EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Deep Edge Detection through Normalized Hadamard-Product Fusion

Gang Hu iD, Conner Saeli

Journal of Imaging · 29.02.2024 · 10 (3) · 62

DOI: 10.3390/jimaging10030062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 29.02.2024. Verfasst von Gang Hu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Information Systems, SUNY Buffalo State University, Buffalo, NY 14222, USA. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep edge detection is challenging, especially with the existing methods, like HED (holistic edge detection). These methods combine multiple feature side outputs (SOs) to create the final edge map, but they neglect diverse edge importance within one output. This creates a problem: to include desired edges, unwanted noise must also be accepted. As a result, the output often has increased noise or thick edges, ignoring important boundaries. To address this, we propose a new approach called the normalized Hadamard-product (NHP) operation-based deep network for edge detection. By multiplying the side outputs from the backbone network, the Hadamard-product operation encourages agreement among features across different scales while suppressing disagreed weak signals. This method produces additional Mutually Agreed Salient Edge (MASE) maps to enrich the hierarchical level of side outputs without adding complexity. Our experiments demonstrate that the NHP operation significantly improves performance, e.g., an ODS score reaching 0.818 on BSDS500, outperforming human performance (0.803), achieving state-of-the-art results in deep edge detection.

Schlagwörter

Stichwörter der Autor:innen

Hadamard productdeep networkedge detectionfusionmutual agreementsalient

Autor:innen und Institutionen

  • Department of Computer Information Systems, SUNY Buffalo State University, Buffalo, NY 14222, USA.
  • Center for Computational Research, SUNY University at Buffalo, Buffalo, NY 14203, USA.

ORCID-Profile: Gang Hu

Zitieren

APA

Hu, G., & Saeli, C. (2024). Enhancing Deep Edge Detection through Normalized Hadamard-Product Fusion. Journal of Imaging, 10(3), 62. https://doi.org/10.3390/jimaging10030062

Vancouver

Hu G, Saeli C. Enhancing Deep Edge Detection through Normalized Hadamard-Product Fusion. Journal of Imaging. 2024;10(3):62. doi:10.3390/jimaging10030062

BibTeX
@article{Hu2024,
  author = {Hu, Gang and Saeli, Conner},
  title = {Enhancing Deep Edge Detection through Normalized Hadamard-Product Fusion},
  journal = {Journal of Imaging},
  year = {2024},
  volume = {10},
  number = {3},
  pages = {62},
  doi = {10.3390/jimaging10030062}
}
Kostenlos starten →