Saliency-aware Image Quality Assessment
- DOI
- 10.2991/wartia-16.2016.280How to use a DOI?
- Keywords
- Visual Saliency, Image Quality Assessment, Saliency Detection,
- Abstract
Currently, visual saliency detection has been discovered and widely applied in the field of computer vision and image processing. Recent works have shown that considering human visual system features in image quality assessment will improve the consistence between objective assessment results and subjective visual perception. So we propose saliency-aware image quality assessment through a universal method to combine saliency detection with image quality assessment metrics. Since there is no image dataset used for image quality assessment and saliency detection researches simultaneously, we create a new image database, called TID-2013S, which is inheriting from image quality assessment database TID-2013 and contains 25 manually labeled ground truth images. In this paper, we select 8 representative full reference image quality assessment metrics and 7 state-of-the-art saliency detection algorithms to validate the performance of our proposed method. Experiment results show that when using the appropriate parameter of mapping function, our saliency-aware approach achieves the best performance improvement by 5.41%. And for most of image quality assessment metrics, the MCA saliency detection algorithm works best.
- Copyright
- © 2016, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Zhanghui Liu AU - Yize Huang AU - Yuzhen Niu AU - Lening Lin PY - 2016/05 DA - 2016/05 TI - Saliency-aware Image Quality Assessment BT - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications PB - Atlantis Press SP - 1352 EP - 1358 SN - 2352-5401 UR - https://doi.org/10.2991/wartia-16.2016.280 DO - 10.2991/wartia-16.2016.280 ID - Liu2016/05 ER -