Visual comfort assessment of stereoscopic images with multiple salient objects

This paper focuses on discomfort assessment issue for S3D images with multiple salient objects, and proposes four kinds of visual features of S3D images that have potential correlations with visual discomfort, including disparity distribution features, disparity jump features, object distribution features as well as object width features. A stereoscopic image database is designed focusing on multiple salient object scenarios and prediction model is built using support vector regression based on the proposed features. Prediction performance evaluation result shows that the proper combinations of the proposed features can achieve effective visual discomfort prediction for these types of pictures, and also shows that the convergence adjustments induced by the disparity discrepancies among the salient objects do cause visual discomfort in these scenarios.