NTT DoCoMo has launched an artificial intelligence (AI) engine that analyzes shelf allocation in stores and warehouses using photos taken with smartphones and other common devices.
The image recognition engine employs DoCoMo’s AI technology and constitutes part of NTT Group’s corevo AI technology. Object-detection technology detects individual items in an image with over 98% accuracy and object-recognition technology identifies specific products with over 95% accuracy by matching them with images stored in a database.
Currently, shelf-analysis technology requires products to be placed in the front row and facing forward to ensure high-precision recognition. DoCoMo says its new engine can recognize products on shelves without special arrangement, even when they are packed tightly together. Virtually any product can be recognized immediately if it is registered in the database, meaning that the technology can be used for millions of product types and brands.
DoCoMo expects its new AI engine to be used widely in the distribution and retail industries for product-shelf management and sales analysis. In particular, companies could use the engine to check shelf allocation much faster than through manual methods.
DoCoMo also said that Cyberlinks is the first company to adopt the AI engine for an application called Tana Scan-AI. The application enables devices such as smartphones to be used to quickly analyze shelf allocation and generate the data required to create a planogram – a visual representation of a store’s products.
The new engine was created through DoCoMo’s Top Gun program, under which hybrid teams across the company’s R&D and corporate divisions are developing practical and innovative solutions to meet specific needs.