On the effect of synthetic morphological feature vectors on hyperspectral image classification performance
| dc.authorscopusid | 56717425400 | |
| dc.authorscopusid | 23396161700 | |
| dc.authorscopusid | 35617171700 | |
| dc.contributor.author | Davari,A.A. | |
| dc.contributor.author | Aptoula,E. | |
| dc.contributor.author | Yanikoglu,B. | |
| dc.date.accessioned | 2024-05-25T12:32:01Z | |
| dc.date.available | 2024-05-25T12:32:01Z | |
| dc.date.issued | 2015 | |
| dc.department | Okan University | en_US |
| dc.department-temp | Davari A.A., Department of Computer Science and Engineering, Sabanci University, Istanbul, Turkey; Aptoula E., Department of Computer Engineering, Okan University, Istanbul, Turkey; Yanikoglu B., Department of Computer Science and Engineering, Sabanci University, Istanbul, Turkey | en_US |
| dc.description.abstract | This paper studies the effect of synthetic feature vectors on the classification performance of hyperspectral remote sensing images. As feature vectors, it has been chosen to employ morphological attribute profiles, that have proven themselves in this field. At this early stage of our work, the relatively simple Bootstrapping algorithm has been used for synthetic feature vector generation. Based on experiments conducted on multiple hyperspectral datasets, it has been observed that synthetic feature vectors contribute considerably to classification performance in the case of limited training dataset sizes. © 2015 IEEE. | en_US |
| dc.identifier.citationcount | 3 | |
| dc.identifier.doi | 10.1109/SIU.2015.7129909 | |
| dc.identifier.endpage | 656 | en_US |
| dc.identifier.isbn | 978-146737386-9 | |
| dc.identifier.scopus | 2-s2.0-84939153674 | |
| dc.identifier.startpage | 653 | en_US |
| dc.identifier.uri | https://doi.org/10.1109/SIU.2015.7129909 | |
| dc.language.iso | en | |
| dc.publisher | Institute of Electrical and Electronics Engineers Inc. | en_US |
| dc.relation.ispartof | 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings -- 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 -- 16 May 2015 through 19 May 2015 -- Malatya -- 113052 | en_US |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
| dc.rights | info:eu-repo/semantics/closedAccess | en_US |
| dc.scopus.citedbyCount | 3 | |
| dc.subject | Bootstrap | en_US |
| dc.subject | Classification | en_US |
| dc.subject | Extended morphological attribute profile | en_US |
| dc.subject | Hyperspectral image | en_US |
| dc.subject | Remote sensing | en_US |
| dc.subject | Resampling | en_US |
| dc.title | On the effect of synthetic morphological feature vectors on hyperspectral image classification performance | en_US |
| dc.type | Conference Object | en_US |