Perceptual metric for color transfer methods

Hristina Hristova        Olivier Le Meur        Remi Cozot        Kadi Bouatouch

IRISA / University of Rennes 1, France

ICIP 2017

Back

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 triples of input, target and result images. Then, for each triple, 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.

User study



Click on the figure above for more information about the performed user study.

Citation

Hristova, Hristina and Le Meur, Olivier and Cozot, Remi and Bouatouch, Kadi (2015). Perceptual metric for color transfer methods, ICIP 2017 
@inproceedings{hristova2017perceptual,
  title={Perceptual metric for color transfer methods},
  author={Hristova, Hristina and Meur, Olivier Le and Cozot, Remi and Bouatouch, Kadi},
  booktitle={ICIP’2017 conference, Beijing, China},
  year={2017}
}

Software