Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates
Independent component analysis combined with various strategies for cross-validation, uncertainty estimates by jack-knifing and critical Hotelling’s T2 limits estimation, proposed in this paper, is used for classification purposes in hyperspectral images. To the best of our knowledge, the combined a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IM Publications Open
2018-02-01
|
| Series: | Journal of Spectral Imaging |
| Subjects: | |
| Online Access: | https://www.impopen.com/download.php?code=I07_a4 |
| _version_ | 1818499942696615936 |
|---|---|
| author | Beatriz Galindo-Prieto Frank Westad |
| author_facet | Beatriz Galindo-Prieto Frank Westad |
| author_sort | Beatriz Galindo-Prieto |
| collection | DOAJ |
| description | Independent component analysis combined with various strategies for cross-validation, uncertainty estimates by jack-knifing and critical Hotelling’s T2 limits estimation, proposed in this paper, is used for classification purposes in hyperspectral images. To the best of our knowledge, the combined approach of methods used in this paper has not been previously applied to hyperspectral imaging analysis for interpretation and classification in the literature. The data analysis performed here aims to distinguish between four different types of plastics, some of them containing brominated flame retardants, from their near infrared hyperspectral images. The results showed that the method approach used here can be successfully used for unsupervised classification. A comparison of validation approaches, especially leave-one-out cross-validation and regions of interest scheme validation is also evaluated. |
| first_indexed | 2024-12-10T20:36:25Z |
| format | Article |
| id | doaj.art-797efb1dccf14a9ebddc2d9e5c8bfc6c |
| institution | Directory Open Access Journal |
| issn | 2040-4565 2040-4565 |
| language | English |
| last_indexed | 2024-12-10T20:36:25Z |
| publishDate | 2018-02-01 |
| publisher | IM Publications Open |
| record_format | Article |
| series | Journal of Spectral Imaging |
| spelling | doaj.art-797efb1dccf14a9ebddc2d9e5c8bfc6c2022-12-22T01:34:31ZengIM Publications OpenJournal of Spectral Imaging2040-45652040-45652018-02-0171a410.1255/jsi.2018.a4Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimatesBeatriz Galindo-Prieto0Frank Westad1Department of Engineering Cybernetics (ITK), Norwegian University of Science and Technology (NTNU), NorwayDepartment of Engineering Cybernetics (ITK), Norwegian University of Science and Technology (NTNU), Norway and CAMO Software, Oslo, NorwayIndependent component analysis combined with various strategies for cross-validation, uncertainty estimates by jack-knifing and critical Hotelling’s T2 limits estimation, proposed in this paper, is used for classification purposes in hyperspectral images. To the best of our knowledge, the combined approach of methods used in this paper has not been previously applied to hyperspectral imaging analysis for interpretation and classification in the literature. The data analysis performed here aims to distinguish between four different types of plastics, some of them containing brominated flame retardants, from their near infrared hyperspectral images. The results showed that the method approach used here can be successfully used for unsupervised classification. A comparison of validation approaches, especially leave-one-out cross-validation and regions of interest scheme validation is also evaluated.https://www.impopen.com/download.php?code=I07_a4hyperspectral imagingROI selectionspectroscopyindependent component analysisICAcross-validationuncertainty testjack-knifingHotelling’s T2classification |
| spellingShingle | Beatriz Galindo-Prieto Frank Westad Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates Journal of Spectral Imaging hyperspectral imaging ROI selection spectroscopy independent component analysis ICA cross-validation uncertainty test jack-knifing Hotelling’s T2 classification |
| title | Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates |
| title_full | Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates |
| title_fullStr | Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates |
| title_full_unstemmed | Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates |
| title_short | Classification in hyperspectral images by independent component analysis, segmented cross-validation and uncertainty estimates |
| title_sort | classification in hyperspectral images by independent component analysis segmented cross validation and uncertainty estimates |
| topic | hyperspectral imaging ROI selection spectroscopy independent component analysis ICA cross-validation uncertainty test jack-knifing Hotelling’s T2 classification |
| url | https://www.impopen.com/download.php?code=I07_a4 |
| work_keys_str_mv | AT beatrizgalindoprieto classificationinhyperspectralimagesbyindependentcomponentanalysissegmentedcrossvalidationanduncertaintyestimates AT frankwestad classificationinhyperspectralimagesbyindependentcomponentanalysissegmentedcrossvalidationanduncertaintyestimates |