Per citar aquest document: http://ddd.uab.cat/record/52528
Matching Local Invariant Features with Contextual Information : an Experimental Evaluation.
Sidibe, Desire (LGI2P - Ecole des Mines Ales (Nimes, França))
Montesinos, Philippe (LGI2P - Ecole des Mines Ales (Nimes, França))
Janaqi, Stefan (LGI2P - Ecole des Mines Ales (Nimes, França))

Data: 2008
Resum: The main advantage of using local invariant features is their local character which yields robustness to occlusion and varying background. Therefore, local features have proved to be a powerful tool for finding correspondences between images, and have been employed in many applications. However, the local character limits the descriptive capability of features descriptors, and local features fail to resolve ambiguities that can occur when an image shows multiple similar regions. Considering some global information will clearly help to achieve better performances. The question is which information to use and how to use it. Context can be used to enrich the description of the features, or used in the matching step to filter out mismatches. In this paper, we compare different recent methods which use context for matching and show that better results are obtained if contextual information is used during the matching process. We evaluate the methods in two applications: wide baseline matching and object recognition, and it appears that a relaxation based approach gives the best results.
Drets: Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades. Creative Commons
Llengua: Anglès.
Document: article ; recerca ; publishedVersion
Matèria: Image matching ; Local invariant features ; SIFT ; Contextual information ; Object recognition ; Imatges coincidents ; Característiques locals invariants ; Informació contextual ; Reconeixement d'objectes ; Imagenes coincidentes ; Características locales invariantes ; Información contextual ; Reconocimiento de objetos
Publicat a: ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 7 n. 1 (2008) p. 26-39, ISSN 1577-5097

Adreça alternativa: http://www.raco.cat/index.php/ELCVIA/article/view/131389


14 p, 1.1 MB

El registre apareix a les col·leccions:
Articles > Articles publicats > ELCVIA : Electronic Letters on Computer Vision and Image Analysis
Articles > Articles de recerca

 Registre creat el 2010-01-14, darrera modificació el 2016-06-11



   Favorit i Compartir