Incremental orthogonal projective non-negative matrix factorization and its applications

Abstract

In this paper, we propose an incremental orthogonal projective non-negative matrix factorization algorithm (IOPNMF), which aims to learn a parts-based subspace that reveals dynamic data streams. There exist two main contributions. Firstly, our proposed algorithm can learn parts-based representations in an online fashion. Secondly, by using projection and orthogonality constrains, our IOPNMF algorithm can guarantee to learn a linear parts-based subspace. To demonstrate the effectiveness of our method, we conduct two kinds of experiments, incremental learning parts-based components on facial database and visual tracking on several challenging video clips. The experimental results show that our IOPNMF algorithm learns parts-based representations successfully.