Medical image quality assessment via contrast masking

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

The human visual system (HVS) is one of the most important factor for image quality assessment (IQA). The IQA approaches integrating the characteristics of HVS are considered as the more reasonable and more effective approaches to obtain the image quality. In this paper, we propose an improved structural similarity metric (SSIM) for the medical images. The proposed method utilizes the visual sensitivity change in the different image regions to weight the quality map, which is obtained via integrating the contrast masking (CM) characteristic into the SSIM-based framework and called C-SSIM. Furthermore, we build a medical image quality assessment database for further testifying the effectiveness of our approach. The experimental result of our approach correlates well with human subjective opinions of image quality.

Original languageEnglish
Title of host publicationProceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015
EditorsLipo Wang, Sen Lin, Zhiyong Tao, Bing Zeng, Xiaowei Hui, Liangshan Shao, Jie Liang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages964-968
Number of pages5
ISBN (Electronic)9781467390989
DOIs
Publication statusPublished - 16 Feb 2016
Event8th International Congress on Image and Signal Processing, CISP 2015 - Shenyang, China
Duration: 14 Oct 201516 Oct 2015

Publication series

NameProceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015

Conference

Conference8th International Congress on Image and Signal Processing, CISP 2015
Country/TerritoryChina
CityShenyang
Period14/10/1516/10/15

Keywords

  • Contrast masking
  • Human Visual System
  • Image quality assessment
  • Medical image database

Fingerprint

Dive into the research topics of 'Medical image quality assessment via contrast masking'. Together they form a unique fingerprint.

Cite this