Fast constrained person identity label propagation in stereo videos using a pruned similarity matrix

In this paper, a novel video data (more specifically facial images) fast labeling method, that aims in the acceleration of a state of the art facial identity label propagation technique is presented. Our method assumes that facial images are derived by applying facial image tracking on stereoscopic videos and thus are temporally ordered. The proposed method utilizes a pruned similarity matrix so that the facial label inference is conducted using fewer entries in this matrix, namely the pairwise similarities of the facial images that exist in the main and the N upper and lower off-diagonals. The proposed method can also incorporate pairwise facial image similarity and dissimilarity constraints into the objective function of the label propagation. Experiments which have been conducted on facial image labeling in three stereoscopic movies, confirm the increased labeling accuracy and the reduced computational cost of the proposed method.