Fine-Grained Visual Recognition of Retail Products

Fine-Grained Visual Recognition of Retail Products

Open set recognition at scale is an issue for computer-vision systems, especially in the retail industry in which scalable AI-related technology solutions at the physical store level have not been deployed to the best of our knowledge. In this context, more challenges arise, such as detection of products in crowded store shelves, fine-grained subtle differences of similar SKUs, and dynamically adapting data distributions due to appearance variations or new classes that have not been labeled before.

This topic is under ongoing research. For questions, please refer to Marco Filax.

Publications

2019

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

Data for Image Recognition Tasks: An Efficient Tool for Fine-Grained Annotations Inproceedings

Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods, 2019.

Abstract | Links | BibTeX

2018

Filax, Marco; Ortmeier, Frank

VIOL: Viewpoint Invariant Object Localizator - Viewpoint Invariant Planar Features in Man-Made Environments Inproceedings

Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), S. 581-588, 2018, ISBN: 978-989-758-290-5.

Abstract | Links | BibTeX

2017

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

QuadSIFT: Unwrapping Planar Quadrilaterals to Enhance Feature Matching Inproceedings

Proceedings of the 25rd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2017 - Short Papers Proceedings, 2017.

Abstract | Links | BibTeX

Fine-Grained Visual Recognition of Retail Products