Image clustering based on multi-features joint learning

As one kind of popular application in computer vision, image clustering has attracted many attentions. Some machine learning algorithms have been widely employed, such as K-Means, Non-negative Matrix Factorization (NMF) and Graph regularized Non-negative Matrix Factorization (GNMF). These methods possess respective strength and weakness. The common problem in these clustering algorithms is that they only use one kind of feature. However, different kinds of features complement each other and can be used to improve performance results. In this paper, in order to make use of the complementarity between different features, we propose a multi-features joint learning algorithm for image clustering. Experimental results on several benchmark image data sets show that the proposed scheme outperforms some existing methods.