Visual Information retrieval is attracting an increasing number of researchers from disparate fields, like image analysis, computer vision, databases, knowledge representation, artificial intelligence, and man-machine interaction. Although a number of prototype systems have been made available, recently, nevertheless, this discipline has not yet reached a mature stage, and over-all has not yet been credited as of concrete use in practical applications. Among the very many different lines of development, we focus particularly on the importance of bridging the semantic gap between the user and visual information retrieval systems. We focus on usage of semiotics as a framework for extraction of semantics, graphs and graph matching as the representation model and retrieval engine and visualization spaces to capture semantics during the interaction.