Fresh fish isn’t really that fresh – even straight off the boat. The way they are caught and killed is not only inhumane but also harmful to the meat produced. There’s a more advanced option, but it’s time-consuming and manual – but Shinkei Systems has found a way to automate it even on a moving boat, and has spent $1.3 million to bring the machine to market.
It’s unpleasant to think about, but harvesting fish doesn’t give much thought to the comfort of the fish. How can fishing boats work on a scale? What generally happens is that the fish are thrown out of the net, roughly sorted and then thrown onto the ice to roll around and finally suffocate minutes or hours later. not good!
Not only is this cruel, but stress, wounds and bacteria in the blood and lactic acid in the muscles will cause the fish’s body to deteriorate rapidly.
Of course, anyone who catches fish individually knows to keep them in the water or kill them immediately to get the best flavor. Usually this involves hitting him on the head and then cutting off his head. It’s still not pretty, but it’s better than the alternative.
But there is a better way, a traditional Japanese method called ike-gym. Doing it this way is not only very humane, but it preserves the meat well, so it can be kept for days or weeks and it will taste good. The problem is the art form.
Ike-jim involves piercing the brain with a sharp spike to send the fish into the sky, then quickly decapitating it, followed by decapitation of the spinal cord. Horrible, yes, but all of these things prevent stress, pain, and the spread of bacteria and harmful substances in the body. But it must be done correctly and within two minutes after the fish is caught, so that it is not measured correctly.
That is, unless you automate it, which is what Shinkei Systems did. Led by co-founder Saif Khawaja, the team has developed a method to process IKE-Jimin fresh-caught fish at a rate of one every 10-15 seconds.
The machine, about the size of a large refrigerator, includes a hatch for incoming fish, an operational area and an outlet into an ice bath. A computer vision system identifies the species and shape of the fish it contains, separates the brain and other vital parts, and goes through the motions of the ike-gym, dispatching the fish quickly and safely.
“Robotics work with surgical-level precision – our vision for this is completely hands-free, no operator,” said Khawaja, who notes that it’s robust against the boats’ natural pitch and roll. But it’s not simply edge detection; We use machine learning in our backbone. Even in the same species, even with the same contour, the brain can be in a different place. Our technological advantage is adaptability to all fish.
Not all of this was done in some isolated Silicon Valley garage, either. “We have deployed our first versions in pilots. When I first started this project I was taking midnight greyhounds when they came out to the docks at 3am, because that was the only way they could talk to them. We’re working with fishermen in Maine, New Hampshire and Cape Cod, and we’ve partnered with major restaurant distributors in Manhattan.
Shinkei and his friends aren’t just going through all this for the sake of the fish. Kitchens pay a premium for IK-JIM processed fish because it tastes better and lasts longer. Schinke’s question was whether machine-processed fish could compete with hand-processed fish.
“Perhaps the most fun and the easiest thing, we gave our fish to a sous chef from one of the best Michelin-starred restaurants in the world,” says Kawaja. “We gave him three boxes of fish: one was depressed, one had his hands ready, and the third was us. It was obvious that he had been kidnapped, but he couldn’t tell the difference between the two.
Sushi chefs are more likely to know the technique, but Ike-jime is starting to gain traction outside of its current niche and Shinke is here to accelerate that. By making it as easy as installing a machine, it allows more fishing boats and distributors to participate, making more money and doing business right in Assam.
Schinke raised $1.3 million in a pre-seed round in January and is now seeking additional investment, making initial design tests and refinements. “What we’re doing with this increase is improving R&D and improving the throughput of the device,” which runs slower than experts, but has plenty of room for improvement. “We should be ready to go into production in the next few months. We’re in the sales process right now, getting a lot of big distributors and public companies. We just want to get the machine into people’s hands.”