关键词: 图像质量评价, 成像模型, 结构相似度, 无参考结构清晰度, 梯度能量函数

Abstract: 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.

Key words: Image Quality Assessment (IQA), imaging model, Structural Similarity (SSIM), No-Reference Structural Sharpness (NRSS), energy function of gradient