Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis
In this paper, we propose a method to reduce spectral dimension based on the phase of integrated bispectrum. Because of the excellent and robust information extracted from the bispectrum, the proposed method can achieve high spectral classification accuracy even with low dimensional feature. The c...
| Main Author: | |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/4097/ http://eprints.utem.edu.my/id/eprint/4097/1/2-SPECTRAL_DIMENSIONALITY_REDUCTION.pdf |
| _version_ | 1848886991366651904 |
|---|---|
| author | Saipullah, Khairul Muzzammil |
| author_facet | Saipullah, Khairul Muzzammil |
| author_sort | Saipullah, Khairul Muzzammil |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | In this paper, we propose a method to reduce spectral dimension based on the phase of integrated bispectrum.
Because of the excellent and robust information extracted from the bispectrum, the proposed method can achieve
high spectral classification accuracy even with low dimensional feature. The classification accuracy of bispectrum
with one dimensional feature is 98.8%, whereas those of principle component analysis (PCA) and independent
component analysis (ICA) are 41.2% and 63.9%, respectively. The unsupervised segmentation accuracy of
bispectrum is also 20% and 40% greater than those of PCA and ICA, respectively. |
| first_indexed | 2025-11-15T19:47:17Z |
| format | Conference or Workshop Item |
| id | utem-4097 |
| institution | Universiti Teknikal Malaysia Melaka |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T19:47:17Z |
| publishDate | 2011 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utem-40972015-05-28T02:39:50Z http://eprints.utem.edu.my/id/eprint/4097/ Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis Saipullah, Khairul Muzzammil TA Engineering (General). Civil engineering (General) In this paper, we propose a method to reduce spectral dimension based on the phase of integrated bispectrum. Because of the excellent and robust information extracted from the bispectrum, the proposed method can achieve high spectral classification accuracy even with low dimensional feature. The classification accuracy of bispectrum with one dimensional feature is 98.8%, whereas those of principle component analysis (PCA) and independent component analysis (ICA) are 41.2% and 63.9%, respectively. The unsupervised segmentation accuracy of bispectrum is also 20% and 40% greater than those of PCA and ICA, respectively. 2011-09-19 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utem.edu.my/id/eprint/4097/1/2-SPECTRAL_DIMENSIONALITY_REDUCTION.pdf Saipullah, Khairul Muzzammil (2011) Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis. In: Image and Signal Processing for Remote Sensing XVII, Monday 19 September 2011, Prague, Czech Republic. http://spiedigitallibrary.org/proceedings/resource/2/psisdg/8180/1/81801H_1?isAuthorized=no |
| spellingShingle | TA Engineering (General). Civil engineering (General) Saipullah, Khairul Muzzammil Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| title | Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| title_full | Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| title_fullStr | Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| title_full_unstemmed | Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| title_short | Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| title_sort | spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis |
| topic | TA Engineering (General). Civil engineering (General) |
| url | http://eprints.utem.edu.my/id/eprint/4097/ http://eprints.utem.edu.my/id/eprint/4097/ http://eprints.utem.edu.my/id/eprint/4097/1/2-SPECTRAL_DIMENSIONALITY_REDUCTION.pdf |