Target Brands, Inc.

Matthew Nokleby

Deepti Pachauri

Nicholas Scott Eggert

Ryan David Siskind

Corey Hadden

Edgar Cobos

Stephen Radachy

Rachel Alderman

Luisa Fernanda Polanía Cabrera

Mauricio Alejandro Flores Ríos

Yiran Li

Kenneth Zins

Methods and systems for automated detection of carton defects are disclosed. One method includes capturing one or more images of a carton via a camera system at a routing location within a warehouse of a retail supply chain, and applying a machine learning model to determine a likelihood of damage of the carton. The method can include, based on the likelihood of damage being above a particular threshold, identifying the carton as damaged. A carton assessment record can be stored in a carton damage tracking database, including the one or more images of the carton alongside the likelihood of damage and the routing location.

Automated detection of carton damage

Systems and methods for automating image annotations are provided, such that a large-scale annotated image collection may be efficiently generated for use in machine learning applications. In some aspects, a mobile device may capture image frames, identifying items appearing in the image frames and detect objects in three-dimensional space across those image frames. Cropped images may be created as associated with each item, which may then be correlated to the detected objects. A unique identifier may then be captured that is associated with the detected object, and labels are automatically applied to the cropped images based on data associated with that unique identifier. In some contexts, images of products carried by a retailer may be captured, and item data may be associated with such images based on that retailer's item taxonomy, for later classification of other/future products.

Large-scale automated image annotation system

Methods and systems for automated detection of carton damage are disclosed. One method includes capturing one or more images of a carton via a camera system at a routing location within a warehouse of a retail supply chain, and applying a machine learning model to determine a likelihood of damage of the carton. The method can include, based on the likelihood of damage being above a particular threshold, identifying the carton as damaged. A carton assessment record can be stored in a carton damage tracking database, including the one or more images of the carton alongside the likelihood of damage and the routing location.

Examples disclosed herein are relevant to systems, methods, and other technology for determining furniture compatibility. For example, graph neural networks (GNNs) that leverage relational information between furniture items in a set may be used as models to predict a compatibility score indicative of visual compatibility of furniture items across the set. In one implementation, the GNN-based model can extend the concept of a siamese network to multiple inputs and branches and use a generalized contrastive loss function. In another implementation, the GNN-based model learns both an edge function and the function that generates the compatibility score. The predicted compatibility score can be used for a variety of purposes, including furniture item recommendations.

Compatibility based furniture recommendations

Growing community of inventors

Minneapolis, MN, United States of America

Matthew Nokleby