基于相位一致结构相似度的图像质量评价方法

针对结构相似度(SSIM)模型不能对模糊和高纹理图像进行较好的质量评价，提出一种基于相位一致结构相似度(MPCSSIM)的全参考图像质量评价方法。该方法保留SSIM中的亮度函数和对比度函数，将结构函数替换成相位一致函数，然后将三者结合起来进行质量评价。实验中LIVE数据库上的计算结果与主观评分的线性相关系数和斯皮尔曼相关系数分别为0.9501和0.9362。实验结果表明相位一致能够更好地提取图像的结构信息，该方法有较好的性能，能够更准确地评价模糊图像和高纹理图像的质量。

Image quality assessment based on phase congruency structural similarity

Concerning the poor image quality evaluation of Structural SIMilarity(SSIM) for blurred images and high texture images,this paper proposed a new algorithm for full reference image quality assessment based on phase congruency structural similarity.The new method kept luminance function and contrast function in SSIM,while replaced the structural function of SSIM with phase congruency function.Then the luminance,contrast and phase congruency information were combined to evaluate the image quality.The linear correlation coefficient and the Spearman rank correlation coefficient between the results of the proposed method on LIVE database and the subjective quality measurements were 0.950 1 and 0.936 2 respectively.The experimental results demonstrate that phase congruency obtains more structural information of the image.The proposed method can obtain better performances and provide more accurate assessment results on burred and high texture images quality.