Open AccessOptimized spectral reconstruction based on adaptive training set selection
Author(s) -
Zhen Liu,
Honggang Chen,
Gui-Ai Gao,
Chan Li
Publication year - 2017
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.25.012435
Subject(s) - principal component analysis , computer science , subspace topology , artificial intelligence , pattern recognition (psychology) , artificial neural network , set (abstract data type) , noise (video) , selection (genetic algorithm) , training set , image (mathematics) , programming language
This paper proposes an improved reflectance reconstruction method by adaptively selecting training samples. Modified Principal Component Analysis estimation was proposed by orthogonal regression considering the system noise; deriving the optimum number of training samples by BP-Adaboost neural network; and grouping the representative samples together by hierarchical cluster analysis from a large database of samples. Finally, the training samples were selected by colorimetric subspace tracking. Experimental results indicated that the proposed method significantly outperforms the traditional methods in terms of both spectral and colorimetric accuracy, and our reflectance modeling is a reasonable and convenient tool to generate adaptive training sets.