Skip to content

IBM's auditor inspects (and verifies) diamonds, pills and materials at the micron level

Nowadays, it is not enough to treat false news, we must also deal with fake drugs, fake luxury goods and fake Renaissance paintings. Sometimes all at once! The IBM Auditor is a gadget and platform designed (naturally) to instantly check that something is what it claims to be, by inspecting it at a microscopic level.

Essentially, you paste a little thing on your phone's camera, open the app, and put the sensor against what you're trying to check, whether it's a generic anti-depressant or a sample of ore. By combining microscopy, spectroscopy and a bit of artificial intelligence, the verifier compares what he sees to a known version of the object and tells you if they are identical.

The key element of this process is an "optical element" that lies in front of the camera (it can act of anything that takes a decent image), which equates to a hyper-purpose specialized macro. It allows the camera to detect features as small as one micron – for comparison, a human hair typically has a width of a few tens of microns.

At the micron level, there are patterns and optical features that are not visible to the naked eye, just like the wavelengths of the light that it reflects. The quality of a weave, the number of defects in a gem, the mixture of metals in an alloy … everything you or I would miss, but a machine learning system trained on such examples will detected instantly.

For example, a counterfeit pill, although orange and smooth and printed like a real one, if we just had to look at it, will probably appear totally different at the micro level: textures and structures with a very distinct pattern , or at least distinct from the real thing – not to mention a spectral signature that is probably very different. There is also no reason not to use it for expensive wines or oils, contaminated water, currency and many other items.

See also  The Dyson Cyclone V10 Wireless Vacuum Embodies the End of Corded Cleaning

IBM was eager to highlight the AI ​​element, which is formed on different models and differentiates them, although as far as I know, it's a fairly simple classification task. I am more impressed by the lens that they put together that can solve at the micron level with so little distortion and do not over exclude or distort the colors. It works even on multiple phones – you do not have to have this or that model.


The first application that IBM announces for its Verifier is part of the diamond trade, which is of course known for fetishizing stones and their uniqueness, and for establishing elaborate supply trains in order to Ensure that the product is carefully controlled. The auditor will be used as an aid for the classification of stones, not alone, but as a tool for human auditors; it's a partnership with the Gemological Institute of America, which will test the integration of the tool into its own workflow.

By imaging the stone from several angles, the individual identity of the diamond can be recorded and tracked, so that its provenance and its traces in the industry can be tracked over the years. Here, IBM imagines that the blockchain will be useful, which is possible but not quite.

It's going to take a little while before you can get one, but I hope this type of technology will become popular enough for you to check the quality or composition of something without visiting a lab. .