Original image
Latetia Barbier

Joanna Ebenstein and Her Morbid Anatomy Museum

Original image
Latetia Barbier

Artist and collector Joanna Ebenstein transformed her lifelong fascination with death into her very own Morbid Anatomy Museum, a 4,200-square-foot Brooklyn warehouse showcasing ghoulish curiosities ranging from a stuffed two-headed duckling and a pickled possum to postmortem photography. We asked her how like-minded enthusiasts could make their own lemonade out of life’s most unusual lemons.

All kids are interested in dead things, but there’s a moment when you’re not supposed to be anymore—especially if you’re a girl. I never had that moment. I always wanted my own natural history museum. As a little kid, my dad would put sea urchins in formaldehyde for me. I loved animals. I’d nurse baby birds back to health. But when they died, I didn’t see any conflict in preserving them.

In 2006, I was a freelancer doing graphic design, and I was reading this amazing book called Stuffed Animals and Pickled Heads, by Stephen Asma. I was at this job thinking, “If I could do anything, what would I do?” Well, I’d go to some of these amazing medical museums and I’d start taking photographs. Then I thought, “I can do that!” So I went to England and France and began collecting photographs. Later that year, one of my clients sent me to a conference where I met a medical museum curator. She said, “We should do a show of your work!” I got a small fellowship as part of that, around $1,000, and I thought, “You know what? I really want to make this show so much better.” So I went to Europe for a month to do more research. When I got back, I had tens of thousands of photographs.

I had so much stuff that I didn’t even know how to sort it. I started this blog called Morbid Anatomy. It never occurred to me, not once, that anybody else would be interested, but within a few days it had a following. I moved my collection into a cheap studio space at Proteus Gowanus Gallery, an arts incubator. I’m lucky I rented it, because they supported whatever I wanted to do. When I told them I was going to move all my Morbid Anatomy stuff in, they said, “Why don’t you make it open to the public?” So we began a lecture series, and I started getting invited to professional medical museum conferences.

I know this is supposed to be a success story about me, but it’s not. The reason I’m successful is that I work with great people and I’m good at seizing opportunities. I could not have done our book, Morbid Anatomy Anthology, without author Colin Dickey. He helped us raise $46,338 when we intended to raise $8,000.

As for the museum? In 2009, I gave a little talk. No one cared except for two people, Tonya and Tracy Hurley, identical twins who were hanging on every word. That’s how it started. Tracy was just one of those people who get things done. She put in a bunch of money; they brought a lot of stuff to donate. We did the Kickstarter and raised $76,013. The public perception of what we’re doing is so successful, but financially we’re still rocky.

I haven’t actively done any research for a little over a year now. My day-to-day work involves designing membership cards, writing weekly mailers, looking over event listings before they go live, corresponding with contributors to the anthology, working on our next exhibition—which is magic—trying to plan the publication to go with that, and working with our development director. We’re a skeleton staff.

At the opening of the museum, I took in the toast, looking around at all the people there, all of our community members who made this possible, and I realized that was what this is about. It’s these really wonderful, quirky people who don’t necessarily have an institution that serves their needs. The Metropolitan Museum is amazing: It produces an experience for the masses. But there are also people whose interests are very niche. They may feel like outcasts. They need a place, too.

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