Global Semantic Classification of Scenes using Power Spectrum Templates

Abstract

Scene recognition and content-based procedures are of great interest for image indexing applications processing very large databases. Knowing the context of a scene, a retrieval system may compute its semantic category in advance and filter out scenes belonging to irrelevant classes. In this paper, we introduce a computational approach which classifies and organises real-world scenes along broad semantic axes. Fundamental to our approach is the computation of global spectral templates providing a continuous organisation of scenes between two categories. These templates encode the structure which is discriminant between two categories. We propose a hierarchical procedure of two stages, that organises images along three semantic axis. Firstly, all the scenes are classified according to an Artificial to Natural axis. Then, natural scenes are organised along the Open to Closed axis whereas artificial environments are classified according to the Expanded to Enclosed scenes axis.