Medical Fusion Image Quality Assessment Based on SSIM
The assessment of image quality is important in numerous image processing applications. Commonly used measures, such as the mean squared error (MSE) and peak signal to noise ratio (PSNR), ignore the spatial information (e.g. redundancy) contained in natural images, which can lead to an inconsistent similarity evaluation from the human visual perception. image similarity indices evaluate how much structural information is maintained by a processed image in relation to a reference image, the Structural Similarity Image (SSIM) operate under the assumption that human visual perception is highly adapted for extracting structural information from a scene. In this article, we propose a new similarity measure that replaces traditional methods to evaluate medical fusion image. Experimental results show that SSIM provides a more consistent image structural fidelity measure than commonly used measures and the consistency of people’s subjective feeling better.
KeywordsSSIM Quality assessment Image fusion
This research is supported by the Ministry of education Chunhui project (Z2009-1-01033), Natural Science Foundation of Department of Education, Natural Science Foundation of Inner Mongolia (2010MS0907).
- 1.Zhu Dalong, Ming Jun (2006) Image quality evaluation method based on structural distortion. Comput Technol Develop 2:56–58Google Scholar
- 2.Cui Yanmei, Ni Guoqiang et al (2000) Image fusion analysis and evaluation using statistical characteristics. Beijing Univ Technol J 20:102–106Google Scholar
- 3.Hu Yuanyuan, Niu Xiamu (2010) Image quality assessment algorithm based on the visual threshold of structural similarity. Shenzhen Univ J 2:185–191Google Scholar
- 4.Zhou Wang, Conrad Bovik (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 23:600–612Google Scholar
- 5.Zhang Yong, Jin Weiqi (2011) Image fusion evaluation method based on structural similarity with the region of interest. Photonics Technol 3:311–315Google Scholar
- 6.YANG Chunling, Gao Rui (2009) Image quality assessment based on structure similarity in wavelet domain. Electron Technol 1:845–849Google Scholar