Perceptual metric for color transfer methods

Abstract : In this paper, we propose a perceptual model for evaluating results from color transfer methods. We conduct a user study, which provides a set of subjective scores for triplets of input, target and result images. Then, for each triplet, we compute a number of image features, which objectively characterize a color transfer. To describe the relationship between these features and the subjective scores, we build a regression model with random forests. An analysis and a cross-validation show that the predictions of our model are highly accurate.
Keywords : color transfer
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing - ICIP 2017, Sep 2017, Shanghai, China. 2017
Liste complète des métadonnées

https://hal.inria.fr/hal-01651141
Contributeur : Olivier Le Meur <>
Soumis le : mardi 28 novembre 2017 - 16:59:38
Dernière modification le : jeudi 12 avril 2018 - 01:55:01

Identifiants

  • HAL Id : hal-01651141, version 1

Citation

Hristina Hristova, Olivier Le Meur, Rémi Cozot, Kadi Bouatouch. Perceptual metric for color transfer methods. IEEE International Conference on Image Processing - ICIP 2017, Sep 2017, Shanghai, China. 2017. 〈hal-01651141〉

Partager

Métriques

Consultations de la notice

274