MLSIM: A Multi-Level Similarity index for image quality assessment

作者：

Highlights：

• Human visual system (HVS) distinguishes the quality of an image mainly according to the details given by low-level gradient information.

• Gradient information of images is segmented into multi levels.

• Riesz transform is utilized to get key features of gradient information.

• Regional mutual information is utilized to combine corresponding coefficients of Riesz transform.

摘要

Highlights•Human visual system (HVS) distinguishes the quality of an image mainly according to the details given by low-level gradient information.•Gradient information of images is segmented into multi levels.•Riesz transform is utilized to get key features of gradient information.•Regional mutual information is utilized to combine corresponding coefficients of Riesz transform.

论文关键词：Image quality assessment (IQA),Riesz transform,Regional mutual information (RMI),Prewitt operator

论文评审过程：Received 1 November 2012, Revised 30 July 2013, Accepted 10 August 2013, Available online 26 August 2013.

论文官网地址：https://doi.org/10.1016/j.image.2013.08.006