Supervised non-negative matrix factorization based latent semantic image indexing

摘要

A novel latent semantic indexing (LSI) approach for content-based image retrieval is presented in this paper. Firstly, an extension of non-negative matrix factorization (NMF) to supervised initialization is discussed. Then, supervised NMF is used in LSI to find the relationships between low-level features and high-level semantics. The retrieved results are compared with other approaches and a good performance is obtained.