Published in The Observer, by Tom Chivers, Sun 4 Aug 2019 09.00 BST

The technology is helping to combat crimes police no longer deal with, but its use raises concerns about civil liberties

Paul Wilks runs a Budgens supermarket in Aylesbury, Buckinghamshire. Like most retail owners, he’d had problems with shoplifting – largely carried out by a relatively small number of repeat offenders. Then a year or so ago, exasperated, he installed something called Facewatch. It’s a facial-recognition system that watches people coming into the store; it has a database of “subjects of interest” (SOIs), and if it recognises one, it sends a discreet alert to the store manager. “If someone triggers the alert,” says Paul, “they’re approached by a member of management, and asked to leave, and most of the time they duly do.”

Facial recognition, in one form or another, is in the news most weeks at the moment. Recently, a novelty phone app, FaceApp, which takes your photo and ages it to show what you’ll look like in a few decades, caused a public freakout when people realised it was a Russian company and decided it was using their faces for surveillance. (It appears to have been doing nothing especially objectionable.) More seriously, the city authority in San Francisco have banned the use of facial-recognition technologies by the police and other government agencies; and the House of Commons Science and technology committee has called for British police to stop using it as well, until regulation is in place, though the then home secretary (now chancellor) Sajid Javid, said he was in favour of trials continuing.

Paul Wilks, Owner Wilks Budgens

Paul Wilks. Owner of WilksBudgens

Wilks Budgens Store

There is a growing demand for the technology in shops, with dozens of companies selling retail facial-recognition software – perhaps because, in recent years, it has become pointless to report shoplifting to the police. Budgets for policing in England have been cut in real terms by about 20% since 2010, and a change in the law in 2014, whereby shoplifting of goods below a value of £200 was made a summary offence (ie less serious, not to be tried by a jury), meant police directed time and resources away from shoplifting. The number of people being arrested and charged has fallen dramatically, with less than 10% of shoplifting now reported. The British Retail Consortium trade group estimates that £700m is lost annually to theft. Retailers are looking for other methods. The rapid improvement in AI technologies, and the dramatic fall in cost, mean that it is now viable as one of those other methods.

“The systems are getting better year on year,” says Josh Davis, a psychologist at the University of Greenwich who works on facial recognition in humans and AIs. The US National Institute of Standards and Technology assesses the state of facial recognition every year, he says, and the ability of the best algorithms to match a new image to a face in a database improved 20-fold between 2014 and 2018. And analogously with Moore’s law, about computer processing power doubling every year – the cost falls annually as well.

In ideal environments such as airport check-ins, where the face is straight on and well lit and the camera is high-quality, AI face recognition is now better than human, and has been since at least 2014. In the wild – with the camera looking down, often poorly lit and lower-definition – it’s far less effective, says Prof Maja Pantic, an AI researcher at Imperial College London. “It’s far from the 99.9% you get with mugshots,” she says. “But it is good, and moving relatively fast forward.”

 

Each algorithm is different, but fundamentally, they work the same way. They are given large numbers of images of people and are told which ones are the same people; they then analyse those images to pick out the features that identify them. Those features are not things like “size of ear” or “length of nose”, says Pantic, but something like textures: the algorithm assesses faces by gradients of light and dark, which allow it to detect points on the face and build a 3D image. “If you grow a beard or gain a lot of weight,” she says, “very often a passport control machine cannot recognise you, because a large part of the texture is different.”

But while the algorithms are understood at this quite high level, the specific things that they use to identify people are not and cannot be known in detail. It’s a black box: the training data goes into the algorithm, sloshes around a bit, and produces very effective systems, but the exact way it works is not clear to the developer. “We don’t have theoretical proofs of anything,” says Pantic. The problem is that there is so much data: you could go into the system and disentangle what it was doing if it had looked at a few tens of photos, perhaps, or a few hundred, but when it has looked at millions, each containing large amounts of data itself, it becomes impossible. “The transparency is not there,” she says.

Still, neither she nor Davis is unduly worried about the rise of facial recognition. “I don’t really see what the big issue is,” Pantic says. Police prosecutions at the moment often rely on eyewitnesses, “who say ‘sure, that’s him, that’s her’, but it’s not”: at least facial recognition, she says, can be more accurate. She is concerned about other invasions of privacy, of intrusions by the government into our phones, but, she says, facial recognition represents a “fairly limited cost of privacy” given the gains it can provide, and given how much privacy we’ve already given up by having our phones on us all the time. “The GPS knows exactly where you are, what you’re eating, when you go to the office, whether you stayed out,” she says. “The faces are the cherry on top of the pie, and we talk about the cherry and forget about the pie.”

As with all algorithmic assessment, there is reasonable concern about bias. No algorithm is better than its dataset, and – simply put – there are more pictures of white people on the internet than there are of black people. “We have less data on dark-skinned people,” says Pantic. “Large databases of Caucasian people, not so large on Chinese and Indian, desperately bad on people of African descent.” Davis says there is an additional problem, that darker skin reflects less light, providing less information for the algorithms to work with. For these two reasons algorithms are more likely to correctly identify white people than black people. “That’s problematic for stop and search,” says Davis. Silkie Carlo, the director of the not-for-profit civil liberties organisation Big Brother Watch, describes one situation where an 18-year-old black man was “swooped by four officers, put up against a wall, fingerprinted, phone taken, before police realised the face recognition had got the wrong guy”.

That said, the Facewatch facial-recognition system is, at least on white men under the highly controlled conditions of their office, unnervingly good. Nick Fisher, Facewatch’s CEO, showed me a demo version; he walked through a door and a wall-mounted camera in front of him took a photo of his face; immediately, an alert came up on his phone (he’s in the system as an SOI, so he can demonstrate it). I did the same thing, and it recognised me as a face, but no alert was sent and, he said, the face data was immediately deleted, because I was not an SOI.

Facewatch are keen to say that they’re not a technology company themselves – they’re a data management company. They provide management of the watch lists in what they say is compliance with the European General Data Protection Regulation (GDPR). If someone is seen shoplifting on camera or by a staff member, their image can be stored as an SOI; if they are then seen in that shop again, the shop manager will get an alert. GDPR allows these watch lists to be shared in a “proportionate” way; so if you’re caught on camera like this once, it can be shared with other local Facewatch users. In London, says Fisher, that would be an eight-mile radius. If you’re seen stealing repeatedly in many different cities, it could proportionately be shared nationwide; if you’re never seen stealing again, your face is taken off the database after two years.

Carlo is not reassured: she says that it involves placing a lot of trust in retail companies and their security staff to use this technology fairly. “We’re not talking about police but security staff who aren’t held to the same professional standards. They get stuff wrong all the time. What if they have an altercation [with a customer] or a grievance?” The SOI database system, she says, subverts our justice system. “How do you know if you’re on the watch list? You’re not guilty of anything, in the legal sense. If there’s proof that you’ve committed a crime, you need to go through the criminal justice system; otherwise we’re in a system of private policing. We’re entering the sphere of pre-crime.”

Fisher and Facewatch, though, argue that it is not so unlike the age-old practice of shops and bars having pictures up in the staff room of regular troublemakers. The difference, they say, is that it is not relying on untrained humans to spot those troublemakers, but a much more accurate system.

The problem is that, at the moment, there is very little regulation – other than GDPR – governing what you can and can’t do with a facial-recognition system. Facewatch say, loudly and often, that they want regulation, so they know what they are legally allowed to do. On the other hand, Carlo and Big Brother Watch, along with other civil liberties groups, want an urgent moratorium and a detailed democratic debate about the extent to which we are happy with technologies like these in our lives. “Our politicians don’t seem to be aware that we’re living through a seismic technological revolution,” she says. “Jumping straight to legislation and ‘safeguards’ is to short-circuit what needs to be a much bigger exercise.”

Either way, it needs to happen fast. In Buckinghamshire, Paul Wilks is already using the technology in his Budgens, and is finding it makes life easier. When he started, his shop would have things stolen every day or two, but since he introduced the system, it’s become less common. “There’s definitely been a reduction in unknown losses, and a reduction in disruptive incidents,” he says. As well as a financial gain, his staff feel safer, especially late at night, “which is good for team morale”. If enough retailers start using facial-recognition technology before the government takes notice, then we may find that the democratic discussion has been short-circuited already.

 

Crime Report 2019

The ACS 2019 Crime Report shows that crimes committed against the convenience sector cost an estimated £246m over the last year, equivalent to over £5,300 for every store in the UK, or what amounts to a 7p tax on every transaction.

The single biggest trigger for violence and abuse was shop theft. ACS estimates that there have been over a million incidents of theft over the last year, with retailers reporting that the vast majority of thefts committed against their business (79%) are by repeat offenders that aren’t being dealt with by local police forces.

Key findings from this year’s Crime Report include:

The three biggest concerns for retailers are violence against staff, theft by customers and verbal abuse against staff

The report estimates that there were almost 10,000 incident of violence in the sector over the last twelve months

Of crimes committed where a weapon was present, the most commonly used weapon was a knife (68% of incidents)

The report also shows that there is a clear link between retailers just doing their jobs by upholding the law, and being subject to abuse. The top three triggers for aggressive or abusive behaviour are challenging shop thieves (1), enforcing age restrictions, for example refusing a sale to someone without ID (2) and refusing to serve drunks (3).

Download the 2019 Crime Report

Watch video highlights here

Facewatch’s facial recognition solution is powered by an Intel® NUC, a mini-PC, and as an Intel IOT (Internet of Things) partner Facewatch is pleased to announce a new campaign to promote the use of facial recognition in the retail sector. Robert Moss a well know technology journalist has written the following introduction which is available to read here or at https://www.insight.tech/retail/facial-recognition-puts-shoplifters-out-of-business.

Facial Recognition Puts Shoplifters Out of Business

 

There are all sorts of retail crime: smash-and-grabs, bad checks, credit card fraud. But worldwide, shoplifters cause the greatest amount of grief for retailers of all sizes. And it’s not just a few bad actors. Shoplifting is a profession, and organized retail crime (ORC) even has its own Wikipedia page.

The root of the problem is that law enforcement agencies often have neither the mandate nor the resources to handle offences like shoplifting. No surprise that retail theft is on the rise.

For example, shoplifting in the United Kingdom is way up while police reports are way down. Experts now say that 90 per cent of shoplifting goes unreported. This is because retailers know there’s no point in filing a report since current law allows the police to investigate only if the value of the stolen goods is greater than £200. This has emboldened criminals to plot their crimes to remain under that number to avoid prosecution.

Across the Atlantic, shoplifting is also on the rise. A 2018 survey shows that ORC costs US retailers approximately $778,000 per $1 billion in sales, an all-time high. The same survey also reports that more than half of retailers in states that have enacted tough anti-ORC laws have seen no increase in support from law enforcement.

All of this illustrates the need for new ways to help retailers and other businesses that no longer receive police protection. But data laws and privacy concerns in many countries make it difficult for retailers to use technology such as facial recognition to prevent theft.

Yet attitudes are changing about the use of cameras.

For instance, a majority in the UK now appears to embrace using facial recognition to prevent shoplifting. According to a YouGov survey:

  • 93 per cent are in favour of local businesses and the police working together by sharing (facial recognition) images to prevent and solve crime.
  • 77 per cent say that if facial recognition technology does not store their image, unless they’re a person of interest, they’d be happy to have their face scanned by these cameras.
  • 73 percent feel more comfortable visiting venues protected by facial recognition systems.

How AI Helps Prevent Shoplifting

But many hurdles make it next to impossible for large chains, never mind mom-and-pop stores, to be in the facial recognition data business. What retailers need is an easy-to-deploy, cost-effective solution that complies with data privacy laws to catch the bad guys.

The Facewatch Facial Recognition Solution provides shoplifting prevention technology that meets these criteria for retailers, restaurants, and other venues.

For example, a football club in Bedfordshire, England had a significant shoplifting problem in its shop, costing the club approximately £1,000 worth of merchandise each month. In 90 days after installing the Facewatch solution, it eliminated the problem from its premises.

Facial Recognition as a Service

Facewatch uses the as-a-service technology model, making advanced facial recognition affordable for even small businesses. The company’s watchlist lives on the cloud. It’s a centralized, managed database of biometric data (not stored photos) corresponding to the faces of peoples who’ve shoplifted or committed other crimes at businesses that subscribe to the service (Figure 1).

Figure 1. Facewatch matches faces against known offenders within seconds of them entering a business.

The hardware to run Facewatch is simple to deploy. It includes a standard HD CCTV camera and Intel® NUC, a mini-PC that is only 4×4 inches in size and consumes very little power. Its performance enables it to play and record video at 4K Ultra HD clarity, making it ideal for a facial recognition system.

The cameras—placed at store entrances—send an image to an on-site NUC loaded with software that converts the image to an algorithm. The algorithm is compared to those in the Facewatch database on the cloud. If it discovers a match, an alert that includes the image of the individual entering the establishment—along with an accuracy reading—is sent to the retailer’s smartphone or other device, warning it that a known criminal on the watchlist has entered its business.

To add a shoplifter to the watchlist takes only six key presses and about 20 seconds, making it easy for store or security staff, and it doesn’t interfere with their normal duties. “They simply follow a dropdown menu, the time and date are automated, tick the box, the whole thing’s designed to be simple,” said Nick Fisher, CEO of Facewatch.

The solution does not retain any personal data on anyone not on the watchlist. “If no match is discovered, the image is deleted in 0.3 seconds,” Fisher said, “and the entire process—from the moment a known shoplifter comes through the door, to the instant the retailer gets an alert—takes place in less than two seconds.”

The algorithm data that corresponds to the faces of people on the watchlist is meaningless on its own. In fact, if someone hacked into the database, they could not reconstruct images of people’s faces based on the algorithm data.

GDPR Compliance

“We’re improving the speed and accuracy of our algorithms all the time,” said Fisher. “This not only helps ensure our customers have the best possible technology, it also ensures the solution follows government regulations.”

The solution meets General Data Protection Regulation (GDPR) compliance, protecting businesses from being held liable for violating privacy laws.

“In setting up Facewatch, we worked with multiple government agencies to confirm the rules of using our watchlist,” said Fisher. “The laws in the UK on meeting the Substantial Public Interest test are the toughest in the world. That means businesses in other countries can use our solution with confidence.”

As more companies deploy facial recognition solutions to reduce shoplifting, the use of such technology may become as common as using a credit card or a mobile app to pay for goods. Public perception is already in favour of using facial recognition for this purpose. Moreover, retailers need a simple and inexpensive way to reduce shoplifting and other crimes, preserve more of their profits, and make their establishments more appealing to customers.

Robert Moss 

 

Facewatch is leading the drive to support retailers in reducing store theft, staff violence and abuse which has seen an unprecedented rise in recent months by partnering with Store Excel.

Store Excel is the fastest growing online and digital community of independent retailers in the UK. Their aim is to support retailers by providing an interconnected network of information, advice and business growth opportunities.

David Gilroy, CEO, Store Excel:

“Store Excel exists to support retailers and to provide information and access to the latest and best products and services. We understand that store security is becoming one of the most worrying issues for UK retailers and by working with Facewatch I believe we can alert our members to a new technology which will improve the environment for those who work in the sector and thereby improve the experience for customers and reduce losses. Store Excel will be using a combination of online communications and telephone marketing to speak to our members and help answer questions about facial recognition and its place in the sector. Technology continues to be a driver of innovation on the high street and it is important that facial recognition is explored as a new force for good”.

 

Nick Fisher, CEO, Facewatch:

“Facewatch is now market ready and has been undergoing successful trials in retailers across the UK for the last 12 months. We are now rolling out the solution to the whole UK retail sector and this starts with helping potential retail clients understand the way facial recognition works in a commercial situation and how effective it is. We have been very careful to ensure data compliance and have a unique approach by being the data controller. We have also commissioned market research to gauge public reaction to the technology which proved positive*. Store Excel also has a unique position in the sector, providing advice, new product and service information to their members and are a highly trusted voice, for us this is a perfect opportunity to partner with them”

Facewatch – product overview:

Facewatch provides retailers with a complete solution that enables store owners and staff to monitor who comes into their store using Facial recognition. A standard HD camera is set up to capture facial images of customers as they enter the store. Each image is checked against a watch list of images, managed by the Facewatch secure cloud, and if there is a match of a ‘person of interest’, who has been added to the stores watch list previously, an alert will be sent to the manager’s phone. The system uses the latest facial recognition algorithms providing a very high level of accuracy, it is easy to install by security industry professionals and to use by non-technical operators. Images captured by the system who do not match an image on the watch list are immediately and securely deleted. The Facewatch system complies to all the required codes of conduct under European GDPR rules as Facewatch is the official data controller.

Recent testimonials from Facewatch trials

Luton Town FC

“We installed Facewatch in our Luton Town FC Store 5 months ago as a result of continued theft of high-value stock. Since the system went live our losses have reduced by 100%. This is an outstanding result and the savings made have enabled us to fund the entire installation and 3 years license fees. We will roll out Facewatch to our stadium shop in May 2019. I would highly recommend Facewatch to any retailer experiencing any type of theft or anti-social behaviour”.
Siobhan Kos-Hodge, Luton Town FC, Head of Retail

 

Wilks Budgens, Aylesbury

“Since installing Facewatch we have seen a reduction in losses of over 25%. Using Facewatch technology is a significant enhancement from the existing solution where we have to log on to the web to view images of Subjects of Interest and try to remember them all. The Facewatch team, especially George, has been great to work with and I would highly recommend their technology and the people that work at Facewatch too.”
Paul Wilks, Owner Budgens Aylesbury

*References #1

YouGov managed independent public poll to ask a number of key questions regarding facial recognition with summary below: (2,029 polled)

86.2% Agreed that Facial recognition technology can be used in everyday life to prevent and solve crime and should be used to support businesses and the police
76.4% agreed if facial recognition technology does not store my image unless I am a person of interest. I would be happy to have my face scanned by these cameras
92.5% agreed that local businesses and the police should be working together by sharing images to prevent and solve crime
66.5% were confident in the accuracy of facial recognition technology to identify the correct person of interest
72.6% agree they would feel more comfortable visiting venues that I know are protected by facial recognition systems

Reference #2

Association of convenience stores 2019 report:

https://www.acs.org.uk/research/crime-report-2019

The 2019 Crime Report shows that crimes committed against the convenience sector cost an estimated £246m over the last year, equivalent to over £5,300 for every store in the UK, or what amounts to a 7p tax on every transaction.

The single biggest trigger for violence and abuse was shop theft.

ACS estimated that there have been over a million incidents of theft over the last year, with retailers reporting that the vast majority of thefts committed against their business (79%) are by repeat offenders that aren’t being dealt with by local police forces

The three biggest concerns for retailers are violence against staff, theft by customers and verbal abuse against staff

The report estimates that there were almost 10,000 incidents of violence in the sector over the last twelve months

Of crimes committed where a weapon was present, the most commonly used weapon was a knife (68% of incidents)

The report also shows that there is a clear link between retailers just doing their jobs by upholding the law and being subject to abuse. The top three triggers for aggressive or abusive behaviour are challenging shop thieves (1), enforcing age restrictions, for example refusing a sale to someone without ID (2) and refusing to serve drunks (3).

Unable to rely on the police for help, many retailers are adopting new security measures to defend their stores from light-fingered offenders

Convenience store magazine

Ask retailers how a particular category performs in-store and you’ll get an array of answers, from tobacco to food to go. Quiz them on the best symbol group and the debate might rage for hours. But ask what impact shoplifting is having on the sector, and the answer is unanimous. “Shoplifting is bad at the moment – as bad as it’s ever been,” says Paul Stone, who owns the Stone’s Spar group of stores in Manchester.

“It’s prevalent,” echoes Jonathan James, owner of James Convenience Retail, which comprises 66 stores across the belt of England.

In its 2019 Crime Report, the Association of Convenience Stores (ACS) estimates that the incidents of shop theft have increased over the past year, despite figures from the Office for National Statistics showing that shop theft reported to the police has declined. In fact, many retailers surveyed by the ACS claim that the response they receive from the police actively deters them from reporting incidents.

“Shop crime’s not really getting followed up by the police,” says Middlesbrough Go Local retailer Bay Bashir. “Everyone’s talking about it at the moment.”

Spar Lindford owner Julian Taylor-Green agrees: “Our relationship with the police is a nightmare. The government are cutting costs, the police are then cutting costs and then blaming central government, and the people that are being held to ransom are the likes of us.

“It’s very difficult to get the police to commit to anything at all.”

With police across the UK failing to take action against shoplifters, many retailers are taking matters into their own hands and upping their security measures in a bid to reduce the problem.

Mark Canniford, owner of Spar Loxton Road, Weston Super Mare, and newly elected town mayor, has found chiller door alarms to be a cost-effective deterrent.

“We’re always trying to make it harder for shoplifters all the time,” he says. “We’ve started using little alarms on our doors which put shoplifters off because they know as soon as they hear the alarms that we’re looking. It was [Londis retailer] Steve Bassett who got me onto it – you can buy them from a DIY store. They can pay for themselves in days, rather than years. Because everyone knows what they [the shoplifters] are doing, they tend to behave themselves.”

Another low-cost way to protect your store is through layout and Paul has recently changed around his Princess Street store to deter shoplifters. “It used to be that you would walk in and if you turned right, you’d be in the sandwich area, and if you went straight in you’d be in the centre of the store,” he explains. “We’ve stopped that turn right so that everyone has to walk into the middle of the store – they can’t just grab and go. We’ve put stacks of low-value products, such as water, on the shopfloor, which is too heavy and not worth enough to shoplift.”

Jonathan has also experimented with what he calls “defensive merchandising”.

“You’re putting the stock on shelves that you know will sell in the next couple of days – the right number of facings, but not deep. You’ll see four bottles on-shelf, rather than 10, and top it up regularly. We’ve filled shoplifting hot spots with sharing bags of crisps and toilet roll multipacks. We also use convex mirrors so that they can’t hide round corners.

“At one store we had two entrances, so we’ve shut one off completely and we’re looking to have one entry and one exit past the till.”

In some cases, more extreme measures are necessary. When one of his stores was losing up to £1,000 a week through theft, Jonathan called on the East of England Co-op’s Secure Response Group.

“On a temporary basis for six weeks we hired store detectives,” explains Jonathan, “one out in the back looking at the cameras and suspicious behaviour, and one at the door waiting to stop people.

“The results were staggering – I think we got 39 in the first week and 103 over six weeks. Once we said enough’s enough staff morale improved massively and so did staff retention. The thieves realised we won’t stand for this. It worked brilliantly all round.

“Going forward, any time we get high levels of stock loss we’ll use EoE to step in and help for a month or six weeks. A store detective doing a 40-hour week costs £580 on a temporary contract, but our shop theft was costing £1,000 a week – it was a business decision. We need it all the time, but unfortunately we can’t afford it.”

Another deterrent is CCTV. “We’ve always put a big customer-facing screen at the front of the door and a good camera – it’s a really good deterrent,” says Paul.

He claims that retailers not only need to ensure that their cameras are good quality, but also that their digital video recorders(DVRs) are up to the job. “Technology improves and cameras are higher definition, so you have to make sure they’re up to date. We’ve got to the stage where the latest cameras are better than the DVR,” he says.

“If you’re recording on 28 cameras and have to take a month’s worth of footage, you can save images, but if the memory isn’t good enough then they’ll be lower res. We started with a one terabyte DVR and now we’ve invested in eight terabytes.”

Chris Grocott, director at Cricklewood Electronics, has witnessed retailers facing similar issues. “With old cameras, you could get a month’s worth of recording on a terabyte. But with the new HD cameras one terabyte may only last a week.

“We get people phoning up saying ‘How can I see footage from three weeks ago?’ But the camera only has one week’s-worth of recording as it automatically overwrites older data.”

Lee Jasper, head of marketing and product solutions group at ADT, agrees that the issue needs addressing. “For businesses that experience a high level of footfall, someone may be consistently committing a crime against them over a period of time, meaning that, for a case to be proven, footage over a more prolonged period may be required by law enforcement.”

Beyond their traditional role of capturing visual evidence of criminals in the act, cameras can also help to identify shoplifters as soon as they enter the store, thanks to the development of facial recognition systems.

Facewatch shop door 2

“Facewatch uses the latest algorithms to identify biometrics of the face and maps that in the cloud against known criminals,” explains Stuart Greenfield, marketing consultant for Facewatch. “Some 99% of stores have CCTV and on a daily basis they’ll do stock control and identify losses of certain products. They’ll then look at the CCTV to identify who took whatever was stolen. They can then get an image [of the shoplifter] from their CCTV and add it to their watch list.”

This could be extremely useful when you consider that retailers surveyed for the ACS Crime Report believed 79% of shoplifters are repeat offenders.

“If you’re a store manager, your mobile will alert you if someone walks into your store who has a known history of shoplifting or violence. The police can also add images to the database via the shop manager,” says Greenfield.

He describes how one convenience retailer it worked with had seen shoplifting fall 25% since using the system. “His staff are now much more relaxed, more confident and more happy to spend time with customers. All in all, it’s given him his money back in a couple of weeks,” Greenfield says.

He claims that there is also the potential for several retailers in an area to use Facewatch and then share information with one another on repeat offenders.

Jonathan claims that sharing intelligence with other retailers can really help. “I’d advise retailers to be proactive with other retailers – while we share customers, we also share thieves so why not talk to each other. Shopwatch schemes are really useful and helpful.”

How you choose to handle security comes down to the individual needs of your store, but if you are already losing a significant amount to theft, then an investment may quickly pay for itself, states ADT’s Jasper.

“There is no price affixed to peace of mind. That being said, owners should look at the occurrence and regularity of theft from their premises and go from there. If a convenience store is losing £5,000 of stock per annum to shoplifting, then this may be a good starting point for how much they should spend per year on securing their premises.

“The question for convenience retailers should not be ‘how much will it cost me to have security?’, but should instead be ‘how much will it cost me not to have security?’.”

Simple steps to curbing crime

To make any investment in a security system as beneficial and as cost effective as possible, there are a number of additional measures retailers should take to protect their business, according to security experts ADT:

  • Low tech deterrence – techniques such as mirrors in aisles and visible signs against shoplifting can help deter criminals
  • Effective inventories – if stock loss is happening, business owners need to know where it is coming from. It might be that additional security is needed in certain parts of a store where shoplifters are able to operate more freely
  • Educate employees – ensure that employees are aware of the risks of shoplifting and theft. They need to be more aware during peak times, beware of customers wearing bulky clothing or carrying large bags, and of shoppers who spend too much time watching staff. Having vigilant staff is key to deterring shoplifters
  • Organise stores effectively – how a store is set out can be a deterrent to shoplifters. Convenience retailers should ensure that their store is designed so that staff have a clear line of sight through it, meaning that they can see the majority of customers and staff at all times. Expensive items, as well as those that are easy to steal, should be moved to the front of the store, near the tills where staff can see them
  • Illumination – if a store is as bright as possible, thieves will feel that they are less likely to get away with committing a crime. Good illumination will also assist CCTV cameras to obtain the best possible image quality.

Facewatch has won the total support of Paul Wilks after a successful trial of Facewatch’s facial recognition security camera system at his store at Jubilee Square significantly reduced shoplifting and abusive behaviour.

 

Just over five years ago, Paul opened his third convenience store in the newly developed Buckingham Park development in the UK. The new store, in the busy square with a school close by, was an immediate local success. However, unlike the two other stores owned by Paul, the level of shoplifting was much higher than he was accustomed to. What was interesting was the type of products that were missing, generally higher value with the top shoplifting choices being steak and wine. With these products being targeted it also meant that the managers of the store were better able to monitor the slippage as high-value items were much easier to track as they are accounted for individually. Paul started to investigate and gained a good working relationship with the local police and it became apparent that this was not impulse theft, it seemed to be more organised.

Around this time a chance encounter began his relationship with Facewatch and the use of the very latest facial recognition security camera technology to solve the problem… Paul explains:

 

‘We were puzzled by the extent of the shoplifting. It was very targeted theft of high-value items and it seemed that perhaps it was organised by someone stealing to order. Just by luck, my wife was talking to a friend she had met, who turned out to be the sales director of Facewatch, and in a conversation, she mentioned the problem. Within a few weeks we decided to become the first trial site for the new facial recognition system’

 

In mid-2018 the Facewatch team installed a new facial recognition security camera inside the main entrance to the Jubilee Square store. The system automatically scans the faces of customers entering the store against a list of known people who had been previously been caught on the existing CCTV cameras shoplifting or abusing the staff, however, this was just the start, Paul continues:

 

‘The technical ability of the Facewatch system is incredible but it became clear very quickly that the power of the system could only be used if the data (The watch list) in the system was good. We found that our existing CCTV cameras were pretty good at capturing shoplifters but the quality of some of the facial images meant that when they were transferred to the Facewatch system it was more difficult to get an immediate match. We discussed this challenge with the Facewatch team and very quickly a very powerful solution was found. The newly installed facial recognition camera was also used to capture CCTV footage of incoming customers and as it was being used in a dual mode for CCTV and facial recognition, we were lawfully allowed to look at these images for 30 days before destroying them. We now have a system that rarely gives us a false match as every image of a thief is almost a perfect headshot’

He continued,

‘Everyday use of the system is now a seamless part of the store manager’s job, the Facewatch smartphone is carried by the manager and when an alert is heard the person is confirmed on the screen and then visually identified. If they are seen stealing or behaving badly, they would be watched by staff. If found to be hiding stolen goods we will call the Police’.

The Buckingham Park store has plenty of signs displayed announcing that the shop is using facial recognition and Paul has confirmed that this has worked as a very effective deterrent and there have not been any customers, over the year’s trial, who have questioned or been concerned about its use.

Paul also mentioned how the system affected his staff,

‘Running a successful convenience store is really like running a happy family, we are a close-knit community both amongst the staff and our regular customers. Everyone is affected by anti-social behaviour in the store and the disruption caused by calling the Police and having to confront a known shoplifter. I am pleased to say that with Facewatch in place where we had a lot of grief a year ago, we have a much more relaxed and positive working environment which is good for the team and the customers. I have to acknowledge that a lot of this is down to introducing Facewatch.’

 

Paul summed up his feeling about Facewatch’s facial recognition security camera system with the following comment:

‘Since installing Facewatch we have seen a reduction in losses of over 25%. Using Facewatch technology is a significant enhancement from the existing CCTV solution. The Facewatch team have been great to work with and I would highly recommend their technology and the people that work at Facewatch.’

 

Nick Fisher, CEO of Facewatch

‘It was a perfect start for the trials of Facewatch to find Paul. Paul was keen to try out the system and prepared to work closely with us to ensure any issues were sorted quickly and effectively. His store managers were very knowledgeable, and this helped us greatly’.

 

Technology overview:

facial recognition security camera system

Facewatch technology

The hardware to run Facewatch is simple to deploy. It includes a standard HD camera and Intel NUC, a mini-PC that is only 4×4 inches in size and consumes very little power. Its performance enables it to play and record video at 4K Ultra HD clarity. If it discovers a match, an alert that includes the image of the individual entering the establishment, along with an accuracy reading, is sent to the retailer’s smartphone, warning it that a known subject of interest on the watchlist has entered the shop.

Data protection and GDPR

The solution meets General Data Protection Regulation (GDPR) compliance, protecting businesses from being held liable for violating privacy laws.

“Facewatch’s retail crime reduction system, using facial recognition, shows how this developing technology can be acceptable and secure for the public whilst reducing crime and unacceptable behaviour in the retail environment.”