human design of features allow the system to perform adequately in specific environments even with subtle changes in background and lighting. However, this brings about some degree of sacrifice in accuracy.

 Employing Deep Learning in these tasks improves the accuracy of facial recognition to a significant degree. This is due to a greatly more sophisticated and modern algorithmic structure that more closely resembles human learning. The layers of such a program can reach above 100, permitting data processing in huge amounts and of increased complexity. Like the human learning around which it was designed, Deep Learning uses “layer by layer” feature-extraction processes. With each layer comes a different “weight”, which directly impacts what the program will learn about the components of visual data.


Because Deep Learning works alone and without human intervention, it can extract as many of these features  as possible, even if they are abstract or even impossible to describe. Features like this are why the programmers of these systems often cannot explains how their software was able to learn something new. The code is simply too abstract. With more features comes greater accuracy. Through these means, facial recognition above human levels can be achieved, and in a tiny fraction of the time.

 High level facial recognition of this caliber improves both security and investigation and has applications extending into many different industries. Banks, shops, hotels, and even bars and nightclubs all stand to benefit. Finding a face in a crowd of people almost instantly will only increase in demand in the near future.


Security Technology of South is proud to offer integration of this service and custom solutions for any and all security needs. Please contact us through email at on our website or via phone at  210-446-4863   24/7


Stakeholders Expectations When Securing a Medical Facility

Medical facilities can be a unique challenge for security integrators. They tend to have a more diverse set of security needs all under the same roof. So-called “Behavioral Health” (psychiatric) units will need a tighter grip than the front door, with the entrance to the emergency department falling somewhere in between the extremes. These differences do in fact require very different approaches within the same overall design solution both in terms of doors and access control as well as security cameras and monitoring. Some areas may even be legally prohibited from operating surveillance devices. On top of this, a solid base of network security and competency from the installer is a must in an environment where a hack would lead to the compromising of medical records and billing information.

Owners or shareholders of private medical ventures will share some common concerns. Diversion of drugs from the clinical setting is one of the most frequently cited reasons for smaller clinics wanting to upgrade security, but is also well within the concerns of any larger operation. These environments have lockdown capability needs similar to what is being implemented in campuses, and stand to benefit from similar mass-notification systems. Moreover, any medical facility will have to at minimum meet legal requirements concerning HIPAA laws and fire code.

In large settings with many departments, it will be necessary to identify more than one decision maker. Because security and access control structure in one area tends to ripple throughout, it is typical that officers from compliance departments, HR, and security will be involved at a minimum. There are titles found only in healthcare settings such as the “CXO” (Chief Experience Officer) who deal with the patient experience rating. Because this will impact virtually every aspect of the hospital, and more directly, funding, this will be an important area of consideration in designing a system. Variations in system architecture allow for a mixing and matching of locks on interior and exterior doors to meet the needs of the customer. The demand for a “one-card solution” is already here, and increasingly users want and expect to be able to manage the functions of these systems through their mobile devices.

When groups enter the building, RFID can be logged from a card carried by each person. It is possible to give varying levels of access to interior doors to different individuals, and of course to track movement and time spent in different areas. Interior access control gives advantages to both management and the general employee.

Having the diverse array of technologies of todays security industry available could seem daunting, but does more to make it easy to tailor access control capabilities of each area and entrance to the complex than it does to confuse the process. The market for security in the medical field goes deep, which is why those who hold the shares and call the shots trust a dedicated outside enterprise to handle those needs.

As a Security Integrator, Security Technology of South Texas is prepared to build a tailor fit system for Please contact us through email at on our website or via phone at  210-446-4863   24/7

Acadian Monitoring Services

Beginning in 2008, Acadian, previously an ambulance dispatch service, began providing video monitoring services within the United States. This company now maintains strong relationships with both manufactures and integrators of access control and video monitoring systems, and in 2017 alone their work led to the capture of over 60 criminals. A serious contender in the video monitoring marketspace, Acadian is now monitoring over 7000 devices nation wide.

This growing division of Acadian’s business makes use of what they term the“SureView Systems Immix Station Platform”, used since 2008. This proprietary platform “gives Acadian the ability to monitor many different video products, including NVRs, cameras, encoders, VMS’, and audio devices.” (”). It is built in an open architecture style setup which allows for the creation of custom integrations for emerging products. These factors have led to “SureView” becoming the second certified partner of Acadian.

What makes Acadian special in this industry is the quality of training they instruct their video analysts with. They are required to take online classes created by “The Monitoring Association”, SureView, and “The Telephone Doctor”, to insure the highest quality and to exceed industry standards. When you talk to an Acadian analyst, you get the sense that you are speaking to a well informed person who will be able to walk you through any issue. Weeks of hands on training with a supervisor is also required before even becoming an official trainee.

Acadian differentiates between “proactive” and “reactive” solutions. A reactive solution in video monitoring is focused on “improving a reaction from a third party” ( This is not to prevent a crime from occurring, but instead to ensure that the appropriate response is taken for any given security event. Video verified solutions are a good example of this, such as Videofied.  Solutions such as this provide police with better information about the event, reduce false alarms, and speed up response time from police services.

Proactive solutions are focused on the prevention of criminal acts and trespassing before the involvement of a third party is initiated..

“Outdoor video monitoring solutions with video analytics and voice down technology”( is one way to get a trespasser to leave the premises without involvement of police. Acadian is able to access an on-site speaker to speak in real time with whoever triggered the event and warn them of impending police involvement if they do not leave. Done correctly, sites with outdoor inventory and outdoor sites in general can often be protected without a call to the cops.

As an authorized dealer of many of the technologies that Acadian monitors, Security Technology of South Texas often makes use of Acadian in our projects requiring real time monitoring and response to security events. Our experience with Acadian has shown their service to be above industry standards as well as highly effective. To learn more about what we can do to product your site or indoor security, please contact us at on our website or via phone at  210-446-4863   24/7.

Avigilon Analytics




Avigilon is a Vancouver based security equipment designer and manufacturer, perhaps most well known for the software they have developed to analyze raw video data, with no input other than the pixels streamed through an HD camera setup. “Open Video Management” using what they term “Self-Learning” video analytics is the cornerstone of any modern video analytics solution. The company also manufactures several lines of high quality HD cameras and access control gear, but it is not a requirement that all equipment be from Avigilon. Avigilon analytics is performed on-site with a proprietary set of hardware and software, and is effectively limited only by the quality of the video input.

What does this all mean for the consumer? For the residential market, there is not much application, and most home owners would see the cost as extraordinary, considering the increasingly cheap residential offerings from mainstream security integrators. It is also generally not necessary to run such extensive analytics in a residential setting. What Avigilon’s video analytics are particularly useful for are larger, enterprise-scale security operations, such as car lots, schools, and highly trafficked gates. This is something our company has considerable experience with, both in installing and integrating with other cameras and access control systems, as well as servicing and maintaining this type of equipment.

For example, let’s look at our most popular security solution featuring Avigilon; car dealerships. Avigilon’s analytics recognize a car versus some other object and distinguishes between a person and an animal or some other moving object which is not a security threat. The degree to which any software is actually “self-learning” is certainly up for debate, though the type of software underpinning these analytics systems is similar in structure to the kind of predictive software used by Google, Amazon, or Facebook to predict future purchases and analyze behaviors. The idea is that the software is able to self-code within the limited scope of object detection and threat discernment. This implies that each individual system that is integrated with Avigilon analytics will be slightly different over time for each installation in order to better perform in that particular setting.

Security Technology of South Texas is well versed in customizing analytics solutions to each customer based on their concerns and security needs. As we move into the future, analytics will become a de facto component of any competent access control and video surveillance installation, as it is able to reduce or eliminate false alarms, the traditional bane of functional, digital security.

Security Technology of South Texas is happy to offer custom designed systems such as this from the ground up or integrated into existing infrastructure, where possible. We are available 24/7 at  on our website or via phone at 210-446-4863.Avigilon-logo