Semantic Categorization and Retrieval of Images

We propose a semantically based set of visual features, their relevance and organization for capturing the semantics of images from different categories. Our goal is to design a set of low-level descriptors that is linked to human perception of image content. The low-level descriptors are automatically associated with intermediate semantic descriptors. The intermediate descriptors are used, also for image categorization and for qualitative definition of semantic keywords in the user queries. These features are used in conjunction with a relevance feedback mechanism. The support vector machine uses the low -level descriptors of the images selected as relevant by user for producing the final query results.