Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization
Sensors · 06.01.2023 · 23 (2) · 689
DOI: 10.3390/s23020689 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 06.01.2023. Verfasst von Pengpeng Yao und 2 weiteren Autor:innen. Beteiligte Einrichtung: Zhuhai Fudan Innovation Institute, Zhuhai 519000, China. Hauptthemen laut MEDLINE: Algorithms, Diagnostic Imaging. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
Spectral reflectance reconstruction for multispectral images (such as Weiner estimation) may perform sub-optimally when the object being measured has a texture that is not in the training set. The accuracy of the reconstruction is significantly lower without training samples. We propose an improved reflectance reconstruction method based on L1-norm penalization to solve this issue. Using L1-norm, our method can provide the transformation matrix with the favorable sparse property, which can help to achieve better results when measuring the unseen samples. We verify the proposed method by reconstructing spectral reflection for four types of materials (cotton, paper, polyester, and nylon) captured by a multispectral imaging system. Each of the materials has its texture and there are 204 samples in each of the materials/textures in the experiments. The experimental results show that when the texture is not included in the training dataset, L1-norm can achieve better results compared with existing methods using colorimetric measure (i.e., color difference) and shows consistent accuracy across four kinds of materials.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Zhuhai Fudan Innovation Institute, Zhuhai 519000, China.
- School of Fashion and Textile, The Hong Kong Polytechnic University, Hong Kong, China.
ORCID-Profile: Pengpeng Yao, Hochung Wu, John H Xin
Förderung
- National Natural Science Foundation of China (NSFC)
Zitieren
APA
Yao, P., Wu, H., & Xin, J. H. (2023). Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization. Sensors, 23(2), 689. https://doi.org/10.3390/s23020689
Vancouver
Yao P, Wu H, Xin JH. Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization. Sensors. 2023;23(2):689. doi:10.3390/s23020689
BibTeX
@article{Yao2023,
author = {Yao, Pengpeng and Wu, Hochung and Xin, John H},
title = {Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization},
journal = {Sensors},
year = {2023},
volume = {23},
number = {2},
pages = {689},
doi = {10.3390/s23020689}
}
EUVIMED