A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF)
Principal components analysis (PCA), maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) models are common factor-based models used for analysis of hyperspectral images. The models can be posed as maximisation problems that result in a symmetric ei...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IM Publications Open
2022-08-01
|
| Series: | Journal of Spectral Imaging |
| Subjects: | |
| Online Access: | https://www.impopen.com/download.php?code=I11_a6 |
| _version_ | 1797995531401691136 |
|---|---|
| author | Neal B. Gallagher |
| author_facet | Neal B. Gallagher |
| author_sort | Neal B. Gallagher |
| collection | DOAJ |
| description | Principal components analysis (PCA), maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) models are common factor-based models used for analysis of hyperspectral images. The models can be posed as maximisation problems that result in a symmetric eigenvalue problem (SEP) for each model. The SEPs allow a simple theoretical comparison of the models using a PCA metaphor with MAF, MNF and MDF describable as weighted PCA models. The examples show that the different methods captured different signals in the images that can be examined individually or combined synergistically allowing for additional modelling and extended visualisation. MDF is a factor-based edge detection model that not only allows for additional visualisation but the opportunity to identify and exclude (or highlight) edge signal in the images. An example shows that models can also be used synergistically for finding and elucidating anomalies. In the example, MDF showed the highest sensitivity of the models studied for anomaly detection. |
| first_indexed | 2024-04-11T10:03:12Z |
| format | Article |
| id | doaj.art-a8ea71bfcb4942e686af415d4a77e9a1 |
| institution | Directory Open Access Journal |
| issn | 2040-4565 |
| language | English |
| last_indexed | 2024-04-11T10:03:12Z |
| publishDate | 2022-08-01 |
| publisher | IM Publications Open |
| record_format | Article |
| series | Journal of Spectral Imaging |
| spelling | doaj.art-a8ea71bfcb4942e686af415d4a77e9a12022-12-22T04:30:19ZengIM Publications OpenJournal of Spectral Imaging2040-45652022-08-0111a610.1255/jsi.2022.a6A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF)Neal B. Gallagher0https://orcid.org/0000-0003-3446-2820Eigenvector Research, Inc., 300 Bella Strada Lane, Manson, WA 98831, USAPrincipal components analysis (PCA), maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) models are common factor-based models used for analysis of hyperspectral images. The models can be posed as maximisation problems that result in a symmetric eigenvalue problem (SEP) for each model. The SEPs allow a simple theoretical comparison of the models using a PCA metaphor with MAF, MNF and MDF describable as weighted PCA models. The examples show that the different methods captured different signals in the images that can be examined individually or combined synergistically allowing for additional modelling and extended visualisation. MDF is a factor-based edge detection model that not only allows for additional visualisation but the opportunity to identify and exclude (or highlight) edge signal in the images. An example shows that models can also be used synergistically for finding and elucidating anomalies. In the example, MDF showed the highest sensitivity of the models studied for anomaly detection.https://www.impopen.com/download.php?code=I11_a6maximum autocorrelation factorsminimum noise factorsmaximum difference factors |
| spellingShingle | Neal B. Gallagher A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) Journal of Spectral Imaging maximum autocorrelation factors minimum noise factors maximum difference factors |
| title | A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) |
| title_full | A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) |
| title_fullStr | A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) |
| title_full_unstemmed | A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) |
| title_short | A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) |
| title_sort | comparison of common factor based methods for hyperspectral image exploration principal components analysis maximum autocorrelation factors maf minimum noise factors mnf and maximum difference factors mdf |
| topic | maximum autocorrelation factors minimum noise factors maximum difference factors |
| url | https://www.impopen.com/download.php?code=I11_a6 |
| work_keys_str_mv | AT nealbgallagher acomparisonofcommonfactorbasedmethodsforhyperspectralimageexplorationprincipalcomponentsanalysismaximumautocorrelationfactorsmafminimumnoisefactorsmnfandmaximumdifferencefactorsmdf AT nealbgallagher comparisonofcommonfactorbasedmethodsforhyperspectralimageexplorationprincipalcomponentsanalysismaximumautocorrelationfactorsmafminimumnoisefactorsmnfandmaximumdifferencefactorsmdf |