基于视觉感知的梯度结构相似度图像质量评价

Image quality assessment based on visual perception and gradient structural similarity

在SSIM算法的基础上,结合亮度和对比度掩蔽等视觉感知信息构造视觉感知(visual perception)函数,提出基于视觉感知的梯度结构相似度评价方法VI_GSSIM(visual perception and gradient based SSIM)。该方法通过图像质量与图像内容和失真类型的相关性,结合图像的误差可视性与内容可视性构造视觉感知函数,对HVS底层视觉系统建模;同时利用梯度重新定义结构信息,得到基于视觉感知的梯度结构相似度模型,对图像进行质量评价。实验结果表明,提出的VI_GSSIM算法比SSIM更符合人眼的视觉特性,尤其适合评价降质较严重的图像。

This paper proposed a new metric of image quality assessment based on visual perception and gradient structural similarity（VI_GSSIM）,which was a combination of visual perception information based on luminance and contrast masking effect.This method used the relevance between image quality and image content and distortion type of a degraded image,constructed visual perception with error visible and content visible to build a low-level HVS perception model,and then redefined structure information with image gradient to come into being the algorithm.The experimental results indicate that VI_GSSIM algorithm is more corresponding to the human visual system,especially suits to evaluate heavy distorting degraded image.