Face clustering in videos based on spectral clustering techniques
Christina Chrysouli, Nicholas Vretos, Ioannis Pitas · 2011
In this paper we propose a novel algorithm for face clustering using spectral graph clustering in order to split and merge a similarity graph. The proposed method makes use of the mutual information-based image similarity. Face clusters are formed based on spectral graph clustering in a two step process. We begin by partitioning the dataset into clusters. A novel adaptive way is proposed for spectral clustering. Then merge is performed using spectral graph clustering on the partitioned clusters, by considering merging only two clusters at a time. Experiments on various video databases containing actors' facial images are conducted. The evaluation of the face clustering provided very good results.