Use case

Dataset for recognition systems, classification and monitoring of goods in stores

The dataset collected using crowdsourcing contains images of products of different categories on supermarket shelves. The goods in the photos are placed in an arbitrary position: with the cover facing the buyer and away from the buyer, sideways and at an angle. 1/3 of the photos have empty and half-empty shelves.

For all images, there is a marking with polygons of each visible product.

The detection of goods and classification by categories and types of placement was carried out in CVAT. The data is presented in the form of source photographs, masks with annotations, and attribute coordinates in an XML file.

“

Case description

Each image from the folder is accompanied by labelling in the .xml file specifying the coordinates of the polylines and general attributes

Attributes:

• is_flipped - inverted position of the product
• is_facing - excellent visibility of the product
• is_occluded - the product is hidden

Metadata:

Extra services for product facings:

Supply chain planning:
Labelling of store shelves according to the necessary criteria for monitoring the layout, purchase planning and advanced predictive analytics.

Warehouse operations:
Datasets for robot merchandisers.

Pricing and promotion:
OCR annotation for deciphering texts on price tags and labels for competitive analysis and cost management of products.

Customer intelligence:
Labelling data to determine the items that are in the greatest demand, and the products that customers most often return to the shelves, etc.

Demand forecasting:
Preparation of data for creating product recommendation systems for offline and online stores.

Didn't find the necessary information?

Leave a request to calculate the cost of a dataset for your business!