Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning

iStock // Ekaterina Minaeva
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Your Smart TV Is Vulnerable to Hackers, According to the FBI

Ahmet Yarali / iStock via Getty Images
Ahmet Yarali / iStock via Getty Images

By this point, many of us have had the experience of mentioning a product or service out loud during a conversation, only to have an ad for that very thing pop up on a smart device mere moments later. And, although you may have gotten used to the idea of your gadgets keeping tabs on you, you might not realize that your new smart TV’s monitoring capabilities make it extra vulnerable to hackers.

KATV reports that the Portland, Oregon branch of the FBI released guidelines last week as part of its “Tech Tuesday” initiative to warn people about the risk of hackers gaining access to unsecured televisions through the routers. Because smart TVs likely have microphones and even cameras, successful hackers could do anything from petty mischief to serious stalking.

“At the low end of the risk spectrum, they can change channels, play with the volume, and show your kids inappropriate videos,” the FBI says. “In a worst-case scenario, they can turn on your bedroom TV’s camera and microphone and silently cyberstalk you.”

Before you head back to Best Buy, brandishing your receipt and begging for a refund, there are a number of safety precautions you can take to make yourself less of an easy target for cyberattacks.

The first step is knowing exactly what features your TV has, and understanding how to control them—the FBI recommends doing an internet search with the model number and the words microphone, camera, and privacy.

After that, you should delve right into those security settings. Disable the collection of personal information if you can, and learn how to limit microphone and camera access. If you don’t see an option to shut off the camera, black tape over it does the trick.

And, even if it’s not the most riveting reading material, it’s worth perusing the fine print on your device and streaming services to find out what data they collect, where they store it, and how they use it.

Check out all of the tips here, and then see what other everyday objects might be susceptible to hackers.

[h/t KATV]

Hotel in Japan Is Offering Rooms for $1 Per Night—If You Agree to Livestream Your Stay

DragonImages/iStock via Getty Images
DragonImages/iStock via Getty Images

Many people are happy to document their vacations online without getting paid to do it. Now, as The Washington Post reports, exhibitionists who can't resist low prices are now eligible to book a hotel room in Fukuoka, Japan for just $1 a night. In return, they must agree to livestream their experience.

Tetsuya Inoue, the manager of Asahi Ryokan in Fukuoka, got the idea for the marketing stunt after one of his guests broadcast his stay voluntarily. Inoue figured that if people are already comfortable sharing their private moments in the hotel with the world, he might as well use that to his advantage.

The "One Dollar Hotel" promotion is a way for Inoue to bring attention to the 30-year-old guesthouse, which is owned by his grandmother. For $1—a fee that covers lodging, taxes, and tips—customers have access to a room that normally costs $27 a night. As guests eat, sleep, and get ready for the day, a camera installed in the room livestreams their every move to the hotel's YouTube channel. The only place where they have privacy is in the bathroom. Signs in the room warn guests not to engage in any "lewd acts" and to keep passports and credit cards out of the camera's field of view.

In addition to generating publicity for Asahi Ryokan, Inoue hopes that his YouTube videos will eventually become popular enough to monetize. Five guests have agreed to the deal so far, and after launching in October, the One Dollar Hotel YouTube channel already has close to 15,000 subscribers.

[h/t The Washington Post]