彩色视觉相似性图像评价方法

针对当前评价方法对彩色图像评价的不足，提出一种基于彩色视觉相似性的图像质量评价方法。首先通过把彩色图像转换到相对均匀的色空间（LAB2000HL），再根据视觉空间响应特性分别使用亮度对比度敏感函数（CSF）和色度CSF进行调整，获得各维图像的结构相似性（M-SSIM）指数，最后综合考虑色空间各维信息对彩色视觉质量影响的权重，建立综合评价指标现实彩色图像的质量评价。实验中，利用图像数据TID2008进行测试，并通过Spearman 等级相关系数和Kendall等级相关系数分析评价结果与其视觉主观评价的一致性。实验结果表明，与其他图像质量方法比较，所提方法的评价结果与视觉主观评价具有较高的一致性。

Color image quality assessment algorithm based on color structural similarity

Concerning the disadvantages of quality assessment algorithms for color images, a new algorithm based on visual structural similarity was proposed. Firstly, testing images were transformed into a selected uniform color space LAB2000HL. Secondly, one luminance Contrast Sensitivity Function (CSF) and two chromatic CSFs were used to filter images respectively. Thirdly, three structural similarity indexes were computed by multi-scale structural similarity index measurement (M-SSIM). Lastly, the proposed algorithm was constructed by weighting the three structural similarity indexes， which depended on different visual sensitivities of luminance and chromaticity. In the experiment, testing results on TID2008 database were compared with the results of visual assessment by Spearman rank-order correlation coefficient and Kendall rank-order correlation coefficient. The experimental results show that the proposed algorithm is more consistent with visual assessment and outperforms several other popular image quality assessment algorithms.