Image annotation using multi-view non-negative matrix factorization and semantic co-occurrence

Image annotation aims to automatically predict a set of relevant keywords for an image that describe its semantics. Nearest Neighbor (NN) based methods have been successfully applied to address image annotation problems. In this paper,a novel method is introduced to improve the performance of annotating images. Firstly, we present a relevance feedback algorithm based on Multi-view non-negative matrix factorization (MultiNMF) to improve the retrieval performance during the process of querying the nearest neighbors. Secondly, a semantic co-occurrence (SC) based strategy is derived to effectively adjust the order of the annotated keywords. Experiment results on Corel5K dataset demonstrate that the proposed method outperforms those previous similar methods.