Video-based face identification using unconstrained non-linear composite filters

摘要

This paper considers the face identification task in video sequences where the individual’s face presents variations;such as expressions, pose, scale, shadow/lighting and occlusion. The principles of Synthetic DiscriminantFunctions (SDF) and K-Law filters are used to design an adaptive unconstrained correlation filter (AUNCF). Wedeveloped a face tracking algorithm which together with a face recognition algorithm were carefully integratedinto a video-based face identification method. First, a manually selected face in the first video frame is identified.Then, in order to build an initial correlation filter, the selected face is distorted so that it generates a training set.Finally, the face tracking task is performed using the initial correlation filter which is updated through the videosequence. The efficiency of the proposed method is shown by experiments on video sequences, where differentfacial variations are presented. The proposed method correctly identifies and tracks the face under observationon the tested video sequences.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.