Semantic-aware blind image quality assessment

作者：

Highlights：

•

• User’s judgment of visual quality is shown to be influenced by image semantics.

• Adding semantic features to blind image quality metrics improve their performances.

• A semantic-aware image quality dataset is proposed.

摘要

•User’s judgment of visual quality is shown to be influenced by image semantics.•Adding semantic features to blind image quality metrics improve their performances.•A semantic-aware image quality dataset is proposed.

论文关键词：Blind image quality assessment,No-reference image quality metrics (NR-IQM),Quality of experience (QoE),Image semantics,Subjective quality datasets

论文评审过程：Received 16 May 2017, Revised 16 October 2017, Accepted 16 October 2017, Available online 26 October 2017, Version of Record 9 November 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.10.009