Attribute profiles without thresholds
| dc.authorscopusid | 23396161700 | |
| dc.authorscopusid | 57195216873 | |
| dc.contributor.author | Aptoula,E. | |
| dc.contributor.author | Koc,S.G. | |
| dc.date.accessioned | 2024-05-25T12:32:31Z | |
| dc.date.available | 2024-05-25T12:32:31Z | |
| dc.date.issued | 2018 | |
| dc.department | Okan University | en_US |
| dc.department-temp | Aptoula E., Gebze Technical University, Institute of Information Technologies, Kocaeli, Turkey; Koc S.G., Okan University, Mechatronics Engineering, Istanbul, Turkey | en_US |
| dc.description | Geoscience and Remote Sensing Society (GRSS); The Institute of Electrical and Electronics Engineers (IEEE) | en_US |
| dc.description.abstract | Morphological attribute profiles are among the most prominent spatial-spectral pixel description methods. They are efficient, highly flexible multiscale tools that operate at the connected component level of images. One of their few yet significant drawbacks is their need for a predefined threshold set. As such there have been multiple attempts for computing thresholds with minimal or no supervision with various levels of success. In this paper, a radically different approach is taken and a new way is presented, circumventing the need for thresholds while harnessing the descriptive power of the hierarchical tree representation underlying the attribute profiles. The introduced approach is validated with two datasets and two attributes, where it exhibits either comparable or superior performance to manual and automatic threshold based attribute profiles. © 2018 IEEE. | en_US |
| dc.identifier.citation | 4 | |
| dc.identifier.doi | 10.1109/IGARSS.2018.8519351 | |
| dc.identifier.endpage | 4510 | en_US |
| dc.identifier.isbn | 978-153867150-4 | |
| dc.identifier.scopus | 2-s2.0-85064165004 | |
| dc.identifier.startpage | 4507 | en_US |
| dc.identifier.uri | https://doi.org/10.1109/IGARSS.2018.8519351 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14517/2394 | |
| dc.identifier.volume | 2018-July | en_US |
| dc.language.iso | en | |
| dc.publisher | Institute of Electrical and Electronics Engineers Inc. | en_US |
| dc.relation.ispartof | International Geoscience and Remote Sensing Symposium (IGARSS) -- 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 -- 22 July 2018 through 27 July 2018 -- Valencia -- 141934 | en_US |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
| dc.rights | info:eu-repo/semantics/closedAccess | en_US |
| dc.subject | Attribute profiles | en_US |
| dc.subject | Hyperspectral images | en_US |
| dc.subject | Pixel classification | en_US |
| dc.subject | Supervised classification | en_US |
| dc.subject | Tree representation | en_US |
| dc.title | Attribute profiles without thresholds | en_US |
| dc.type | Conference Object | en_US |
| dspace.entity.type | Publication |