Sightcorp logo

Anonymous Video Analytics: Face Detection Software for Digital Signage

Posted By :
Comments : 0

Digital signs are quite a fixture in stores, shopping malls, airports, train stations, and many other public venues. As this medium for digital signage-based advertising becomes increasingly commonplace, network operators are incorporating Anonymous Video Analytics to more effectively measure the audience viewing them. But what is Anonymous Video Analytics and how does it measure the audience viewing a particular message from a digital sign?

What is Anonymous Video Analytics (AVA)?

Anonymous Video Analytics is a computer vision technology that uses a technique known as pattern detection, for gathering metrics about digital signage audience engagement. AVA typically involves using a camera mounted on a digital signage unit and a computer running face detection software to capture data on the individuals viewing the signs.

It is important to note, however, that the data captured by AVA is completely anonymous. Because the software uses pattern detection algorithms, it cannot identify an individual. There are no images stored and no personal information is collected. The only data that is stored is of an anonymous, aggregate, statistical nature.

However, many still find this confusing and often refer to AVA as facial recognition. That’s a misnomer. The correct term is face detection.

Let’s take a look at the difference between the two.

The difference between Face Detection and Facial Recognition

Face Detection software uses pattern detection algorithms that scan hundreds of thousands of anonymous face images for pixel intensity variations. These variations are dark areas where eyes tend to be and light areas where noses tend to be. This information is then used by the algorithms to determine the type of pixel arrangements which resemble the general pattern of a human face. These algorithms can also be extended to recognize pixel combinations that correspond to age, gender, and other important demographical information.

In contrast to face detection, facial recognition is a software program that is designed to obtain a positive identification of an individual against a database that archives personal information. It uses deep learning algorithms to maps an individual’s facial features mathematically and stores the data as a faceprint. In other words, facial recognition answers the question:

How does Anonymous Video Analytics work?

If a person walks up to a digital signage unit that is enabled with Anonymous Video Analytics, the camera sensor mounted on to it will take what it sees and run it through the AVA software. It will then will determine if pixel patterns present resemble a human face and then count that as a viewer.

When a face is detected, it is not matched against a database of known individuals. From a privacy standpoint, this is important to note because, in essence, there is no database. There are only algorithms that use mathematical information to determine if a combination of pixels matches a statistical pattern of a human face. This information is stored as log files with information such as the time of day, the number of viewers, and some general demographic characteristics.

Why use Anonymous Video Analytics

If you’re running an advertising campaign using digital signage, you’ll most likely want to know how many people saw your ad. You’ll also want to understand the effectiveness of the dollars you spend on your digital signage-based advertising initiatives.

Anonymous Video Analytics provides a way for marketing professionals to determine viewership metrics for digital signage content. These metrics include the following:

  • Notice (how many people looked at the ads)
  • Demographics (gender and age bracket)
  • Dwell time (how long they looked at the ads
  • Time of day (when they viewed the ads)


With AVA-enabled digital signage, you can be better informed about who your audience is and at what time of the day your promotional content mostly viewed. This is quite a major leap from traditional audience measurement techniques, where teams of people physically count the numbers of passersby.

Other interesting articles

Melissa Roux Author
follow me
About the Author
Hobbies: reading, hiking, football and traveling. Why I'm an expert: I have 6 years of experience in copywriting; I'm always learning new things; I started out my marketing career in the education sector, where I had the opportunity to learn about multiple fields; I started working in the tech industry last year and find it highly engaging