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.
Restoring the correct or realistic color of a cultural heritage object is a crucial problem for imaging techniques. Digital images often have undesired color casts due to adverse effects caused by unstable illuminant conditions, vignetting, and color changes due to camera settings. In this work, we present an improved color correction method for color cast images that makes the color appear more realistic. It is based on a computational model of the human visual system that perceives objects by color constancy theory; it realizes illumination non-uniformity compensation and chromaticity correction for color cast images by taking into account the color stability of some pigments. This approach has been used to correct the color in Cave 465 of the Mogao Grottoes. The experimental results demonstrate that the proposed method is able to “adaptively correct” color cast images with widely varying lighting conditions and improve the consistency efficaciously. It can achieve improved consistency in the mean CIEDE2000 color difference compared with the images before correction. This colorimetric correction methodology is sufficiently accurate in color correction implementation for cast images of murals captured in the early years.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.