Optimized clustering method for spectral reflectance recovery

Frontiers in Psychology

article

Yifan Xiong¹  Guangyuan Wu¹  Xiaozhou Li²  Xin Wang¹ 

[1] Faculty of Light Industry, Qilu University of Technology, Shandong Academy of Sciences;State Key Laboratory of Bio-based Material and Green Papermaking, Qilu University of Technology, Shandong Academy of Sciences

关键词: Spectral recovery;    dynamic partitional clustering;    Color space;    camera responses;    spectral reflectance;   

DOI  :  10.3389/fpsyg.2022.1051286

学科分类：社会科学、人文和艺术（综合）

来源: Frontiers

【 摘 要 】

An optimized method based on dynamic partitional clustering was proposed for spectral reflectance recovery from camera response values. The proposed method produces dynamic clustering subspaces using a combination of dynamic and static clustering, which determines each testing sample as a priori clustering center to obtain the clustering subspace by competition. The Euclidean distance weighted and polynomial expansion models in the clustering subspace were adaptively applied to improve the spectral recovery accuracy. The experimental results demonstrate that the proposed method outperforms existing methods in spectral and colorimetric accuracy and presents the effectiveness and robustness of spectral recovery accuracy under different color spaces.

【 授权许可】

CC BY