Back to articles
Volume: 29 | Article ID: art00009
Interactions Between Saliency and Utility
  DOI :  10.2352/ISSN.2470-1173.2017.14.HVEI-120  Published OnlineJanuary 2017

We evaluate improvements to image utility assessment algorithms with the inclusion of saliency information, as well as the saliency prediction performance of three saliency models based on successful utility estimators. Fourteen saliency models were incorporated into several utility estimation algorithms, resulting in significantly improved performance in some cases, with RMSE reductions of between 3 and 25%. Algorithms designed for utility estimation benefit less from the addition of saliency information than those originally designed for quality estimation, suggesting that estimators designed to measure utility also measure some degree of saliency information, and that saliency is important for utility estimation. To test this hypothesis, three saliency models are created from NICE and MS-DGU utility estimators by convolving logical maps of image contours with a Gaussian function. The performance of these utility-based models reveals that highlyperforming utility estimation algorithms can also predict saliency to an extent, reaching approximately 77% of the prediction performance of state-of-the-art saliency models when evaluated on two common saliency datasets.

Subject Areas :
Views 28
Downloads 3
 articleview.views 28
 articleview.downloads 3
  Cite this article 

Edward T. Scott, Sheila S. Hemami, "Interactions Between Saliency and Utilityin Proc. IS&T Int’l. Symp. on Electronic Imaging: Human Vision and Electronic Imaging,  2017,  pp 77 - 84,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2017
Electronic Imaging
Society for Imaging Science and Technology