Deep generative neural networks for spectral image processing

Mishra, Puneet

doi:10.1016/j.aca.2021.339308

Cited by 2 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The typical approach to hyperspectral image processing is either pixel-wise analysis using chemometric models 21 or based on image analysis using DL approaches. 17 Pixel-wise predictions are mainly performed when there is spatial heterogeneity and also interest in exploring the spatial differences in properties. In the presented results, we did not perform pixel-wise predictions to generate chemical maps.…”

Section: Resultsmentioning

confidence: 99%

“…One of the main steps in using HSI in the spectral range of VNIR is that, for predictive modeling, calibrations need to be developed. 17,18 Calibrations are nothing but predictive models based on reference samples covering a wide variation in physicochemical properties of interest. 19 In the case of VNIR spectral modeling, some special chemometric methods such as partial least squares (PLS) are considered as the gold standard.…”

mentioning

confidence: 99%

“…3,21 In fact, it can be observed that HSI in the close range is minimally treated as imaging but more as a point spectrometer capable of measuring spectra from different locations. The rich contextual spatial information available in the imaging domain of HSI is minimally used, 17 and also, minimal attention is paid to it during modeling. In some recent studies, the authors have started focusing on using spatial information for improved model building 22,23 as well as the validation of models in terms of spatial homogeneity/heterogeneity.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction

Mishra,

Albano‐Gaglio,

Font‐i‐Furnols

2024

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

This study demonstrates a new approach to process hyperspectral images where both the contextual spatial information as well as the spectral information are used to predict sample properties. The deep contextual spatial information is extracted using the deep feature extraction from pretrained resnet‐18 deep learning architecture, while the spectral information was readily available as the average pixel values. To fuse the information in a complementary way, a multiblock modeling approach called sequential orthogonalized partial least squares was used. The sequential model guarantees that the information learned is complementary from spatial and spectral domains. The potential of the approach is demonstrated to predict several physical and chemical properties in pork bellies.

show abstract

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction

Mishra,

Albano‐Gaglio,

Font‐i‐Furnols

2024

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Principal component analysis (PCA) is a widely used linear dimensionality reduction technique. 21 Because hyperspectral images are highdimensional, they are processed to reduce the amount of data and make them easier to analyze. 22 As one of the most widely used color systems, RGB include almost all colors that can be perceived by human vision.…”

Section: Chemometrics Methodsmentioning

confidence: 99%

“…Data compression is crucial because it removed redundant bands and simplifying operations and classification algorithms. Principal component analysis (PCA) is a widely used linear dimensionality reduction technique 21 . Because hyperspectral images are high‐dimensional, they are processed to reduce the amount of data and make them easier to analyze 22 .…”

Section: Methodsmentioning

confidence: 99%

Non‐destructive discrimination of homochromatic foreign materials in cut tobacco based on VIS‐NIR hyperspectral imaging

et al. 2023

View full text Add to dashboard Cite

BACKGROUND The presence of foreign materials (FM) not only reduces the commercial value of tobacco and the quality of cigarette products, but also affects the aroma and flavor of cigarettes. Existing tobacco deblending equipment has received little study with respect to homochromatic FM. In the present study, visible‐near infrared (VIS‐NIR) hyperspectral imaging technique combined with chemometrics were used to identify and visualize the homochromatic FM on the surface of thining tobacco. A comparison with conventional vision method was made to analyze the feasibility of the method. The importance of detecting FM in cut tobacco was further demonstrated by first studying the volatile organic compounds produced in cigarette mixed FM smoke and their effects on human health before conducting hyperspectral experiments. RESULTS The results indicated that solid‐phase microextraction and gas chromatography mass spectrometry could detect volatile organic compounds in mainstream cigarette smoke that were not cigarette components and affected consumer health. Then, spectral features of the samples were extracted from hyperspectral images for building identification models to distinguish FM from cut tobacco. The visual RGB values of cut tobacco and FM were also used for the analysis of the recognition models. The results showed that the accuracy, precision and recall reached 100.00% using the back propagation artificial neural network classification model based on the principal component analysis raw wavelengths. The visualization results based on the optimal model produced clearer localization than conventional computer vision method. CONCLUSION The present study revealed that the VIS‐NIR hyperspectral imaging technology had advantage in the detection and localization of FM on the surface of thinning tobacco, which provided a foundation for improving the quality and safety of cut tobacco production. © 2023 Society of Chemical Industry.

show abstract

Deep generative neural networks for spectral image processing

Cited by 2 publications

References 32 publications

A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction

A short note on deep contextual spatial and spectral information fusion for hyperspectral image processing: Case of pork belly properties prediction

Non‐destructive discrimination of homochromatic foreign materials in cut tobacco based on VIS‐NIR hyperspectral imaging

Contact Info

Product

Resources

About