EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multibranch Wavelet-Based Network for Image Demoiréing

Chia-Hung Yeh iD, Chen Lo, Cheng-Han He

Sensors · 26.04.2024 · 24 (9) · 2762

DOI: 10.3390/s24092762 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.04.2024. Verfasst von Chia-Hung Yeh und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, National Taiwan Normal University, Taipei 10610, Taiwan. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Ministry of Science and Technology, Taiwan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Moiré patterns caused by aliasing between the camera’s sensor and the monitor can severely degrade image quality. Image demoiréing is a multi-task image restoration method that includes texture and color restoration. This paper proposes a new multibranch wavelet-based image demoiréing network (MBWDN) for moiré pattern removal. Moiré images are separated into sub-band images using wavelet decomposition, and demoiréing can be achieved using the different learning strategies of two networks: moiré removal network (MRN) and detail-enhanced moiré removal network (DMRN). MRN removes moiré patterns from low-frequency images while preserving the structure of smooth areas. DMRN simultaneously removes high-frequency moiré patterns and enhances fine details in images. Wavelet decomposition is used to replace traditional upsampling, and max pooling effectively increases the receptive field of the network without losing the spatial information. Through decomposing the moiré image into different levels using wavelet transform, the feature learning results of each branch can be fully preserved and fed into the next branch; therefore, possible distortions in the recovered image are avoided. Thanks to the separation of high- and low-frequency images during feature training, the proposed two networks achieve impressive moiré removal effects. Based on extensive experiments conducted using public datasets, the proposed method shows good demoiréing validity both quantitatively and qualitatively when compared with the state-of-the-art approaches.

Schlagwörter

Stichwörter der Autor:innen

deep learningimage restorationmoiré patternwavelet transform

Autor:innen und Institutionen

  • Department of Electrical Engineering, National Taiwan Normal University, Taipei 10610, Taiwan.
  • Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung 80424, Taiwan.

ORCID-Profile: Chia-Hung Yeh

Förderung

  • National Science and Technology Council
  • Ministry of Science and Technology, Taiwan

Zitieren

APA

Yeh, C. H., Lo, C., & He, C. H. (2024). Multibranch Wavelet-Based Network for Image Demoiréing. Sensors, 24(9), 2762. https://doi.org/10.3390/s24092762

Vancouver

Yeh CH, Lo C, He CH. Multibranch Wavelet-Based Network for Image Demoiréing. Sensors. 2024;24(9):2762. doi:10.3390/s24092762

BibTeX
@article{Yeh2024,
  author = {Yeh, Chia-Hung and Lo, Chen and He, Cheng-Han},
  title = {Multibranch Wavelet-Based Network for Image Demoiréing},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {9},
  pages = {2762},
  doi = {10.3390/s24092762}
}
Kostenlos starten →