No-reference stereoscopic image quality assessment on both complex contourlet and spatial domain via Kernel ELM

作者：

Highlights：

• A novel NR-SIQA method is proposed using both complex contourlet and spatial domain features.

• A series of ‘quality-aware’ features are discovered in the complex contourlet domain.

• We combine monocular and binocular images to assess image quality.

摘要

•A novel NR-SIQA method is proposed using both complex contourlet and spatial domain features.•A series of ‘quality-aware’ features are discovered in the complex contourlet domain.•We combine monocular and binocular images to assess image quality.

论文关键词：No reference stereoscopic image quality assessment,Complex contourlet transform,Visual discomfort,CIELAB color space,Kernel extreme learning machine

论文评审过程：Received 21 April 2021, Revised 6 September 2021, Accepted 12 October 2021, Available online 16 November 2021, Version of Record 20 November 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116547