Method of image quality assessment based on region of interest and Structural Similarity

DOI

10.2991/icmse-15.2015.141How to use a DOI?

Keywords

Structure Similarity(SSIM); image quality assessment; weighted coefficient; Region-Of-Interest(ROI).

Abstract

In this paper, a method of image quality assessment based on visual regions of interest and Structural Similarity(SSIM) is proposed through combining human visual interest regions and structural similarity. In this algorithm, we firstly use the SSIM to separately assess those interest regions, and get weight of different regions through analyzing the influencing factors such as brightness, gray level, area size, and then work out the image quality of ROI by adding up those weights of different regions. Secondly we can get the assessment of the entire image by using the SSIM to evaluate the entire image. The final assessment of image is the result of adding up different weights of the entire image and ROI. What’s more, the experiment results prove the method is more accurate and efficient than SSIM.

Copyright

© 2015, 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/).

Download article (PDF)

TY  - CONF
AU  - Dai Li
AU  - Tao Cheng
PY  - 2015/12
DA  - 2015/12
TI  - Method of image quality assessment based on region of interest and Structural Similarity
BT  - Proceedings of the 2015 6th International Conference on Manufacturing Science and Engineering
PB  - Atlantis Press
SP  - 786
EP  - 791
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmse-15.2015.141
DO  - 10.2991/icmse-15.2015.141
ID  - Li2015/12
ER  -