EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High Dynamic Range Image Reconstruction from Saturated Images of Metallic Objects

Shoji Tominaga, Takahiko Horiuchi iD

Journal of Imaging · 15.04.2024 · 10 (4) · 92

DOI: 10.3390/jimaging10040092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 15.04.2024. Verfasst von Shoji Tominaga und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Grant-in-Aid for Scientific Research (C).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study considers a method for reconstructing a high dynamic range (HDR) original image from a single saturated low dynamic range (LDR) image of metallic objects. A deep neural network approach was adopted for the direct mapping of an 8-bit LDR image to HDR. An HDR image database was first constructed using a large number of various metallic objects with different shapes. Each captured HDR image was clipped to create a set of 8-bit LDR images. All pairs of HDR and LDR images were used to train and test the network. Subsequently, a convolutional neural network (CNN) was designed in the form of a deep U-Net-like architecture. The network consisted of an encoder, a decoder, and a skip connection to maintain high image resolution. The CNN algorithm was constructed using the learning functions in MATLAB. The entire network consisted of 32 layers and 85,900 learnable parameters. The performance of the proposed method was examined in experiments using a test image set. The proposed method was also compared with other methods and confirmed to be significantly superior in terms of reconstruction accuracy, histogram fitting, and psychological evaluation.

Schlagwörter

Stichwörter der Autor:innen

HDR image databaseLDR-to-HDR mappingdeep neural network approachgloss perceptionhigh dynamic range image reconstructionhuman psychological experimentsmaterial appearancemetallic objectsreconstruction of saturated glosssaturated low dynamic range images

Autor:innen und Institutionen

  • Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway.
  • Department of Business and Informatics, Nagano University, Ueda 386-0032, Japan.
  • Graduate School of Engineering, Chiba University, Chiba 263-8522, Japan.

ORCID-Profile: Takahiko Horiuchi

Förderung

  • Grant-in-Aid for Scientific Research (C)

Zitieren

APA

Tominaga, S., & Horiuchi, T. (2024). High Dynamic Range Image Reconstruction from Saturated Images of Metallic Objects. Journal of Imaging, 10(4), 92. https://doi.org/10.3390/jimaging10040092

Vancouver

Tominaga S, Horiuchi T. High Dynamic Range Image Reconstruction from Saturated Images of Metallic Objects. Journal of Imaging. 2024;10(4):92. doi:10.3390/jimaging10040092

BibTeX
@article{Tominaga2024,
  author = {Tominaga, Shoji and Horiuchi, Takahiko},
  title = {High Dynamic Range Image Reconstruction from Saturated Images of Metallic Objects},
  journal = {Journal of Imaging},
  year = {2024},
  volume = {10},
  number = {4},
  pages = {92},
  doi = {10.3390/jimaging10040092}
}
Kostenlos starten →