Matching hyperspectral absorptions by weighted hamming distance
Abstract To analyse and compare hyperspectral signatures, features extraction and matching are two key issues. In this letter, hyperspectral absorption features and the corresponding matching algorithm are discussed. First, an absorption detection method is applied to catch all necessary spectral ab...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-09-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ell2.12238 |
| _version_ | 1811210245208276992 |
|---|---|
| author | Baofeng Guo |
| author_facet | Baofeng Guo |
| author_sort | Baofeng Guo |
| collection | DOAJ |
| description | Abstract To analyse and compare hyperspectral signatures, features extraction and matching are two key issues. In this letter, hyperspectral absorption features and the corresponding matching algorithm are discussed. First, an absorption detection method is applied to catch all necessary spectral absorptions with improved reliability. Then, a weighted Hamming distance is proposed to match the binary absorption‐features. Next, an elastic matching scheme is designed to classify the hyperspectral data. Experiments of classification are carried out on six classes of vegetation from the Salinas data‐set. Results show that the proposed method not only increased the overall classification accuracy to 73.13% from back propagation neural network's 71.86% and support vector machine's 73.06%, but also improved the error distributions among different classes. |
| first_indexed | 2024-04-12T04:52:33Z |
| format | Article |
| id | doaj.art-79c86b030c8340df8ea34b845c8df992 |
| institution | Directory Open Access Journal |
| issn | 0013-5194 1350-911X |
| language | English |
| last_indexed | 2024-04-12T04:52:33Z |
| publishDate | 2021-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj.art-79c86b030c8340df8ea34b845c8df9922022-12-22T03:47:16ZengWileyElectronics Letters0013-51941350-911X2021-09-01571972772910.1049/ell2.12238Matching hyperspectral absorptions by weighted hamming distanceBaofeng Guo0School of Automation Hangzhou Dianzi University Hangzhou ChinaAbstract To analyse and compare hyperspectral signatures, features extraction and matching are two key issues. In this letter, hyperspectral absorption features and the corresponding matching algorithm are discussed. First, an absorption detection method is applied to catch all necessary spectral absorptions with improved reliability. Then, a weighted Hamming distance is proposed to match the binary absorption‐features. Next, an elastic matching scheme is designed to classify the hyperspectral data. Experiments of classification are carried out on six classes of vegetation from the Salinas data‐set. Results show that the proposed method not only increased the overall classification accuracy to 73.13% from back propagation neural network's 71.86% and support vector machine's 73.06%, but also improved the error distributions among different classes.https://doi.org/10.1049/ell2.12238Image recognitionComputer vision and image processing techniquesNeural netsSupport vector machines |
| spellingShingle | Baofeng Guo Matching hyperspectral absorptions by weighted hamming distance Electronics Letters Image recognition Computer vision and image processing techniques Neural nets Support vector machines |
| title | Matching hyperspectral absorptions by weighted hamming distance |
| title_full | Matching hyperspectral absorptions by weighted hamming distance |
| title_fullStr | Matching hyperspectral absorptions by weighted hamming distance |
| title_full_unstemmed | Matching hyperspectral absorptions by weighted hamming distance |
| title_short | Matching hyperspectral absorptions by weighted hamming distance |
| title_sort | matching hyperspectral absorptions by weighted hamming distance |
| topic | Image recognition Computer vision and image processing techniques Neural nets Support vector machines |
| url | https://doi.org/10.1049/ell2.12238 |
| work_keys_str_mv | AT baofengguo matchinghyperspectralabsorptionsbyweightedhammingdistance |