Amazon cameras can recognize products using computer vision

Using photos of products in Amazon warehouses and training a computer model, the e-commerce giant has developed a camera system that can track products as they pass one by one on conveyor belts to make sure they match the images. Ultimately, Amazon's AI and robotics experts want to combine the technology with robots that identify objects by picking them up and flipping them over.

"Solving this problem so that robots can pick up items and process them without having to search and scan a barcode is fundamental," Nontas Antonakos, manager of applied sciences at Amazon's computer vision group, was quoted as saying by CNet.

This technology will make it possible to deliver parcels to customers faster and more accurately.

The system, called multimodal identification, is not yet going to completely replace barcodes. It is currently being used at facilities in Barcelona (Spain) and Hamburg (Germany), according to Amazon. However, the company says this is already speeding up the time it takes to process packages there. The technology will be distributed to Amazon businesses.

Earlier, the owner of the Stockmann network completed the acquisition of Lamoda's business in Russia.