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.