A fuzzy query based image retrieval system

An interactive content-based visual image retrieval system that can retrieve an image using a fuzzy description of colors and textures is presented in this paper. Each image in the image database is represented by its visual features: color and textual information. The user can pose a query in terms of colors and textures using natural language. As humans are more comfortable using linguistic terms without caring about the finer differences between classes, fuzzy queries can be useful to allow the incorporation of linguistic terms into descriptions of color and texture match degree. The experimental results demonstrate the effectiveness of our system for retrieving images from a large image database.