Graphics Reference
In-Depth Information
Table 4.
PLCC
Algorithm\Distortion JP2K JPEG WN
Blur
FF
ALL
PSNR
0.9227
0.9020
0.9291
0.7736 0.8913 0.8837
SSIM
0.9295
0.9108
0.9059 0.9113 0.9446 0.9204
MS-SSIM
0.9230 0.9018 0.8363 0.7999 0.7896 0.8501
FSIM
0.9217 0.9034 0.8730
0.9604 0.9498 0.9217
RFSIM
0.9338
0.9091 0.9125 0.9037 0.9260 0.9170
SIFT-SSIM
0.9362 0.9180 0.9237 0.9155 0.9529 0.9293
In Tables above, we make the most prominent data bold. It is clear that the pro-
posed algorithm in two distortions of JPEG and FF has achieved the best results, its
overall performance exceeds to most algorithms, and it can be compared with FSIM.
4
Conclusion
Aims to ignorance features of the structural similarity algorithm, and while SIFT fea-
tures have a variety of invariant and scalability, we consider to build comprehensive
image quality assessment index with structural similarity and SIFT features. SIFT-
SSIM of full reference algorithm was proposed, and experiments verify its high
performance.
Acknowledgement.
This work is supported by the Anhui Natural Science Foundation
of China (Grant No. 1208085MF97).
References
1.
Pang, L.-L., Li, C.-L., Luo, J.: Summary of Image Quality assessment Technology. Avio-
nics Technology 42(2), 31-35 (2011)
2.
VQEG. Final report from VQEG on the validation of objective models of video quality as-
sessment (March 15, 2000),
http://www.its.bldrdoc.gov/vqeg/projects/
frtv_phaseII/downloads/VQEGII_Final_Peport.pdf
3.
Wang, Z., Alan, C.B., Hamid, R.S.: Image quality assessment: from error visibility to struc-
tural similarity. IEEE Transactions on Image Processing 13(4), 600-612 (2004)
4.
Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multi-scale structural similarity for image quality
assessment. In: IEEE Asilomar Conference on Signals, Systems and Computers,
pp. 1398-1402 (2003)
5.
Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: A feature similarity index for image qual-
ity assessment. IEEE Transactions on Image Processing 20(8), 2378-2386 (2011)
6.
Zhang, L., Zhang, L., Mou, X.: RFSIM: a feature based image quality assessment metric
using Riesz transforms. In: Proc. IEEE International Conference on Image Processing,
pp. 321-324 (2010)
Search WWH ::
Custom Search