Volltext-Downloads (blau) und Frontdoor-Views (grau)

Fine-Grained Product Classification on Leaflet Advertisements

  • In this paper, we describe a first publicly available fine-grained product recognition dataset based on leaflet images. Using advertisement leaflets, collected over several years from different European retailers, we provide a total of 41.6k manually annotated product images in 832 classes. Further, we investigate three different approaches for this fine-grained product classification task,In this paper, we describe a first publicly available fine-grained product recognition dataset based on leaflet images. Using advertisement leaflets, collected over several years from different European retailers, we provide a total of 41.6k manually annotated product images in 832 classes. Further, we investigate three different approaches for this fine-grained product classification task, Classification by Image, Classification by Text, as well as Classification by Image and Text. The last both approaches use the text extracted directly from the leaflet product images. We show, that the combination of image and text as input improves the classification of visual difficult to distinguish products. The final model leads to an accuracy of 96.4% with a Top-3 score of 99.2%. https://github.com/ladwigd/Leaflet-Product-Classificationshow moreshow less

Export metadata

Statistics

frontdoor_oas
Metadaten
Document Type:Conference Proceeding
Conference Type:Konferenzartikel
Zitierlink: https://opus.hs-offenburg.de/10147
Bibliografische Angaben
Title (English):Fine-Grained Product Classification on Leaflet Advertisements
Conference:The Upper Rhine Artificial Intelligence Symposium (5. : 16-17 November 2023 : Mulhouse, France)
Author:Daniel LadwigStaff Member, Bianca LammStaff MemberORCiD, Janis KeuperStaff MemberORCiDGND
Year of Publication:2024
Creating Corporation:ENSISA-IRIMAS
First Page:144
Last Page:151
Parent Title (English):UR-AI2023 : The Upper-Rhine Artificial Intelligence Symposium : Artificial Intelligence for Time Series, Robotics and Beyond
Editor:Jean-Philippe Lauffenburger, Jonathan Weber
URL:https://urai2023.sciencesconf.org/data/pages/book_urai2023_en_2024.pdf
Language:English
Inhaltliche Informationen
Institutes:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Forschung / IMLA - Institute for Machine Learning and Analytics
Collections of the Offenburg University:Bibliografie
Tag:fine-grained; image classification; leaflets; products; retail; text extraction
Formale Angaben
Relevance for "Jahresbericht über Forschungsleistungen":Konferenzbeitrag: h5-Index < 30
Open Access: Open Access 
 Bronze 
Licence (German):License LogoUrheberrechtlich geschützt