一种针对图像模糊的无参考质量评价指标

No-reference quality index for image blur

在成像模型的基础上,分析了图像模糊的原因,提出了一种为图像构造参考图像的方法,进而将结构相似度(SSIM)评价方法引入到无参考图像质量评价中,提出一种无参考结构清晰度(NRSS)的新的无参考图像质量评价方法,将其用于对模糊图像的质量评价。该方法通过低通滤波器来构造参考图像,通过计算原始图像与参考图像的结构相似度值来评价原始图像质量,很好地结合了成像系统的数学模型和结构相似度评价方法的优势,实验结果表明无参考结构清晰度评价指标能够给出和主观评价方法以及其余有参考评价方法一致的结果。

With the analysis of image blur based on the imaging model,a method was proposed for constructing reference images,and at the same time the Structural Similarity（SSIM）index was introduced into no-reference image quality assessment.A novel no-reference image quality assessment index called No-Reference Structural Sharpness（NRSS）was then proposed for quality evaluation of blurred images.This method constructed a reference image by a low-pass filter,and assessed the image quality by computing the SSIM between the original image and the reference one,thus considering the mathematical model of imaging system as well as the advantages of SSIM.The experimental results show that the new index is well in accordance with quality assessment results of both subjective evaluation and full-reference methods.