Original image

Salsa Time!

Original image

In August, it's hard to find time to sit down and research some fascinating subject for you because I'm knee deep in tomatoes. Everyday I head to the garden with a five-gallon bucket and fill it up. Sometimes twice a day. I also grow peppers, so that means it's salsa time! Cue the music!

The original recipe I got from the county extension service says to use:

2 pounds chile peppers
5 pounds tomatoes
1 pound onions
1 cup vinegar
3 teaspoons salt
1/2 teaspoon pepper

Twelve years later, that's not at all how I do it. For one thing, I don't have a scale. Also, I figure any recipe that yields "six to eight pints" is a waste of time when I have bushels of tomatoes to process. Watch me make salsa, after the jump.


Preparing the peppers is the most dangerous part of the process. First, roast them to loosen the skins. I use enough peppers to fill a large cookie sheet, a very old one kept just for this purpose. If you burn a jalapeno, you won't want to use that cookie sheet for anything else. Cut a slit in each pepper to prevent it from exploding (not a pretty sight).


Bake at a high temperature until the skins are seriously blistered. You might want to open the windows during this process. Then put on the gloves. Do not omit the gloves. Roasted peppers are juicy, and should be treated like toxic waste. A male friend once cut up some of my peppers of a much milder variety. Afterward, he washed his hands and then used the bathroom in the style men do. He was in agony for days.


Cut the stem end off each pepper and open along the slit. The skin should peel off easily (if you roasted them long enough).


Scrape out the seeds and inner membranes. Do not scratch your nose. After you've cleaned each pepper, cut what's left into small bits. Refrigerate until use. Wash all utensils and dishes. Wash your gloves well before you take them off if you are going to use them again. Then wash your hands and use lotion. I'm serious.


To peel tomatoes, dip them in boiling water for 30-60 seconds to heat the skin, then put them in cold water to stop the process. The skin should then slip off easily.


I normally peel enough tomatoes to fill my turkey roasting pan. It takes me about a second to peel a tomato, but it takes forever to peel enough tomatoes... and the entire time, the theme song from Attack of the Killer Tomatoes runs through my head.


Then I chop and drain excess water from the tomatoes, sometimes overnight, which leaves two pots of pure tomato meat. Chop 3 or 4 big onions, and a bunch of cilantro.  I use cilantro in one batch, then garlic (also home grown) in the next batch. Using both is just flavor overkill. I code the finished product so I'll know which kind I'm opening. Combine all ingredients, dividing them as best you can between two pots. I use a cup of vinegar, a palmful of salt, and a spoon or so of ground pepper for each pot. Heat and simmer for five minutes.


At that point, the salsa is done, and the kitchen is covered in tomato juice. During the cooking process, I heat as much water as I can to can the salsa in the canner. I fill the jars halfway from one pot, and the rest from the other, so it doesn't matter if the proportions were a little different. Always use a recommended safe canning method.


My grandma, who had a large family, used to can vegetables in half-gallon jars in a #2 washtub over a fire outside. It was the only way to do massive home canning before air conditioning. And birth control.

432Finished Salsa.jpg

The finished product: 16 pints of weapons grade salsa! Three or four more batches like this, and I'll have a year's supply plus Christmas gifts for everyone. There was also a half-cup or so left for sampling. The kids declared it good. But what's this? While I made salsa, somehow the back room became filled with tomatoes again! When I get all the dishes washed, I'll start on tomato sauce. This will go on for about six weeks.

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