提出一种基于Gaussian-Hermite矩和人类视觉系统（HVS）特性融合的图像全参考质量评价方法。正交矩在图像处理和模式识别方面有很重要的作用。图像的低阶矩能很好地表征图像的特征，可用于图像质量的准确评价。该方法首先通过计算两幅图像间连续正交矩能量差异获得低阶矩特征；然后，结合HVS的掩盖效应对图像的不同区域分配不同权重；最后，对图像所有分区的连续正交矩能量差进行加权平均得到图像质量分数。在国际通用的图像质量评价数据集中，对所提出的方法进行测试。实验结果对比表明，该方法具有很好的效果。
We present a new full-reference image quality metric using Gaussian-Hermite moments and human visual system (HVS). Orthogonal moments are powerful tools in pattern recognition and image processing applications. Low-order moments well characterize features of an image and can be used to assess the image quality accurately. Firstly the proposed method obtains the feature of low-order moments through computing the continuous orthogonal moment energy differences between two images. Then, by combining the masking effect of human visual system (HVS), the different weighting factors are assigned to different areas in an image. Finally, image quality scores are derived by the weighted average of the continuous orthogonal moment energy differences in all the areas of the image. The performance of the proposed method is evaluated on several public databases. Experimental results and comparisons demonstrate the efficiency of the method.
[1] 蒋刚毅, 黄大江, 王旭,等. 图像质量评价方法研究进展[J]. 电子与信息学报, 2010, 32(1)：219-226.
[2] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[3] Wang Z, Bovik A C. A universal image quality index[J]. IEEE Signal Processing Letters, 2002, 9 (3): 81-84.
[4] Sheikh H R, Bovik A C. Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006, 15 (2):430-444.
[5] Wee C Y, Paramesran R, Mukundan R, et al. Image quality assessment by discrete orthogonal moments[J]. Pattern Recognition, 2010, 43(12):4 055-4 068.
[6] Mukundan R, Ong S H, Lee P A. Image analysis by Tchebichef moments[J]. IEEE Transactions on Image Processing, 2001, 10(9):1 357-1 364.
[7] Yap P T, Paramesran R, Ong S H. Image analysis by Krawtchouk moments[J]. IEEE Transactions on Image Processing, 2003, 12(11):1 367-1 377.
[8] Yang B, Dai M. Image analysis by Gaussian-Hermite moments[J]. Signal Processing, 2011, 91(10): 2 290-2 303.
[9] 吴金建. 基于人类视觉系统的图像信息感知和图像质量评价[D]. 西安：西安电子科技大学, 2014.
[10] Li L, Zhu H, Yang G, et al. Referenceless measure of blocking artifacts by tchebichef kernel analysis[J]. IEEE Signal Processing Letters, 2014, 21(1):122-125.
[11] Sheikh H R, Wang Z, Cormack L, et al. LIVE image quality assessment database release 2[EB/OL].(2006)[2017-01-15].http://live.ece.utexas.edu/research/quality.
[12] Larson E C, Chandler D M. Categorical subjective image quality CSIQ database[EB/OL]. (2009-04-24)[2017-01-15]. http://vision.okstate.edu/csiq/.
[13] Zaric A, Tatalovic N, Brajkovic N, et al. Vcl@fer image quality assessment database[J]. Automatika Journal for Control Measurement Electronics Compu, 2012,53(4):105-110.
