一种抗模糊失真的结构相似度图像质量评价法*

作者：郑德品，沈海斌，赵武峰 日期：2007-10-25/span> 浏览：9403 查看PDF文档

一种抗模糊失真的结构相似度图像质量评价法*

郑德品，沈海斌，赵武峰
（浙江大学 超大规模集成电路设计研究所，浙江 杭州 310027）

摘要：针对人眼对不同图像纹理的敏感差异，提出了一种抗模糊失真的加权结构相似度(WSSIM)图像质量评价方法，它通过提取人眼敏感的边缘信息，将图像分割成不同区域，进行加权处理，获得加权结构相似度(WSSIM)，解决了SSIM对于严重模糊图像的评价问题。在LIVE图库中的高斯模糊库（Gaussian_Blur）与PSNR，SSIM，多尺度结构相似度(MS_SSIM)进行仿真比较。实验结果表明，WSSIM模型计算简单，评价性能远远优于前两种方法而略优于MS_SSIM。
关键词：峰值信噪比；结构相似度；多尺度结构相似度；图像质量评价；人类视觉系统
中图分类号：TN391文献标识码：A文章编号：1001-4551(2007)10-0082-03

A blur insensitive structural similarity for image quality assessment
ZHENG Depin, SHEN Haibin, ZHAO Wufeng
（Institute of VLSI Design, Zhejiang University, Hangzhou 310027, China）
Abstract: Considering different texture has different sensitivity for human eyes, a blur insensitive structural similarity model(WSSIM) was proposed, which based on edge to partition different weight region. Experimental comparisons with PSNR, SSIM and MS_SSIM on the LIVE database show that this appoach is simple to calculate, the performance is more excellent than PSNR,SSIM and better than MS_SSIM.
Key words: peak signalnoise ratio (PSNR); structural similarity (SSIM); multiscale structural similarity (MS_SSIM); image quality assessment (IQA); human visual system (HVS)

参考文献(Reference)：
［1］DALY S. The Visible Difference Predictor: an Algorithm for the Assessment of Image Fidelity, Digital Images and Human Vision［C］//A. B.Watson, Ed. Cambridge, MA: MIT Press,1993:179-206.
［2］GIROD B. Whats Wrong with Meansquared Error, Digital Images and Human Vision［C］//A. B. Watson, Ed. Cambridge, MA: MIT Press,1993:207-220.
［3］TEO P C, HEEGER D J. Perceptual Image Distortion［C］. Proc of SPIE, 1994,2179:127-141.
［4］李彦丽, 金东瀚, 焦秉立. 几种典型的感知视频质量评价模型［J］. 计算机工程与应用, 2002,38(13)：66-68.
［5］BOVIK A C. Handbook of Image and Video Processing: Second Edition［M］. New York: Academic Press,2005.
［6］ZHOU W, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity［J］. IEEE Transactions on Image Processing, Apr. 2004,13(4):600-612.
［7］ZHOU W, SIMONCELLI E P. Translation Insensitive Image Similarity in Complex Wavelet  Domain［C］//Proc of IEEE, ICASSP’2005:573-576.
［8］ZHOU W, SIMONCELLI E P, BOVIK A C. Multiscale Structural Similarity for Image Quality Assessment［C］//Proc of IEEE Asilomar Conference on Signals, Systems and Computers, 2003(2):1398-1402.
［9］SHEIKH H R, ZHOU W. CORMACK L, et al, “LIVE Image Quality Assessment Database Release2”［EB/OL］. ［2007-02-19］. http://live.ece.utexas.edu/research/quality.
［10］PENG Jinye, ZHANG Yubian. Multiscale Bayesian Face Recognition by Using Antisymmetrical Biorthogonal Wavelets［C］//Proc of IEEE on Infotech and Infonet(ICII2001), 2001,3:414-420.
［11］ZHOU W, SIMONCELLI E P. Stimulus Synthesis for Efficient Evaluation and Refinement of Perceptual Image Quality Metrics［C］. Proceedings of SPIE,2004,5292.
［12］VQEG PHASE II. Final Report From the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment. ［EB/OL］. ［2005-01-10］. http://www.its.bldrdoc.gov/vqeg.