Facial image clustering in stereoscopic videos using double spectral analysis
作者：
Highlights：
• We developed a facial image clustering algorithm for stereoscopic videos.
• A double spectral analysis was used for performing the clustering.
• Features that were used included both global (Mutual Information based) and local (Local Binary Patterns).
• Facial image trajectory information was also used in clustering.
• Best results occurred for local features and multiple representative images per facial image trajectory.
摘要
Author-Highlights•We developed a facial image clustering algorithm for stereoscopic videos.•A double spectral analysis was used for performing the clustering.•Features that were used included both global (Mutual Information based) and local (Local Binary Patterns).•Facial image trajectory information was also used in clustering.•Best results occurred for local features and multiple representative images per facial image trajectory.
论文关键词：Stereoscopic video,Stereo facial image clustering,Spectral clustering,Local binary patterns,Local features,Facial fiducial points
论文评审过程：Received 11 July 2014, Revised 24 December 2014, Accepted 26 January 2015, Available online 7 February 2015.
论文官网地址：https://doi.org/10.1016/j.image.2015.01.009
