Product recognition in store shelves as a sub-graph isomorphism problem
This addresses the costly task of manual shelf compliance verification for store personnel, but it is incremental as it builds on existing computer vision methods with a novel formulation.
The paper tackled the problem of verifying compliance of store shelf layouts by proposing a computer vision pipeline that formulates product recognition as a sub-graph isomorphism problem, resulting in dramatic improvement in recognition and auto-localization within aisles.
The arrangement of products in store shelves is carefully planned to maximize sales and keep customers happy. However, verifying compliance of real shelves to the ideal layout is a costly task routinely performed by the store personnel. 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 together with a novel formulation of the product recognition problem as a sub-graph isomorphism between the items appearing 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.