Using feature selection to aid an iconic search through an image database

In this paper a method that facilitates an iconic query of an image/video database is presented. A query object is characterised by colour and texture properties. The same characteristics are computed locally for the database images. A statistical decision rule is then used to test for similarity between the iconically specified query and the database image descriptors. We show that by carefully selecting the set of descriptors the false alarm rate can be significantly reduced. The floating search feature selection method has been adapted to make it applicable to the hypothesis testing based query processing. The dimensionality reduction not only improves the performance but also enhances the computational efficiency of the method