基于视觉相似性的去色图像质量评估

针对基于结构相似性的去色图像质量评估算法没有充分利用图像的梯度特征且采用的对比度相似度特征会忽略图像连续颜色块的一致性导致算法与人类视觉主观判定有较大出入的问题，提出一种基于图像视觉相似性的去色图像质量评估算法--C2G-VSIM。该算法以彩色图像为参考图像，由不同去色算法产生的与之相关的去色灰度图像作为测试图像，对参考图像以及测试图像进行颜色空间转换，并且进行高斯滤波，充分考虑了图像亮度相似度和结构相似度特征，并在此基础上首先引入一种新的颜色一致性对比特征以促使C2G-VSIM对全局颜色对比度特征进行捕捉，其次引入梯度幅值特征至C2G-VSIM中以提高算法对图像梯度特征的敏感度，最后联合得到图像质量评估因子C2G-VSIM。在Cadík的数据集上的实验结果表明，C2G-VSIM与人类视觉主观评定的等级相关性在准确度和主观评判喜爱度上分别达到了0.8155和0.7634，相对于基于彩色图和灰度图的结构相似性（C2G-SSIM）评估算法在未增加较大耗时的情况下，准确度有明显提高。所提算法与人类视觉主观判定具有较高的一致性，且计算简单，在实际工程中能大规模且有效地对去色图像进行自动化评分。

Objective quality assessment for color-to-gray images based on visual similarity

The Color-to-Gray (C2G) image quality evaluation algorithm based on structural similarity does not make full use of the gradient feature of the image, and the contrast similarity feature ignores the consistency of the continuous color blocks of the image, thus leading to a large difference between the algorithm and the subjective judgment of human vision. A C2G image quality evaluation algorithm named C2G Visual Similarity Index Measurement (C2G-VSIM) was proposed based on Human Visual System (HVS). In this algorithm, the color image was regarded as the reference image, the corresponding decolorization image obtained by different algorithms was regarded as the test image. By applying color space conversion and Gaussian filtering to these reference and test images, taking full account of the characteristics of image brightness similarity and structual similarity, a new color consistency contrast feature was introduced to help C2G-VSIM to capture the global color contrast feature; then the gradient amplitude feature was also introduced into C2G-VSIM to improve the sensitivity of the algorithm to the image gradient feature. Finally, by combining those above features, a new imgage quality evaluation operator named C2G-VSIM was obtained. Experimental results on Cadík's dataset showed that in terms of accuracy and preference evaluation, the Spearman Rank Order Correlation Coefficient (SROCC) between C2G-VSIM and subjective assessment of human visuality was 0.8155 and 0.7634, respectively, the accuracy was improved significantly without increasing the time consuming compared to C2G Structure Similarity Index Measurement (C2G-SSIM). The proposed algorithm has high consistency compared to human visuality, as well as simple calculation, which can effectively and automatically evaluate decolorization images in actual project with large scale.