An experienced wine connoisseur can probably tell at a glance if that $1,000 bottle is the genuine article, but most of us cannot. A properly trained machine learning algorithm might be able to help with that. IBM has announced the creation of an artificial intelligence program that can look at items and tell you whether or not they are counterfeits. And of course, it’s got blockchain technology built in. Doesn’t everything these days?
Counterfeiting costs the global economy more than $1.2 trillion annually, as consumers pay inflated prices for fake items and businesses lose sales to those same fakes. IBM says its Crypto Anchor Verifier can help authenticate everything from diamonds to food, and the technology can work with a smartphone camera. It is partnering first with the Gemological Institute of America (GIA) to evaluate and grade diamonds using the Crypto Anchor Verifier.
According to IBM, every object has distinctive optical patterns, and AI can be trained to pick up on those patterns to decide whether something is authentic. It’s the sort of thing a well-trained human could do, but it’s harder to have a human expert on call than to just point your phone at something.
IBM started from the perspective of spectrophotometers, which can measure optical properties. However, these are bulky, expensive, and difficult to operate. It crafted an AI that can determine optical properties from a camera image to estimate whether it’s “real.” Of course, it needed all that higher level data to train the neural network to recognize objects based on their color, motion, viscosity, hue saturation, and so on.
This system plugs into a blockchain system, which you’ve probably heard about in reference to cryptocurrency. However, a blockchain is simply a distributed ledger and verified authenticity. In this case, IBM uses a blockchain to record the optical properties of an original item and track it all the way through the supply chain. The blockchain, therefore, confirms the item in question is the real deal and not a fake.
IBM says the Crypto Anchor Verifier can be used to verify a myriad of items including paper currency and medicines. It could also analyze water quality or detect contamination with bacteria like E. coli. Although, your smartphone camera doesn’t quite have the hardware for that. IBM is a little vague on which applications will work with a phone camera, but it seems confident the GIA partnership will result in a scanner anyone can use to verify their precious gems.
IBM’s Power9 Could Dent x86 Server Market With Emphasis On GPU Compute
Intel's x86 architecture dominates the server space, but don't count Power9 out altogether. IBM's CPU family is picking up design wins from companies working in AI and data centers.
IBM’s Project Debater to Set Stage for New Kind of Civil Society
Could this be how the Anthropocene age ends, not with a bang, but with a corporate AI composing fragmented arguments in favor of telemedicine?