Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Perceptual metric for color transfer methods

Abstract: 

We present 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.

up
0 users have voted:

Paper Details

Authors:
Olivier Le Meur, Remi Cozot, Kadi Bouatouch
Submitted On:
14 September 2017 - 10:33am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Hristina Hristova
Paper Code:
2072
Document Year:
2017
Cite

Document Files

Perceptual evaluation metric

(15 downloads)

Subscribe

[1] Olivier Le Meur, Remi Cozot, Kadi Bouatouch, "Perceptual metric for color transfer methods", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2033. Accessed: Oct. 19, 2017.
@article{2033-17,
url = {http://sigport.org/2033},
author = {Olivier Le Meur; Remi Cozot; Kadi Bouatouch },
publisher = {IEEE SigPort},
title = {Perceptual metric for color transfer methods},
year = {2017} }
TY - EJOUR
T1 - Perceptual metric for color transfer methods
AU - Olivier Le Meur; Remi Cozot; Kadi Bouatouch
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2033
ER -
Olivier Le Meur, Remi Cozot, Kadi Bouatouch. (2017). Perceptual metric for color transfer methods. IEEE SigPort. http://sigport.org/2033
Olivier Le Meur, Remi Cozot, Kadi Bouatouch, 2017. Perceptual metric for color transfer methods. Available at: http://sigport.org/2033.
Olivier Le Meur, Remi Cozot, Kadi Bouatouch. (2017). "Perceptual metric for color transfer methods." Web.
1. Olivier Le Meur, Remi Cozot, Kadi Bouatouch. Perceptual metric for color transfer methods [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2033