Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/27747
Título: | Context-aware features and robust image representations | Autor: | Martins, P. Carvalho, P. Gatta, C. |
Palavras-chave: | Local features; Keypoint extraction; Image content descriptors; Image representation; Visual saliency; Information theory; Kernel estimators; Complementarity | Data: | Fev-2014 | Editora: | Elsevier | Citação: | MARTINS, P.; CARVALHO, P.; GATTA, C. - Context-aware features and robust image representations. "Journal of Visual Communication and Image Representation". ISSN 1047-3203. Vol. 25 Nº. 2 (2014) p. 339-348 | Título da revista, periódico, livro ou evento: | Journal of Visual Communication and Image Representation | Volume: | 25 | Número: | 2 | Resumo: | Local image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific type of features; the idea is to retrieve complementary features which are relevant within the image context. We empirically validate the method by investigating the repeatability, the completeness, and the complementarity of context-aware features on standard benchmarks. In a comparison with strictly local features, we show that our context-aware features produce more robust image representations. Furthermore, we study the complementarity between strictly local features and context-aware ones to produce an even more robust representation. | URI: | https://hdl.handle.net/10316/27747 | ISSN: | 1047-3203 | DOI: | 10.1016/j.jvcir.2013.10.006 | Direitos: | openAccess |
Aparece nas coleções: | I&D CISUC - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Context-Aware Features and Robust Image Representations.pdf | 1.37 MB | Adobe PDF | Ver/Abrir |
Citações SCOPUSTM
5
Visto em 15/abr/2024
Citações WEB OF SCIENCETM
10
4
Visto em 2/abr/2024
Visualizações de página 5
1.108
Visto em 16/abr/2024
Downloads
334
Visto em 16/abr/2024
Google ScholarTM
Verificar
Altmetric
Altmetric
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.