Visual Fatigue Prediction for Stereoscopic Image

In this letter, we propose a visual fatigue prediction metric which can replace subjective evaluation for stereoscopic images. It detects stereoscopic impairments caused by inappropriate shooting parameters or camera misalignment which induces excessive horizontal and vertical disparities. Pearson´s correlation was measured between the proposed metrics and the subjective results by using k-fold cross-validation, acquiring ranges of 78-87% with sparse feature and 74-85% with dense feature.