In this paper an efficient method for image retargeting is proposed. It relies on a monte-carlo model that makes use of image saliency. Each random sample is extracted from deformation probability mass function defined properly, and shrinks or enlarges the image by a fixed size. The shape of the function, determining which regions of the image are affected by the deformations, depends on the image saliency. High informative regions are less likely to be chosen, while low saliency regions are more probable. Such a model does not require any optimization, since its solution is obtained by extracting repeatedly random samples, and allows real-time application even for large images. Computation time can be additionally improved using a parallel implementation. The approach is fully automatic, though it can be improved by providing interactively cues such as geometric constraints and/or automatic or manual labeling of relevant objects. The results prove that the presented method achieves results comparable or superior to reference methods, while improving efficiency.
Gallea, R., Ardizzone, E., Pirrone, R. (2014). Monte-Carlo Image Retargeting. In VISAPP 2014 Proceedings of the 9th International Conference on Computer Vision Theory and Applications (pp.402-408). SCITEPRESS – Science and Technology Publications [10.5220/0004744404020408].
Monte-Carlo Image Retargeting
GALLEA, Roberto;ARDIZZONE, Edoardo;PIRRONE, Roberto
2014-01-01
Abstract
In this paper an efficient method for image retargeting is proposed. It relies on a monte-carlo model that makes use of image saliency. Each random sample is extracted from deformation probability mass function defined properly, and shrinks or enlarges the image by a fixed size. The shape of the function, determining which regions of the image are affected by the deformations, depends on the image saliency. High informative regions are less likely to be chosen, while low saliency regions are more probable. Such a model does not require any optimization, since its solution is obtained by extracting repeatedly random samples, and allows real-time application even for large images. Computation time can be additionally improved using a parallel implementation. The approach is fully automatic, though it can be improved by providing interactively cues such as geometric constraints and/or automatic or manual labeling of relevant objects. The results prove that the presented method achieves results comparable or superior to reference methods, while improving efficiency.File | Dimensione | Formato | |
---|---|---|---|
47444.pdf
Solo gestori archvio
Descrizione: Articolo principale
Dimensione
690.87 kB
Formato
Adobe PDF
|
690.87 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
1_pdfsam_VISAPP 2014 Volume 1.pdf
Solo gestori archvio
Descrizione: Copertina e indice
Dimensione
1.64 MB
Formato
Adobe PDF
|
1.64 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.