In this paper we present tests and results of an automatic color fading restoration process for digitized movies. The proposed color correction method is based on the ACE model, an unsupervised color equalization algorithm based on a perceptual approach and inspired by some mechanisms of the human visual system, This perceptual approach is local, robust and does not need any user region selection or any other user supervision. However the model has a small number of parameters that has to be set once before the filtering. The tests presented in this paper aim to study these parameters and find their effect on the final result.

Tuning of perceptual technique for digital movie color restoration / A. Rizzi, M. Chambah, D. Lenza, B. Besserer, D. Marini (PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING). - In: Visual Communications and Image Processing 2004 / [a cura di] S. Panchanathan, B. Vasudev. - [s.l] : SPIE, 2004. - ISBN 0-8194-5211-4. - pp. 1286-1294 (( convegno Electronic Imaging tenutosi a San Jose nel 2004 [10.1117/12.525789].

Tuning of perceptual technique for digital movie color restoration

A. Rizzi
Primo
;
D. Marini
Ultimo
2004

Abstract

In this paper we present tests and results of an automatic color fading restoration process for digitized movies. The proposed color correction method is based on the ACE model, an unsupervised color equalization algorithm based on a perceptual approach and inspired by some mechanisms of the human visual system, This perceptual approach is local, robust and does not need any user region selection or any other user supervision. However the model has a small number of parameters that has to be set once before the filtering. The tests presented in this paper aim to study these parameters and find their effect on the final result.
ACE; Automatic color correction; Color constancy; Color fading; Digital film restoration
Settore INF/01 - Informatica
SPIE
IS&T
Book Part (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/192180
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 5
social impact