Image Analysis and Processing - ICIAP 2017

Abstract

The arrangement of products in store shelves is carefully planned to maximize sales and keep customers happy. How-ever, verifying compliance of real shelves to the ideal lay-out is a costly task routinely performed by the store person-nel. In this paper, we propose a computer vision pipeline to recognize products on shelves and verify compliance to the planned layout. We deploy local invariant features to-gether with a novel formulation of the product recognition problem as a sub-graph isomorphism between the items ap-pearing in the given image and the ideal layout. This allows for auto-localizing the given image within the aisle or store and improving recognition dramatically.