Perceptual stereoscopic image quality assessment method with tensor decomposition and manifold learning. Issue 5 (1st May 2018)

• Record Type: Journal Article
• Authors: Jiang, Gangyi; He, Meiling; Yu, Mei; Shao, Feng; Peng, Zongju
• Is Part Of: IET image processing. Volume 12:Issue 5(2018)
• Page Start: 810
• Page End: 818
• Publication Date: 2018-05-01
• Subjects: image colour analysis -- stereo image processing -- learning (artificial intelligence) -- tensors -- matrix algebra -- visual perception; perceptual stereoscopic image quality assessment method -- tensor decomposition -- manifold learning -- left view quality -- right view quality -- prediction deviation -- asymmetrically distorted stereoscopic images -- human visual perception -- low‐dimensional manifold -- perceptual SIQA method -- training stage -- quality prediction stage -- Tucker decomposition -- RGB images -- dimension reduction -- colour channels -- training sets -- projection matrix -- binocular visual characteristics -- monocular image quality -- overall stereoscopic estimate -- local energy ratio based pooling strategy -- cyclopean based binocular quality -- benchmark databases; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0650
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Perceptual quality assessment of stereoscopic images is a challenge in three‐dimensional video systems. Existing studies suggest that simply averaging the quality of left and right views can effectively predict the quality of symmetrically distorted stereoscopic images, but prediction deviation occurs in the case of asymmetrically distorted stereoscopic images. Most previous stereoscopic image quality assessment (SIQA) methods have been based only on the luminance component of the images; in addition, the basis of human visual perception is critical to image quality assessment and lies on the low‐dimensional manifold. Inspired by this, a new perceptual SIQA method is proposed, which includes two stages: training stage and quality prediction stage. In the training stage, the authors apply Tucker decomposition to RGB images to reduce dimensions along colour channels to produce training sets, and the projection matrix is obtained through manifold learning. In the quality prediction stage, considering the binocular visual characteristics of visual perception, the overall stereoscopic estimate depends on the monocular image quality via a local energy ratio based pooling strategy and cyclopean based binocular quality. Extensive experiments on three available benchmark databases demonstrate that the proposed metric has better performance and achieves highly consistent alignment with subjective assessment compared with state‐of‐the‐art SIQA metrics.