Original image

The Art of Repairing and Digitizing a 400-year-old 3D Book

Original image

From the BODY WORLDS exhibition to Brain Surgery Live, it’s clear that modern humans are pretty curious about what goes on beneath our skin. But this is hardly a new phenomenon: More than 400 years ago, an intricate lift-the-flap anatomy book called Catoptrum Microcosmicum was a smash hit in Europe.

“Back then, pictures of the body were a lot less frequent, and there wasn’t anything like x-rays,” Steve Novak, head of Archives & Special Collections at Columbia University, tells mental_floss. “This satisfied a very basic curiosity about how the body is formed. And then there’s that pregnant woman in the middle of the first page. In the 17th century, as today, sex sells … and in the 17th century, I think that qualified as sex.”

The book was so popular that it was reprinted again and again, and some copies are still around today. One of those copies lives in the collection of Columbia’s Health Sciences Library, where staff members have recently restored and digitized the fragile book. 

The book, a 1661 edition, came to the library in pretty rough shape. Its parchment cover had stretched, which caused the book to warp. At some point in the last few centuries, someone had spilled a dark liquid onto the pages, rendering some of the text unreadable.

A conservator carefully removed the cover and took the book apart. He then crafted a new cover out of paper and leather—materials common in bookmaking in the 17th century—and hand-stitched the book back together. 

Next came the stain removal, which was accomplished using a device called a suction table. The conservator washed the stained pages with water, then sucked out the moisture before it could spread. 

The paper flaps themselves were quite jumbled, and some were torn. The conservator delicately disentangled them, then applied a thin tissue backing to make them just a little sturdier.

Once the book was clean and sturdy, it went to the library’s reprography department, where expert photographers painstakingly captured every inch of every page. They used tiny brushes and panes of glass to separate the flaps, each of which took quite a long time to photograph. 

“It’s not a matter of just putting it underneath the camera and flipping pages,” digital imaging manager Dave Ortiz explains. “Just to do the three flapped pages took us upward of eight or nine days.” 

Once the photo shoots had ended, the imaging staff compiled a master version of the book, which is now available to the public online. Alexis Hagadorn, head of the library's conservation program, says she's thrilled with the outcome: “It’s really exciting. Because of the conservation treatment and the care with the high-resolution imaging, you can actually see a lot more online than you can working directly from the book. It’s a really perfect example of how conservation and reprography and special collections departments all work together. We have this new technology to bring to bear on much older things, and we’re finding new ways to make them accessible to people who want to see them.”

Steve Novak agrees. The book is a treasure, he says—not only as an object, but also as a window into history. “It’s a wonderful example of popular science writing,” he says, made all the more impressive because it came “… from a time when science was really just getting started.”

To see the book online or download it for your e-reader, visit

Banner image via YouTube.

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
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!

Original image
Name the Author Based on the Character
May 23, 2017
Original image