Automatic Matting of Identification Photos

This paper proposes a framework for matting identification photos automatically. We firstly adopt image processing operations such as skin detection, k-means clustering, Grab cut segmentation and canny operator to generate a trimap with three regions, i.e., background, foreground and unknown regions. Then, we improve the Bayesian matting by introducing an alpha regularization term. Experiments demonstrate that our system can achieve about 86% acceptance rate for real photo datasets.