Self-organising maps as a relevance feedback technique in Content-Based Image Retrieval

Self-Organising Maps (SOMs) can be used in implementing a powerful relevanc e feedback mechanism for Content-Based Image Retrieval (CBIR). This payer i ntroduces the PicSOM CBIR system, and describes the use of SOMs as a releva nce feedback technique in it. The technique is based on the SOM's inherent property of topology-preserving mapping from a high-dimensional feature spa ce to a two-dimensional grid of artificial neurons. On this grid similar im ages are mapped in nearby locations. As image similarity must, in unannotat ed databases, he based on low-level visual features, the similarity of imag es is dependent on the feature extraction scheme used. Therefore in PicSOM there exists a separate tree-structured SOM for each different feature type . The incorporation of the relevance feedback and the combination of the ou tputs from the SOMs are performed as two successive processing steps. The p roposed relevance feedback technique is described, analysed qualitatively. and visualised in the paper. Also, its performance is compared with a refer ence method.