A review of hyperspectral imaging for nanoscale materials research

Dong, Xingchen; Jakobi, Martin; Wang, Shengjia; Köhler, Michael H.; Zhang, Xiaoxing; Koch, Alexander W.

doi:10.1080/05704928.2018.1463235

Cited by 51 publications

(36 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperspectral imaging, a technique integrating both machine vision and near-infrared spectroscopy, can acquire spectral and spatial information simultaneously. This advantage of hyperspectral imaging enables its wide application in various fields [10,11,12,13].…”

Section: Introductionmentioning

confidence: 99%

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

et al. 2019

View full text Add to dashboard Cite

Cotton seed purity is a critical factor influencing the cotton yield. In this study, near-infrared hyperspectral imaging was used to identify seven varieties of cotton seeds. Score images formed by pixel-wise principal component analysis (PCA) showed that there were differences among different varieties of cotton seeds. Effective wavelengths were selected according to PCA loadings. A self-design convolution neural network (CNN) and a Residual Network (ResNet) were used to establish classification models. Partial least squares discriminant analysis (PLS-DA), logistic regression (LR) and support vector machine (SVM) were used as direct classifiers based on full spectra and effective wavelengths for comparison. Furthermore, PLS-DA, LR and SVM models were used for cotton seeds classification based on deep features extracted by self-design CNN and ResNet models. LR and PLS-DA models using deep features as input performed slightly better than those using full spectra and effective wavelengths directly. Self-design CNN based models performed slightly better than ResNet based models. Classification models using full spectra performed better than those using effective wavelengths, with classification accuracy of calibration, validation and prediction sets all over 80% for most models. The overall results illustrated that near-infrared hyperspectral imaging with deep learning was feasible to identify cotton seed varieties.

show abstract

Section: Introductionmentioning

confidence: 99%

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It has also been reported that the technique can be used to investigate ENPs in complex matrices of environmental samples (Badireddy et al, 2012). However, dark-field spectroscopy is more applicable for surface plasmonic nanoparticles (Dong et al, 2018).…”

Section: Dark Field Spectroscopymentioning

confidence: 99%

Analytical approaches for characterizing and quantifying engineered nanoparticles in biological matrices from an (eco)toxicological perspective: old challenges, new methods and techniques

Monikh

Chupani

Vijver

et al. 2019

Science of The Total Environment

View full text Add to dashboard Cite

License: Article 25fa pilot End User Agreement This publication is distributed under the terms of Article 25fa of the Dutch Copyright Act (Auteurswet) with explicit consent by the author. Dutch law entitles the maker of a short scientific work funded either wholly or partially by Dutch public funds to make that work publicly available for no consideration following a reasonable period of time after the work was first published, provided that clear reference is made to the source of the first publication of the work. This publication is distributed under The Association of Universities in the Netherlands (VSNU) 'Article 25fa implementation' pilot project. In this pilot research outputs of researchers employed by Dutch Universities that comply with the legal requirements of Article 25fa of the Dutch Copyright Act are distributed online and free of cost or other barriers in institutional repositories. Research outputs are distributed six months after their first online publication in the original published version and with proper attribution to the source of the original publication. You are permitted to download and use the publication for personal purposes. All rights remain with the author(s) and/or copyrights owner(s) of this work. Any use of the publication other than authorised under this licence or copyright law is prohibited. If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons.

show abstract

“…Mäkelä and Geladi [20] have shown that hyperspectral imaging in the NIR region can be used for reliable determination of the heterogeneity of renewable carbon materials after multivariate image regression. Dong et al [21] reviewed recent research on hyperspectral imaging based on different techniques including Raman spectroscopy for the analysis of nanoscale materials such as metal nanoparticles, carbon nanotubes, graphene, multi-layer nanoscale materials, as well as biological components in cells.…”

Section: Basic Principles Of Vibrational Spectroscopy and Samplingmentioning

confidence: 99%

Some Applications of Vibrational Spectroscopy for the Analysis of Polymers and Polymer Composites

Bokobza

2019

Polymers

View full text Add to dashboard Cite

Vibrational spectroscopies, including infrared and Raman techniques, are important tools for the characterization of chemical composition, molecular structures, and chain orientation under mechanical deformation of polymeric materials. The development of fiber-optic-based spectrometers has broadened the use of vibrational spectroscopy for process monitoring in various fields including polymerization, curing, and manufacturing processes. Combined with chemometrics, near-infrared (NIR) spectroscopy is now recognized as one of the most important techniques for polymer analyses. Infrared and Raman studies also offer invaluable means for the analysis of inorganic particles used as reinforcing fillers for polymers. The characterization of surface species and the nature of interfacial bonding between the organic and inorganic phases are important issues for the understanding of composite properties. Infrared spectroscopy is particularly convenient for the detection and analysis of hydroxyl groups on filler surfaces, and Raman spectroscopy is particularly well suited for the study of carbon-based materials. In both techniques, polymer-filler interactions can be evidenced through frequency shifts or width changes of bands associated with vibrational modes of functional groups of either macromolecular chains or filler particles. Selected examples of application of infrared and Raman spectroscopies illustrate their potential for monitoring polymer processes, measuring polymer orientation, and characterizing polymer composites.

show abstract

A review of hyperspectral imaging for nanoscale materials research

Cited by 51 publications

References 93 publications

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Analytical approaches for characterizing and quantifying engineered nanoparticles in biological matrices from an (eco)toxicological perspective: old challenges, new methods and techniques

Some Applications of Vibrational Spectroscopy for the Analysis of Polymers and Polymer Composites

Contact Info

Product

Resources

About