Utilizing Video Analytics: Facial Recognition in Retailing

Currently, one of the most contentious video analytics is facial recognition (FR). Across the globe it has sparked considerable debate about whether it is a force for good or one of the more sinister surveillant technologies developed thus far. Recent ECR Retail Loss research captured some of the contrasting views about this technology, including the opportunities it presents and some of the challenges of operationalizing it in a retail context.

Respondents fell into three overlapping camps: those that considered it to be one of the most important crime prevention developments in recent years, those that were deeply concerned about the negative impact its use could have on their company’s brand, and those that were struggling to understand how it could be made to work cost effectively in a retail environment.

Crime Prevention Opportunities

Most respondents to the ECR Retail Loss research were extremely interested in what facial recognition could potentially do to help them manage their problem of external theft by persistent shop thieves. One respondent suggested that it was the first real step change in loss prevention technologies in many years: “…it gets me excited again about what we might be able to do in loss prevention.”

- Sponsors -

In many respects it is easy to see why respondents would be very interested in this technology. Trying to identify when a persistent offender has entered a retail store is not an easy task; existing strategies typically rely on staff present at the time remembering what they look like and then taking appropriate action. In addition, building case files against these types of offenders is currently a highly manual and time consuming activity. Therefore, the allure of facial recognition is readily apparent—the ‘automatic’ identification of known offenders as they enter any property covered by the technology.

Of course, the reality is much more nuanced and of concern is the extent to which facial recognition will be viewed by customers entering stores where it is in operation as an overly intrusive surveillant technology.

Negative Impact on Business Brand

This concern was the biggest factor that was currently holding back the use of facial recognition by many of the respondents to the research: “There is a diktat that we are not going anywhere near facial recognition because of reputational issues.” Certainly, negative publicity about facial recognition in several countries was fueling these concerns, not the least being its extensive use by the police and other government agencies in China. Consequently, this has raised numerous concerns about the legality of its use by public and private bodies and the purposes for which it can be used.

Operationalizing Facial Recognition

These concerns have led many retailers to not even begin using facial recognition, but some have undertaken trials and reported both positive and negative experiences. While few are willing to go on record to describe their experiences (another indicator of concerns about reputational issues), those that have shared information in closed industry fora have highlighted the following:

  1. A positive impact on levels of external theft and retail loss in stores where it is being used.
  2. An increase in staff confidence and feelings of safety in stores where it is being used.
  3. Concerns about who should respond to an alert and what actions they should take.
  4. Concerns about liability issues when accessing shared offender databases.
  5. Difficulties building a robust return on investment model.

Certainly, the issue of how to operationalize the data coming from facial recognition systems is something that future users will need to address—which store staff should receive the alerts, how should they respond, and how do the answers to these questions fit with a company’s stated policies on staff safety and security? 

Facial vs. Object Recognition

While the identification of individuals through video technologies may still be a step too far for many main retailers, there is certainly much more enthusiasm and considerably less privacy-associated friction for what might be described as object recognition systems. This is the use of video technologies to uniquely identify and track objects, be that a human being or a box of products. Under this scenario the system does not necessarily know or care who I am, but is more interested in where I have been, what I have done, and when. For instance, some self-checkout systems now ‘track’ shoppers to associate them with a payment point before allowing them to leave a designated area. To date, these types of systems have attracted far less negative attention and may well be a more acceptable form of public space video recognition technology in the near term, particularly if they can help retailers manage their loss prevention issues more effectively.


Adrian Beck
Adrian Beck

Video Watch is a monthly column written by Professor Adrian Beck sharing insights on the proactive use and impact of video technologies in retail. It reflects the latest research and monthly discussions of the Video Working Group of ECR Retail Loss, the leading global think tank on retail loss. The research commissioned by ECR Retail Loss is supported by independent research grants provided by Genetec and other leaders in retail loss prevention.