IS&T | Library

Spectral Reflectance Estimation with Smoothness Constraint

Abstract

A multimodal optomechatronics system is presented for measuring and monitoring change in cultural heritage objects exposed to environmental condition fluctuations or conservation treatments. It combines structured light, 3D colour digital image correlation and multispectral imaging, delivering information about an object's 3D shape, displacements, strains and reflectivity. The high functionality and applicability of the system are presented with the example of historical parchment subjected to changes in relative humidity.

Digital Library: ARCHIVING

Published Online: June 2023

Regular Article

27 10

Spectral Reflectance Estimation
Smoothness Constraint
Multispectral Imaging

Shoji Tominaga, Shogo Nishi, Ryo Ohtera, Hideaki Sakai

DOI

10.2352/CIC.2022.30.1.26

Volume 30

Issue 1

Evaluating the Performance of Different Cameras for Spectral Reconstruction

Abstract

We consider the problem of estimating surface-spectral reflectance with a smoothness constraint from image data. The total variation of a spectral reflectance over the visible wavelength range is defined as the measure of smoothness. A penalty on roughness, equivalent to smoothness, is added to the performance index to estimate the spectral reflectance functions. The optimal estimates of the spectral reflectance functions are determined to minimize a total cost function consisting of the estimation error and the roughness of the spectral functions. An RGB camera and multiple LED light sources are used to construct the multispectral image acquisition system. We model the observed images using spectral sensitivities, illuminant spectrum, unknown spectral reflectance, a gain parameter, and an additive noise term. The estimation algorithms are developed for the two estimation methods of PCA and LMMSE. The optimal estimators are derived based on the least-square criterion for PCA and the mean squared error minimization criterion for LMMSE. The feasibility of the proposed method is shown in an experiment using three mobile phone cameras. It is confirmed that the optimal estimators improve the accuracy for both original PCA and LMMS estimators.

Digital Library: CIC

Published Online: November 2022

Regular Article

45 16

Spectral Reconstruction
Hyperspectral Imaging
Multispectral Imaging

Yi-Tun Lin, Graham D. Finlayson

DOI

10.2352/CIC.2022.30.1.37

Volume 30

Issue 1

Abstract

Spectral Reconstruction (SR) algorithms seek to map RGB images to their hyperspectral image counterparts. Statistical methods such as regression, sparse coding, and deep neural networks are used to determine the SR mapping. All these algorithms are optimized ‘blindly’ and the provenance of the RGBs is not considered. In this paper, we benchmark the performance of SR methods—in order of increasing complexity: regression, sparse coding, and deep neural network—when different RGB camera spectral sensitivity functions are used. In effect, we ask: “Are some cameras better able to recover spectra from RGBs than others?”. In our experiments, RGB images are generated by numerical integration for a fixed set of hyperspectral images using 9 different camera response functions (each from a different camera manufacturer) plus the CIE 1964 color matching functions. Then, we train SR methods on the respective RGB image sets. Our experiments show three important results. First, different cameras <strong>do</strong> support slightly better or worse spectral reconstruction but, secondly, that changing the spectral sensitivities alone does not change the ranking of different algorithms. Finally, we show that sometimes switching the used camera for SR can give a greater performance boost than switching to use a more complex SR method.

Digital Library: CIC

Published Online: November 2022

Investigating the Upper-Bound Performance of Sparse-Coding-Based Spectral Reconstruction from RGB Images

148 8

Spectral Reconstruction
Hyperspectral Imaging
Multispectral Imaging
Sparse Coding

Yi-Tun Lin, Graham D. Finlayson

Page , November 2021, © Society for Imaging Science and Technology 2021

DOI

10.2352/issn.2169-2629.2021.29.19

Volume 29

Issue 1

In Spectral Reconstruction (SR), we recover hyperspectral images from their RGB counterparts. Most of the recent approaches are based on Deep Neural Networks (DNN), where millions of parameters are trained mainly to extract and utilize the contextual features in large image patches as part of the SR process. On the other hand, the leading Sparse Coding method ‘A+’—which is among the strongest point-based baselines against the DNNs—seeks to divide the RGB space into neighborhoods, where locally a simple linear regression (comprised by roughly 102 parameters) suffices for SR. In this paper, we explore how the performance of Sparse Coding can be further advanced. We point out that in the original A+, the sparse dictionary used for neighborhood separations are optimized for the spectral data but used in the projected RGB space. In turn, we demonstrate that if the local linear mapping is trained for each spectral neighborhood instead of RGB neighborhood (and theoretically if we could recover each spectrum based on where it locates in the spectral space), the Sparse Coding algorithm can actually perform much better than the leading DNN method. In effect, our result defines one potential (and very appealing) upper-bound performance of point-based SR.

Digital Library: CIC

Published Online: November 2021

Spectral Imaging to Differentiate Contaminant Levels

36 5

Multispectral Imaging
Image Analysis
Food Safety

Min Zhao, Qiyue Liang, Susana Diaz-Amaya, Amanda J. Deering, Lia Stanciu, George T.-C. Chiu, Jan P. Allebach

Pages 342-1 - 342-8, January 2021, © Society for Imaging Science and Technology 2021

DOI

10.2352/ISSN.2470-1173.2021.16.COLOR-342

Volume 33

Issue 16

Mercury (Hg) and Arsenic (As) have been recognized as chemical threats to human health. Still, the detection of lower contamination levels using traditional image analysis remains challenging due to the small number of available data samples and the insufficient utilization of the spatial information contained in the sensor pad images. To overcome this challenge, we use the spectra data of the colorimetric response pads and propose two kinds of classification models for differentiating contaminant levels with high test accuracy. In the first model, we use the SMOTE method to solve the imbalanced data problem, then apply the sequential forward selection algorithm to select optimal wavelength features in combination with the k-NN classifier to discriminate five contaminant levels. The second technique comprises principal component analysis (PCA) used as a dimensionality reduction technique combined with the random forest (RF) classifier to classify five contaminant levels. Our proposed system is trained and evaluated on a limited dataset of 126 spectral responses of five contamination levels. Our algorithms can yield 77% and 87% average accuracy, respectively. We will present an overview of the base model, the pipelines and the comparison of our proposed two classification models, and the phone-based narrow-band spectral imaging system that can obtain the camera spectral response for accurate and precise heavy metals analyses with the aid of narrow bandpass filters in front of a cell phone’s camera lens.

Digital Library: EI

Published Online: January 2021

A Web-based Visualization Tool for Multispectral Images

30 4

Multispectral Imaging
Visualization
Computer Graphics
Cultural Heritage Imaging
Web-based

Snehal A. Padhye, David Messinger, James A. Ferwerda

DOI

10.2352/ISSN.2470-1173.2021.14.CVAA-014

Volume 33

Issue 14

Exploring the Facial Color Representative Regions Using the Humanae Images

Multispectral imaging has been a valuable technique for discovering hidden texts in manuscripts, learning the provenance of antique books, and generally studying cultural heritage objects. Standard software used in displaying and analyzing such multispectral images are often complex and requires installation and maintenance of custom packages and libraries. We present an easy-to-use web-based multispectral imaging visualization tool that enables simultaneous interaction with the information captured in different spectral bands.

Digital Library: EI

Published Online: January 2021

JIST-first

38 10

Multispectral Imaging
Visualization
Computer Graphics
Cultural Heritage Imaging
Web-based

Yuchun Yan, Hayan Choi, Hyeon-Jeong Suk

DOI

10.2352/J.ImagingSci.Technol.2020.64.6.060406

Volume 33

Issue 14

It is difficult to describe facial skin color through a solidcolor as it varies from region to region. In this article, the authors utilized image analysis to identify the facial color representative region. A total of 1052 female images from Humanae project were selected as a solid color was generated for each image as their representative skin colors by the photographer. Using the open CV-based libraries, such as EOS of Surrey Face Models and DeepFace, 3448 facial landmarks together with gender and race information were detected. For an illustrative and intuitive analysis, they then re-defined 27 visually important sub-regions to cluster the landmarks. The 27 sub-region colors for each image were finally derived and recorded in L^*, a^*, and b^*. By estimating the color difference among representative color and 27 sub-regions, we discovered that sub-regions of below lips (low Labial) and central cheeks (upper Buccal) were the most representative regions across four major ethnicity groups. In future study, the methodology is expected to be applied for more image sources. c 2020 Society for Imaging Science and Technology.

Digital Library: EI

Published Online: November 2020

Method for the optimal approximation of the spectral response of multicomponent image

40 3

Multispectral Imaging
Wiener Inverse
Spectral reconstruction
multispectral sensor
Neural Network
Real Time Application

J Matanga, P Gouton, E Bourillot, S Journaux, P Ele

DOI

10.2352/ISSN.2470-1173.2019.9.IMSE-371

Volume 31

Issue 9