Non-negative matrix factorisation for object class discovery and image auto-annotation

In information retrieval, sub-space techniques are usually used to reveal the latent semantic structure of a data-set by projecting it to a low dimensional space. Non-negative matrix factorisation (NMF), which generates a non-negative representation of data through matrix decomposition, is one such technique. It is different from other similar techniques, such as singular vector decomposition (SVD), in its nonnegativity constraints which lead to its parts-based representation characteristic. In this paper, we present the novel use of NMF in two tasks; object class detection and automatic annotation of images. Experimental results imply that NMF is a promising sub-space technique for discovering the latent structure of image data-sets, with the ability of encoding the latent topics that correspond to object classes in the basis vectors generated. Categories and Subject Descriptors I.5 [Pattern Recognition]: Miscellaneous ; H.3.1 [Information Storage and Retrieval]: Content Analysis and...

• Type: Conference
• Year: 2008
• Where: CIVR
• Authors: Jiayu Tang, Paul H. Lewis
• Keywords: CIVR 2008, Image Analysis, Latent Semantic Structure, Non-negative Matrix Factorisation, Sub-space Technique