Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

The quest for the integration of visual saliency models in objective image quality assessment: A distraction power compensated combination strategy

Zhang, Wei, Talens-Noguera, Juan V. and Liu, Hantao 2015. The quest for the integration of visual saliency models in objective image quality assessment: A distraction power compensated combination strategy. Presented at: 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada, 27-30 September 2015. 2015 IEEE International Conference on Image Processing (ICIP). IEEE, p. 1250. 10.1109/ICIP.2015.7351000

Full text not available from this repository.

Abstract

Novel research on image quality metrics (IQMs) attempts to further improve their reliability by including visual attention aspects of the human visual system. Literature so far mainly focuses on the extension of a specific IQM with a specific visual saliency model. In this paper, we quest the integration of visual saliency models in IQMs, in terms of its statistical meaningfulness and combination strategy. In the first step an exhaustive evaluation is conducted by integrating twenty state-of-the-art saliency models into eight best-known IQMs for image quality assessment. It demonstrates linearly combining saliency and IQMs yields a statistically significant gain in performance. Based on the statistics, we revisit the combination strategy of saliency and IQMs and propose a new strategy taking into account the distraction power of local distortions. Results show that the proposed combination strategy consistently outperforms the conventionally used linear combination strategy.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Publisher: IEEE
ISBN: 978-1-4799-8339-1
Last Modified: 01 Feb 2019 16:00
URI: http://orca.cf.ac.uk/id/eprint/118914

Citation Data

Cited 4 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item