Amazon is putting the “eye” in AI to help it detect damaged products so they won’t be shipped to customers. Scientists at Amazon Fulfillment Technologies in Germany are developing the technology, and the company hopes to deploy the damage-detection software at a dozen operations in North America and Europe before the holiday season.
“Like other sophisticated AI tools, the damage-detecting technology relies on software and lots of data. But damaged products are very rare, which makes the data needed to train the AI scarce,” Amazon said in a press release on Friday touting the initiative.
But last year, they cracked the code, discovering that they could supply a machine learning model with reference images in order to “teach it” how to compare the product it’s “looking at” to an image of what the product should look like.
Amazon uses computer vision to scan every item that passes through one of its German warehouses where it is testing the technology. “Next,” it explained, “a machine learning model analyzes the scans to discover hidden patterns and continuously improve the system’s ability to detect damage. This approach to machine learning and computer vision gives AI the capability to make the types of subjective decisions about damage that humans make all the time.”
Amazon said it would install the system in more locations and planned to expand the system’s capabilities.
