On Predicting Visual Comfort of Stereoscopic Images: A Learning to Rank Based Approach

• Published in: IEEE signal processing letters Vol. 23; no. 2; pp. 302 - 306
• Main Authors: Jiang, Qiuping, Shao, Feng, Lin, Weisi, Jiang, Gangyi
• Format: Journal Article
• Language: English
• Published: IEEE 01.02.2016
• Subjects: absolute categorical rating (ACR); Context; Feature extraction; learning to rank (L2R); Measurement; Observers; qualitative description behavior; Retina; Stereo image processing; Stereoscopic images; visual comfort assessment (VCA); Visualization; qualitative description behavior; Absolute categorical rating (ACR); learning to rank (L2R); stereoscopic images; visual comfort assessment (VCA)
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2016.2516521

Predicting the degree of experienced visual comfort in the context of stereoscopic 3-D (S3D) viewing is particularly challenging. In this letter, a simple yet effective visual comfort assessment (VCA) approach for stereoscopic images is proposed from the perspective of learning to rank (L2R). The proposed L2R-based VCA (L2R-VCA) approach is inspired by the traditional absolute categorical rating (ACR) methodology in subjective study and is to characterize the qualitative description behavior of human subjective study. Experimental results on our recently built database confirm the promising performance of the proposed L2R-VCA approach, yielding higher consistency with human subject judgment results.