Close Ad

The Spoon

Daily news and analysis about the food tech revolution

cashierless technology

Noka’s Smart Shopping Baskets Lets Customers Walk Out Without Going Through the Check-Out Line

According to Omnico’s US Retail Report, 74 percent of consumers believe technology will make shopping easier and remove sources of annoyance, like long lines at the register. A start-up called Noka recently introduced its cashierless technology for grocery stores and supermarkets.

What sets Tbilisi Georgia-based Noka’s tech apart from simple self-checkout is its smart shopping baskets. When customers enter a store equipped with Noka’s technology, they grab a basket and touch a sensor button (not a fingerprint sensor). They are then let in the barrier separating the entrance and main store area.

Once in the store area, customers grab items and fill up their baskets. Noka’s baskets identify the shopper and track the items placed into the basket. All products are located behind fridge-like doors which cannot be opened unless a customer has their hand on the basket. Shelves within the store are equipped with weight sensors that recognize how many products are picked up from the shelf.

Introducing NOKA Technology: Shopping experience in the first cashierless store

If a customer decides to put an item back, it is automatically subtracted from the order. At checkout, they simply press the sensor button again and pay with a credit card or Apple pay. After payment is complete, the customer can exit out the two-way barrier.

According to David Topchishvili, the CEO of Noka, “Unlike Amazon Go, Trigo, AiFi and other competitors, NOKA technology doesn’t use recognition cameras, we don’t need large servers for computing, and it can be easily scalable.”

Although Noka does stand apart with its smart shopping baskets, there are still a lot of companies in this space. A company that has a similar concept to Noka, is Israel-based Shopic, which has created smart shopping carts. Amazon was one of the first to debut its cashierless tech in 2018, with its first Amazon Go. Other companies in the cashierless space include AiFi, Mashgin, Grabango, and Trigo.

Noka unveiled a prototype of its system in August 2020 and trialed it at an experimental store with 100 SKUs in November 2020. In September 2021, the company’s deployed its baskets for the first time in an actual store environment in its home country of Georgia. In this first real-world deployment, the company’s baskets can identify up to 1,000 product SKUs.

SKS 2020: Grabango Says its Computer Vision Avoids Biases Because it Doesn’t Use Facial Recognition

Grabango CEO Will Glaser said this week that because his company’s technology doesn’t use facial recognition, it can avoid some of the same types of racial biases found in other computer vision and machine learning algorithms. Glaser’s comments came during my fireside chat with him at our Smart Kitchen Summit this week.

Grabango makes cashierless (or as Grabango calls it, “lineless”) checkout technology for grocery retail. Grabango installs hundreds of cameras in the ceiling of a store, and through a combination of computer vision and AI, keeps track of what people put in their basket (or pocket). When shoppers go to check out, they choose a cashier or use an accompanying mobile app that automatically charges for the items kept.

This type of computer vision-based system is also used by other cashierless checkout companies such as Zippin, Standard Cognition and Amazon, and could become more widespread as demand for contactless retail experiences grows.

But the problem with some computer vision + AI systems is that their algorithms can contain the human biases of their creators. As TechCrunch wrote earlier this year, “MIT researchers reported in January 2019 that facial recognition software is less accurate in identifying humans with darker pigmentation.” In a busy retail environment where a lot of people are grabbing a lot of different items all throughout the day, it’s not hard to see how this type of bias could adversely impact people of color.

Glaser recognized some of the problems that can arise when algorithms are only developed or trained on white men in a lab. He made a point of saying that Grabango’s technology does not use facial recognition, and that it has a 99.6 percent revenue accuracy rate. Grabango’s system does follow a person around store, but doesn’t personally identify them (it can, however, stay with a person even after they have put on or taken off a jacket).

Grabango’s system is also being used in real world conditions, so it continues to train its algorithms in a diverse setting. Last month, Grabango announced that it’s integration with Giant Eagle’s GetGo Market in the Pittsburgh area went live. So now we’ll be able to see in a more open environment if Glaser’s claims hold true.

Shopic Raises $7.6 Million Series A for its Cashierless Checkout Tech

Shopic, and Israel-based startup that creates cashierless checkout solutions for medium to large grocery stores, announced today that it has raised a $7.6 million Series A round of funding. The round was led by IBI Tech Fund, with participation from existing investor Entrée Capital, and brings the company’s total funding so far to $11 million.

Cashierless checkout systems use computer vision, shelf sensors and artificial intelligence to allow shoppers to walk in to a store, grab what they want and leave, getting charged automatically as they exit.

We weren’t familiar with Shopic before the company emailed us their announcement this morning. Based on Shopic’s website, it appears that unlike other cashierless checkout startups, Shopic’s system does not rely on retrofitting a store with banks of computer vision cameras to monitor what shoppers purchase. Instead, it looks like Shopic uses a shopper’s mobile phone, which they use to scan items as they shop, and there is a component that monitors the shopping cart itself to ensure that there is no shoplifting.

Shopic also allows stores to communicate back to the customer as they shop. So, based on what someone is buying, the store could offer enhanced product information or push customized sales and promotions in real time. Shopic also says its system can also help stores optimize shelf stocking and in-store behavior.

With its fresh round of capital, Shopic says that it will expand deployments of is platform to existing and new customers across Europe and North America, though it will be facing plenty of competition.

Amazon is big pioneer of cashierless checkout with its Go and Go Grocery stores. A host of startups also offer solutions to supermarkets around the world. Trigo, Grabango and Zippin all use Amazon-like systems of cameras and computer vision to keep track of what people are buying. But Shopic seems to be more of a blend between the mobile phone aspect of Swiftly and the cart monitoring of Caper.

Shopic’s fundraise has also come at a unique time. The COVID-19 global pandemic is re-shaping the grocery store experience as retailers attempt to reduce human-to-human contact. As such, preventative measures like facemasks are being worn by store employees and plexiglass shields are going up in front of cashiers.

But at some point, for the people who aren’t too scared to go into the grocery stores themselves, a contactless cashierless checkout might be the best option. You don’t have to interact with a cashier or touch a credit card terminal that potentially hundreds of other people have touched that day.

For sure, there are still questions around equity and jobs that go along with widescale adoption of cashierless checkout. But as the virus continues its rampage and even resurges in some areas, grocery retailers could accelerate more contactless options like cashierless checkout to keep shoppers and workers safe.

An earlier version of this story said Shopic had raised a total of $8.45 million, based on data in Crunchbase. Shopic got in touch with us and provided the accurate dollar figure.

Israel’s Shufersal to Implement Trigo Vision’s Cashierless Tech Across all its Stores

Trigo Vision announced today that its cashierless checkout technology, which delivers Amazon Go-like experiences at retail, will be installed in every location of Shufersal, Israel’s largest supermarket chain.

Technically, the two companies have signed an agreement to adopt Trigo Vision‘s technology, but the two still need to go through a pilot in one store first over the next year, and then roll out to the rest of the chain’s 272 locations.

Trigo Vision says that one of benefits of its technology over Amazon Go is that Trigo Vision can be retrofitted into any retail store of any size. Amazon Go stores are built from the ground up to house Amazon’s high-tech cameras and sensors and are typically smaller, hovering around the 2,000 square foot mark. Trigo Vision’s system uses basic off-the-shelf connected cameras, computer vision and machine learning to be able to identify products people put in their cart in a way, the company says, that can accommodate any lighting condition or store set up.

Being able to accurately identify more than 2,500 SKUs in a store has been a challenge, Trigo Vision CEO, Michael Gabay and COO, Jenya Beilin told me in a phone interview. Part of the issue with using computer vision for product identification is that the algorithms must be able to understand subtle shifts in branding, like for a special promotion or a seasonal flavor. But Trigo Vision claims that its technology has automated this process, and now it will go into broader real world use courtesy of the Shufersal partnership.

The competition to bring cashierless checkout tech to the grocery masses is fierce. Amazon is rolling out its Go stores at a fast pace across the country. Sam’s Club just debuted its first cashierless retail store. And Microsoft has long-been rumored to be working on cashierless tech with Walmart: the two giants recently expanded on an existing cloud partnership, which includes working on the internet of things and IT modernization. It makes sense that including a cahsierless retail component could be a part of that relationship, especially when so much data around how people shop and what they purchase can be mined from such a store.

Based in Tel Aviv, Trigo Vision raised a $7 million seed round earlier this year. The company says it’s expanding quickly and will have 20 – 25 people on their team by the end of the year. In addition to Shufersal, Trigo Vision has one other pilot happening right now with an undisclosed European grocer.