Publicação
Multispectral Face Recognition on the Wild
| datacite.subject.fos | Engenharia e Tecnologia::Outras Engenharias e Tecnologias | |
| dc.contributor.author | Martins, Pedro | |
| dc.contributor.author | Bernadino, Alexandre | |
| dc.contributor.author | Silva, José | |
| dc.date.accessioned | 2026-02-10T09:09:25Z | |
| dc.date.available | 2026-02-10T09:09:25Z | |
| dc.date.issued | 2022-03-22 | |
| dc.description.abstract | This work proposes a multispectral face recognition system in an uncontrolled environment, aiming to identify or authenticate identities (people) through their facial images. Face recognition systems in uncontrolled environments have shown impressive performance improvements over the last decades. However, most are limited to the use of a single spectral band in the visible spectrum. The use of multispectral images makes it possible to collect information that is not obtainable in the visible spectrum when certain occlusions exist (e.g., fog and plastic materials) and in low or no light environments. The proposed work uses the scores obtained by face recognition systems in different spectral bands to make a joint final decision in identification. The evaluation of different methods for each of the components of a face recognition system allowed selecting the most suitable ones for a multispectral face recognition system in an uncontrolled environment. The experimental results, expressed in Rank-1 scores, were 99.5% and 99.6% in the TUFTS multispectral database with pose variation and expression variation, indicating that the use of multispectral images in an uncontrolled environment is advantageous when compared with the use of single spectral band images. | eng |
| dc.identifier.issn | 978-989-96698-8-8 | |
| dc.identifier.uri | http://hdl.handle.net/10400.26/61587 | |
| dc.language.iso | eng | |
| dc.peerreviewed | yes | |
| dc.publisher | Academia militar | |
| dc.rights.uri | N/A | |
| dc.subject | multispectral face recognition | |
| dc.subject | score fusion. | |
| dc.title | Multispectral Face Recognition on the Wild | por |
| dc.type | text | |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 27 | |
| oaire.citation.issue | 6 | |
| oaire.citation.startPage | 22 | |
| oaire.citation.title | Jornadas das Engenharias 6ª Edição - Livro de Artigos | |
| oaire.version | http://purl.org/coar/version/c_ab4af688f83e57aa |