EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DarwinGSE: Towards better image retrieval systems for intellectual property datasets

João António iD, Jorge Valente, Carlos Mora, Artur Almeida, Sandra Jardim iD

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0304915 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von João António und 4 weiteren Autor:innen. Beteiligte Einrichtung: Techframe-Information Systems, SA, São Domingos de Rana, Portugal. Hauptthemen laut MEDLINE: Intellectual Property. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 118 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Programa Operacional Regional do Centro.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A trademark’s image is usually the first type of indirect contact between a consumer and a product or a service. Companies rely on graphical trademarks as a symbol of quality and instant recognition, seeking to protect them from copyright infringements. A popular defense mechanism is graphical searching, where an image is compared to a large database to find potential conflicts with similar trademarks. Despite not being a new subject, image retrieval state-of-the-art lacks reliable solutions in the Industrial Property (IP) sector, where datasets are practically unrestricted in content, with abstract images for which modeling human perception is a challenging task. Existing Content-based Image Retrieval (CBIR) systems still present several problems, particularly in terms of efficiency and reliability. In this paper, we propose a new CBIR system that overcomes these major limitations. It follows a modular methodology, composed of a set of individual components tasked with the retrieval, maintenance and gradual optimization of trademark image searching, working on large-scale, unlabeled datasets. Its generalization capacity is achieved using multiple feature descriptions, weighted separately, and combined to represent a single similarity score. Images are evaluated for general features, edge maps, and regions of interest, using a method based on Watershedding K-Means segments. We propose an image recovery process that relies on a new similarity measure between all feature descriptions. New trademark images are added every day to ensure up-to-date results. The proposed system showcases a timely retrieval speed, with 95% of searches having a 10 second presentation speed and a mean average precision of 93.7%, supporting its applicability to real-word IP protection scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Intellectual PropertyHumansInformation Storage and RetrievalDatabases, FactualAlgorithmsImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Techframe-Information Systems, SA, São Domingos de Rana, Portugal.
  • Smart Cities Research Center, Polytechnic Institute of Tomar, Tomar, Portugal.

ORCID-Profile: João António, Sandra Jardim

Förderung

  • Programa Operacional Regional do Centro

Zitieren

APA

António, J., Valente, J., Mora, C., Almeida, A., & Jardim, S. (2024). DarwinGSE: Towards better image retrieval systems for intellectual property datasets. PLOS ONE. https://doi.org/10.1371/journal.pone.0304915

Vancouver

António J, Valente J, Mora C, Almeida A, Jardim S. DarwinGSE: Towards better image retrieval systems for intellectual property datasets. PLOS ONE. 2024. doi:10.1371/journal.pone.0304915

BibTeX
@article{Antnio2024,
  author = {António, João and Valente, Jorge and Mora, Carlos and Almeida, Artur and Jardim, Sandra},
  title = {DarwinGSE: Towards better image retrieval systems for intellectual property datasets},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0304915}
}
Kostenlos starten →