Full-reference IPTV image quality assessment by deeply learning structural cues

作者：

Highlights：

• We leverage structural cues to calculate the similarity between the original image and the test one.

• A novel distance metric is proposed to measure the difference between the reference image and each test image.

• We propose a structure-preserved deep neural networks to extract deep representation from these images.

摘要

•We leverage structural cues to calculate the similarity between the original image and the test one.•A novel distance metric is proposed to measure the difference between the reference image and each test image.•We propose a structure-preserved deep neural networks to extract deep representation from these images.

论文关键词：Full-reference IQA,IPTV,Distance metric,Structural information,Deep model

论文评审过程：Received 30 June 2019, Revised 25 December 2019, Accepted 1 January 2020, Available online 11 January 2020, Version of Record 28 February 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115779